From 8372e2da8a99ea79e7cefe5185819ecf13744332 Mon Sep 17 00:00:00 2001 From: yifanmai <185227+yifanmai@users.noreply.github.com> Date: Wed, 3 Jun 2026 22:35:59 +0000 Subject: [PATCH] Build frontend --- .../{index-6sfOSsz5.js => index-C3aFzfEs.js} | 4 +-- .../{react-BhnNyHuP.js => react-D3IQTVQZ.js} | 26 +++++++++---------- ...kIsf0iIR.js => react-markdown-DTLembof.js} | 2 +- ...harts-Bmm96ixf.js => recharts-DhnSad7c.js} | 2 +- ...{tremor-DyW3D1Ox.js => tremor-B1ftEuaD.js} | 2 +- src/helm/benchmark/static_build/index.html | 10 +++---- 6 files changed, 23 insertions(+), 23 deletions(-) rename src/helm/benchmark/static_build/assets/{index-6sfOSsz5.js => index-C3aFzfEs.js} (71%) rename src/helm/benchmark/static_build/assets/{react-BhnNyHuP.js => react-D3IQTVQZ.js} (78%) rename src/helm/benchmark/static_build/assets/{react-markdown-kIsf0iIR.js => react-markdown-DTLembof.js} (99%) rename src/helm/benchmark/static_build/assets/{recharts-Bmm96ixf.js => recharts-DhnSad7c.js} (99%) rename src/helm/benchmark/static_build/assets/{tremor-DyW3D1Ox.js => tremor-B1ftEuaD.js} (99%) diff --git a/src/helm/benchmark/static_build/assets/index-6sfOSsz5.js b/src/helm/benchmark/static_build/assets/index-C3aFzfEs.js similarity index 71% rename from src/helm/benchmark/static_build/assets/index-6sfOSsz5.js rename to src/helm/benchmark/static_build/assets/index-C3aFzfEs.js index 1ffd6c3925f..7d0cbb4e4ff 100644 --- a/src/helm/benchmark/static_build/assets/index-6sfOSsz5.js +++ b/src/helm/benchmark/static_build/assets/index-C3aFzfEs.js @@ -1,2 +1,2 @@ -import{j as e,g as F,c as z,m as ae,s as je,b as $e,p as me,y as De,a as ue,d as re,e as le}from"./tremor-DyW3D1Ox.js";import{d as Be,g as Oe,r as i,L as b,O as Fe,u as ie,e as be,f as Ue,H as qe,h as We,i as P,R as ze}from"./react-BhnNyHuP.js";import{R as Ve}from"./react-markdown-kIsf0iIR.js";import"./recharts-Bmm96ixf.js";(function(){const t=document.createElement("link").relList;if(t&&t.supports&&t.supports("modulepreload"))return;for(const r of document.querySelectorAll('link[rel="modulepreload"]'))n(r);new MutationObserver(r=>{for(const o of r)if(o.type==="childList")for(const l of o.addedNodes)l.tagName==="LINK"&&l.rel==="modulepreload"&&n(l)}).observe(document,{childList:!0,subtree:!0});function a(r){const o={};return r.integrity&&(o.integrity=r.integrity),r.referrerPolicy&&(o.referrerPolicy=r.referrerPolicy),r.crossOrigin==="use-credentials"?o.credentials="include":r.crossOrigin==="anonymous"?o.credentials="omit":o.credentials="same-origin",o}function n(r){if(r.ep)return;r.ep=!0;const o=a(r);fetch(r.href,o)}})();var G={},xe;function Je(){if(xe)return G;xe=1;var s=Be();return G.createRoot=s.createRoot,G.hydrateRoot=s.hydrateRoot,G}var Ge=Je();const Qe=Oe(Ge);function Ze({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"M3.75 6.75h16.5M3.75 12h16.5m-16.5 5.25h16.5"}))}const ve=i.forwardRef(Ze);function Ke({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"M9 12.75 11.25 15 15 9.75M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"}))}const Xe=i.forwardRef(Ke);function Ye({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"m9.75 9.75 4.5 4.5m0-4.5-4.5 4.5M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"}))}const es=i.forwardRef(Ye),we=""+new URL("crfm-logo-Du4T1uWZ.png",import.meta.url).href,Ne=""+new URL("helm-logo-simple-DzOhNN41.png",import.meta.url).href;function ss({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M12 2.25a.75.75 0 0 1 .75.75v11.69l3.22-3.22a.75.75 0 1 1 1.06 1.06l-4.5 4.5a.75.75 0 0 1-1.06 0l-4.5-4.5a.75.75 0 1 1 1.06-1.06l3.22 3.22V3a.75.75 0 0 1 .75-.75Zm-9 13.5a.75.75 0 0 1 .75.75v2.25a1.5 1.5 0 0 0 1.5 1.5h13.5a1.5 1.5 0 0 0 1.5-1.5V16.5a.75.75 0 0 1 1.5 0v2.25a3 3 0 0 1-3 3H5.25a3 3 0 0 1-3-3V16.5a.75.75 0 0 1 .75-.75Z",clipRule:"evenodd"}))}const ts=i.forwardRef(ss);function as({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M15.75 2.25H21a.75.75 0 0 1 .75.75v5.25a.75.75 0 0 1-1.5 0V4.81L8.03 17.03a.75.75 0 0 1-1.06-1.06L19.19 3.75h-3.44a.75.75 0 0 1 0-1.5Zm-10.5 4.5a1.5 1.5 0 0 0-1.5 1.5v10.5a1.5 1.5 0 0 0 1.5 1.5h10.5a1.5 1.5 0 0 0 1.5-1.5V10.5a.75.75 0 0 1 1.5 0v8.25a3 3 0 0 1-3 3H5.25a3 3 0 0 1-3-3V8.25a3 3 0 0 1 3-3h8.25a.75.75 0 0 1 0 1.5H5.25Z",clipRule:"evenodd"}))}const ns=i.forwardRef(as);function rs({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M15 3.75a.75.75 0 0 1 .75-.75h4.5a.75.75 0 0 1 .75.75v4.5a.75.75 0 0 1-1.5 0V5.56l-3.97 3.97a.75.75 0 1 1-1.06-1.06l3.97-3.97h-2.69a.75.75 0 0 1-.75-.75Zm-12 0A.75.75 0 0 1 3.75 3h4.5a.75.75 0 0 1 0 1.5H5.56l3.97 3.97a.75.75 0 0 1-1.06 1.06L4.5 5.56v2.69a.75.75 0 0 1-1.5 0v-4.5Zm11.47 11.78a.75.75 0 1 1 1.06-1.06l3.97 3.97v-2.69a.75.75 0 0 1 1.5 0v4.5a.75.75 0 0 1-.75.75h-4.5a.75.75 0 0 1 0-1.5h2.69l-3.97-3.97Zm-4.94-1.06a.75.75 0 0 1 0 1.06L5.56 19.5h2.69a.75.75 0 0 1 0 1.5h-4.5a.75.75 0 0 1-.75-.75v-4.5a.75.75 0 0 1 1.5 0v2.69l3.97-3.97a.75.75 0 0 1 1.06 0Z",clipRule:"evenodd"}))}const ls=i.forwardRef(rs);function is({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M12.53 16.28a.75.75 0 0 1-1.06 0l-7.5-7.5a.75.75 0 0 1 1.06-1.06L12 14.69l6.97-6.97a.75.75 0 1 1 1.06 1.06l-7.5 7.5Z",clipRule:"evenodd"}))}const ye=i.forwardRef(is);function os({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M11.47 4.72a.75.75 0 0 1 1.06 0l3.75 3.75a.75.75 0 0 1-1.06 1.06L12 6.31 8.78 9.53a.75.75 0 0 1-1.06-1.06l3.75-3.75Zm-3.75 9.75a.75.75 0 0 1 1.06 0L12 17.69l3.22-3.22a.75.75 0 1 1 1.06 1.06l-3.75 3.75a.75.75 0 0 1-1.06 0l-3.75-3.75a.75.75 0 0 1 0-1.06Z",clipRule:"evenodd"}))}const Le=i.forwardRef(os);function cs({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M10.5 3.75a6.75 6.75 0 1 0 0 13.5 6.75 6.75 0 0 0 0-13.5ZM2.25 10.5a8.25 8.25 0 1 1 14.59 5.28l4.69 4.69a.75.75 0 1 1-1.06 1.06l-4.69-4.69A8.25 8.25 0 0 1 2.25 10.5Z",clipRule:"evenodd"}))}const ds=i.forwardRef(cs);function oe(s,t){return t?t==="home"?"https://crfm.stanford.edu/helm/":s?`https://crfm.stanford.edu/helm/${t}/${s}/`:`https://crfm.stanford.edu/helm/${t}/latest/`:"#"}function Me(){const[s,t]=i.useState([]),[a,n]=i.useState();return i.useEffect(()=>{if(a&&a.title&&a.title!=="All Leaderboards"){const r=a.title==="Lite"||a.title==="Classic"?"HELM "+a.title:a.title;document.title=r+" - Holistic Evaluation of Language Models (HELM)"}},[a]),i.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(r=>r.json()).then(r=>{if(t(r),window.PROJECT_ID){const o=r.find(l=>l.id===window.PROJECT_ID);n(o)}else{const o=r.find(l=>l.id==="lite");n(o)}}).catch(r=>{console.error("Error fetching JSON:",r)})},[]),a===void 0||a.title===void 0?null:e.jsxs("div",{className:"dropdown z-50",children:[e.jsxs("div",{tabIndex:0,role:"button",className:"btn normal-case bg-white font-bold p-2 border-0 text-lg block whitespace-nowrap z-40","aria-haspopup":"true","aria-controls":"menu",children:[a.title," ",e.jsx(ye,{fill:"black",color:"black",className:"text w-4 h-4 inline"})]}),e.jsx("ul",{tabIndex:0,className:"-translate-x-36 dropdown-content z-[1] menu p-1 shadow-lg bg-base-100 rounded-box w-max text-base",role:"menu",children:s.map((r,o)=>e.jsx("li",{className:"z-40",children:e.jsxs("a",{href:oe(void 0,r.id),className:"block",role:"menuitem",children:[e.jsx("strong",{className:a.title===r.title?"underline":"",children:r.title}),": ",r.description]})},o))})]})}function A(s){return s.startsWith("http://")||s.startsWith("https://")?s:`${window.BENCHMARK_OUTPUT_BASE_URL.replace(/\/$/,"")}/${s.replace(/^\//,"").split("/").map(t=>encodeURIComponent(t)).join("/")}`}function J(){return window.RELEASE?`/releases/${window.RELEASE}`:`/runs/${window.SUITE}`}async function hs(s){try{return await(await fetch(A(`${J()}/summary.json`),{signal:s})).json()}catch(t){return console.log(t),{release:void 0,suites:void 0,suite:void 0,date:""}}}function ms(){const[s,t]=i.useState({release:void 0,suites:void 0,suite:void 0,date:""}),[a,n]=i.useState();i.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(m=>m.json()).then(m=>{if(window.PROJECT_ID){const g=m.find(j=>j.id===window.PROJECT_ID);n(g)}else{const g=m.find(j=>j.id==="lite");n(g)}}).catch(m=>{console.error("Error fetching JSON:",m)})},[]),i.useEffect(()=>{const m=new AbortController;async function g(){const j=await hs(m.signal);t(j)}return g(),()=>m.abort()},[]);const r=a!==void 0&&a.releases!==void 0?a.releases:["v1.0.0"],o=s.release||s.suite||null;if(!o)return null;const l=`Release ${o} (${s.date})`;if(r.length<=1)return e.jsx("div",{children:l});const u=r.indexOf(o),h=u<0?e.jsx(F,{color:"blue",children:"preview"}):u===0?e.jsx(F,{color:"blue",children:"latest"}):e.jsx(F,{color:"yellow",children:"stale"});return e.jsxs("div",{className:"dropdown",children:[e.jsxs("div",{tabIndex:0,role:"button",className:"normal-case bg-white border-0 block whitespace-nowrap","aria-haspopup":"true","aria-controls":"menu",children:[l," ",h," ",e.jsx(ye,{fill:"black",color:"black",className:"inline text w-4 h-4"})]}),e.jsx("ul",{tabIndex:0,className:"dropdown-content z-[50] menu p-1 shadow-lg bg-base-100 rounded-box w-max text-base",role:"menu",children:["latest"].concat(r).map(m=>e.jsx("li",{children:e.jsx("a",{href:oe(m,a?a.id:"lite"),className:"block",role:"menuitem",children:m})},m))})]})}function us(){return e.jsxs("nav",{className:"navbar h-24 px-8 md:px-12 bg-base-100 max-w[1500]px",children:[e.jsx("div",{children:e.jsxs("div",{className:"dropdown md:hidden mr-4",children:[e.jsx("label",{tabIndex:0,className:"btn btn-ghost hover:bg-transparent btn-lg px-0",children:e.jsx(ve,{className:"w-16 h-16"})}),e.jsxs("ul",{tabIndex:0,className:"menu menu-lg dropdown-content mt-3 z-50 p-2 bg-base-100 shadow",children:[e.jsx("li",{children:e.jsx(b,{to:"leaderboard",children:"Leaderboard"})}),e.jsx("li",{children:e.jsx(b,{to:"models",children:"Models"})}),e.jsx("li",{children:e.jsx(b,{to:"scenarios",children:"Scenarios"})}),e.jsx("li",{children:e.jsx(b,{to:"runs",className:"whitespace-nowrap",children:"Predictions"})}),e.jsx("li",{children:e.jsx(b,{to:"https://github.com/stanford-crfm/helm",children:"GitHub"})})]})]})}),e.jsxs("div",{className:"flex-1 items-center",children:[e.jsx("a",{href:"https://crfm.stanford.edu/",className:"w-24",children:e.jsx("img",{src:we,className:"object-contain"})}),e.jsx(b,{to:"/",className:"mx-2 w-32",children:e.jsx("img",{src:Ne,className:"object-contain"})}),e.jsx(Me,{})]}),e.jsx("div",{className:"flex-none hidden md:block",children:e.jsxs("ul",{className:"flex flex-row gap-6 px-1",children:[e.jsx("li",{children:e.jsx(b,{to:"leaderboard",children:"Leaderboard"})}),e.jsx("li",{children:e.jsx(b,{to:"models",children:"Models"})}),e.jsx("li",{children:e.jsx(b,{to:"scenarios",children:"Scenarios"})}),e.jsx("li",{children:e.jsx(b,{to:"runs",children:"Predictions"})}),e.jsx("li",{children:e.jsx(b,{to:"https://github.com/stanford-crfm/helm",children:"GitHub"})}),e.jsx("li",{className:"hidden lg:flex",children:e.jsx(ms,{})})]})})]})}function xs(){return e.jsxs("nav",{className:"navbar h-24 px-8 md:px-12 bg-base-100 max-w[1500]px",children:[e.jsx("div",{children:e.jsx("div",{className:"dropdown md:hidden mr-4",children:e.jsx("label",{tabIndex:0,className:"btn btn-ghost hover:bg-transparent btn-lg px-0",children:e.jsx(ve,{className:"w-16 h-16"})})})}),e.jsxs("div",{className:"flex-1 items-center",children:[e.jsx(b,{to:"https://crfm.stanford.edu/",className:"w-24",children:e.jsx("img",{src:we,className:"object-contain"})}),e.jsx(b,{to:"/",className:"mx-2 w-32",children:e.jsx("img",{src:Ne,className:"object-contain"})}),e.jsx(Me,{})]})]})}function fs(){return e.jsxs(e.Fragment,{children:[window.PROJECT_ID==="home"?e.jsx(xs,{}):e.jsx(us,{}),e.jsx("main",{className:"p-8 pt-0",children:e.jsx("div",{className:"mx-auto max-w-[1500]px",children:e.jsx(Fe,{})})})]})}async function O(s){try{return await(await fetch(A(`${J()}/schema.json`),{signal:s})).json()}catch(t){return t instanceof Error&&t.name!=="AbortError"&&console.log(t),{adapter:[],metric_groups:[],metrics:[],models:[],perturbations:[],run_groups:[]}}}function ps({href:s,children:t}){return e.jsx("a",{href:s,className:"link link-primary link-hover",target:"_blank",rel:"noreferrer",children:t})}function U({value:s}){return e.jsx("span",{children:e.jsx(Ve,{components:{a:ps},children:s})})}function B({title:s,subtitle:t,markdown:a=!1}){return e.jsxs("header",{className:"m-4 ml-0",children:[e.jsx("h1",{className:"text-4xl",children:s}),a&&t!==void 0?e.jsx("h2",{className:"mt-2 text-neutral",children:e.jsx(U,{value:t})}):t!==void 0&&e.jsx("h2",{className:"mt-2 text-neutral",children:t})]})}const gs={open:"green",limited:"yellow",closed:"red"},js={open:"Open",limited:"Limited",closed:"Closed"};function bs({level:s}){return e.jsx(F,{color:gs[s],children:js[s]})}function $(){return e.jsx("div",{className:"w-full",children:e.jsx("div",{className:"block mx-auto my-24 loading loading-spinner loading-lg"})})}function vs(){const[s,t]=i.useState([]);i.useEffect(()=>{const l=new AbortController;async function u(){const h=await O(l.signal);t(h.models)}return u(),()=>l.abort()},[]);const[a,n,r]=s.reduce((l,u)=>{switch(u.access){case"open":l[0]+=1;break;case"limited":l[1]+=1;break;case"closed":l[2]+=1;break}return l},[0,0,0]),o=Object.values(s.reduce((l,u)=>{const h=u.creator_organization;return l[h]===void 0?(l[h]={name:h,models:1},l):(l[h].models+=1,l)},{}));return s.length===0?e.jsx($,{}):e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Models"}),e.jsxs("div",{className:"overflow-x-auto mt-12",children:[e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Creator"}),e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Description"}),e.jsx("th",{children:"Access"})]})}),e.jsx("tbody",{children:s.map(l=>e.jsxs("tr",{children:[e.jsx("td",{className:"text-lg",children:l.creator_organization}),e.jsxs("td",{children:[e.jsx("span",{className:"text-xl",children:l.display_name}),e.jsx("br",{}),e.jsx("span",{children:l.name})]}),e.jsx("td",{children:e.jsx(U,{value:l.description})}),e.jsx("td",{children:e.jsx(bs,{level:l.access})})]}))})]}),e.jsx(B,{title:"Analysis"}),e.jsxs("div",{className:"grid md:grid-cols-3 grid-cols-1 gap-8",children:[e.jsxs(z,{className:"flex flex-col justify-between",children:[e.jsx(ae,{children:"Models"}),e.jsx(je,{className:"text-6xl md:!text-[96px]",children:s.length}),e.jsx($e,{values:[a,n,r],colors:["green","yellow","red"]}),e.jsx(me,{categories:["Open","Limited","Closed"],colors:["green","yellow","red"]})]}),e.jsxs(z,{className:"md:col-span-2",children:[e.jsx(ae,{children:"Creator Organizations"}),e.jsxs("div",{className:"flex justify-between mt-4",children:[e.jsx(De,{data:o,category:"models",index:"name",variant:"pie",className:"basis-5/12"}),e.jsx(me,{categories:o.map(l=>l.name),className:"basis-7/12"})]})]})]})]})]})}function K({to:s,children:t,inTable:a=!1,title:n=""}){return a?e.jsx(b,{className:"link link-hover",to:s,title:n,children:t}):e.jsx(b,{className:"link link-primary link-hover",to:s,children:t})}function ws(){const[s,t]=i.useState([]),[a,n]=i.useState({});i.useEffect(()=>{const l=new AbortController;async function u(){const h=await O(l.signal);t(h.run_groups.filter(m=>!m.todo&&m.taxonomy&&!m.display_name.includes("CLEVA"))),n(Object.fromEntries(h.metrics.map(m=>[m.name,m])))}return u(),()=>l.abort()},[]);const r=l=>{var g;const u=(g=l.environment)==null?void 0:g.main_name,h=u?a[u]:void 0;if(h===void 0)return"";const m=h.display_name||h.short_display_name||h.name;return h.description?`${m} – ${h.description}`:m},o=Object.values(s.reduce((l,u)=>{var m;const h=((m=u.taxonomy)==null?void 0:m.task)||"Unknown";return l[h]===void 0?(l[h]={name:h,value:1},l):(l[h].value+=1,l)},{}));return s.length===0?e.jsx($,{}):(console.log(s),e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Scenarios",subtitle:"A scenario represents a use case and consists of a dataset of instances."}),e.jsxs("div",{className:"overflow-x-auto mt-12",children:[e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Scenario"}),e.jsx("th",{children:"Task"}),e.jsx("th",{children:"What"}),e.jsx("th",{children:"Who"}),e.jsx("th",{children:"When"}),e.jsx("th",{children:"Language"}),e.jsx("th",{children:"Description"}),e.jsx("th",{children:"Metric"})]})}),e.jsx("tbody",{children:s.map(l=>{var u,h,m,g,j;return e.jsxs("tr",{children:[e.jsxs("td",{children:[e.jsx(K,{to:`/leaderboard/${l.name}`,children:e.jsx("span",{className:"text-lg",children:l.display_name})}),e.jsx("span",{className:"block",children:l.name})]}),e.jsx("td",{children:((u=l.taxonomy)==null?void 0:u.task)||""}),e.jsx("td",{children:((h=l.taxonomy)==null?void 0:h.what)||""}),e.jsx("td",{children:((m=l.taxonomy)==null?void 0:m.who)||""}),e.jsx("td",{children:((g=l.taxonomy)==null?void 0:g.when)||""}),e.jsx("td",{children:((j=l.taxonomy)==null?void 0:j.language)||""}),e.jsx("td",{children:e.jsx(U,{value:l.short_description||l.description})}),e.jsx("td",{children:e.jsx(U,{value:r(l)})})]})})})]}),e.jsx(B,{title:"Analysis"}),e.jsxs("div",{className:"grid md:grid-cols-4 gap-8",children:[e.jsxs(z,{className:"flex flex-col",children:[e.jsx(ae,{children:"Total scenarios"}),e.jsx(je,{className:"mx-auto my-6 md:mt-16 !text-[72px] md:!text-[96px]",children:s.length})]}),e.jsx(z,{className:"col-span-3",children:e.jsxs("div",{className:"grid md:grid-cols-2 gap-x-12",children:[e.jsx(ue,{data:o.slice(0,Math.floor(o.length/2))}),e.jsx(ue,{data:o.slice(Math.ceil(o.length/2))})]})})]})]})]}))}function Ns(){return A(`${J()}/groups.json`)}async function Ee(s){try{return await(await fetch(Ns(),{signal:s})).json()}catch(t){return t instanceof Error&&t.name!=="AbortError"&&console.log(t),[]}}function ce({children:s}){return e.jsx("div",{role:"navigation",className:"tabs flex-nowrap border-b-2 border-gray-2 overflow-x-auto overflow-y-hidden",children:s})}function X({active:s=!1,onClick:t=()=>{},size:a="md",children:n}){return e.jsx("div",{onClick:t,className:`whitespace-nowrap text-${a} mb-[-2px] text-md tab tab-bordered${s?" border-2 border-grey-500 rounded":" border-none"}`,children:n})}function ys({title:s,titleId:t,...a},n){return i.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 20 20",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":t},a),s?i.createElement("title",{id:t},s):null,i.createElement("path",{fillRule:"evenodd",d:"M4.25 5.5a.75.75 0 0 0-.75.75v8.5c0 .414.336.75.75.75h8.5a.75.75 0 0 0 .75-.75v-4a.75.75 0 0 1 1.5 0v4A2.25 2.25 0 0 1 12.75 17h-8.5A2.25 2.25 0 0 1 2 14.75v-8.5A2.25 2.25 0 0 1 4.25 4h5a.75.75 0 0 1 0 1.5h-5Z",clipRule:"evenodd"}),i.createElement("path",{fillRule:"evenodd",d:"M6.194 12.753a.75.75 0 0 0 1.06.053L16.5 4.44v2.81a.75.75 0 0 0 1.5 0v-4.5a.75.75 0 0 0-.75-.75h-4.5a.75.75 0 0 0 0 1.5h2.553l-9.056 8.194a.75.75 0 0 0-.053 1.06Z",clipRule:"evenodd"}))}const fe=i.forwardRef(ys);function q(s){return Number.isNaN(Number(s))?String(s):String(Math.round(Number(s)*1e3)/1e3)}function Ls(s){return s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}function Y({value:s,title:t,hideIcon:a}){if(typeof s.value=="string"&&s.value.includes("⚠")&&(s.value=s.value.replace("⚠","")),s.value===void 0)return"-";if(s.run_spec_names){const n=(()=>{if(s.run_spec_names.length==1)return"/runs/"+s.run_spec_names[0];if(s.run_spec_names.length>1){const r="/runs/?q="+s.run_spec_names.map(l=>`^${Ls(l)}$`).join("|");return encodeURI(r)}})();return n?e.jsx(K,{to:n,inTable:!0,title:t,children:e.jsxs("div",{className:"flex items-center ",children:[q(s.value),!a&&e.jsx(fe,{className:"w-3 h-3 ml-1",stroke:"#cbcbcb",fill:"#cbcbcb"})]})}):t?e.jsx("a",{title:t,children:q(s.value)}):e.jsx(e.Fragment,{children:q(s.value)})}return s.href?e.jsx(K,{to:s.href,inTable:!0,title:t,children:e.jsxs("div",{className:"flex items-center",children:[q(s.value),!a&&e.jsx(fe,{className:"w-3 h-3 ml-1",stroke:"#cbcbcb",fill:"#cbcbcb"})]})}):s.markdown?e.jsx(U,{value:String(s.value)}):t?e.jsx("a",{title:t,children:q(s.value)}):e.jsx(e.Fragment,{children:q(s.value)})}function de({schema:s,groupTable:t,numRowsToDisplay:a,sortColumnIndex:n=1,sortable:r=!0,displayColumnIndexes:o=void 0,miniStyle:l=!1}){const[u,h]=i.useState(1),[m,g]=i.useState(Math.min(t.header.length-1,n));function j(c){return c.length>30?c.substring(0,27)+"...":c}const y=c=>{const x=["AIRBench 2024 -","-book"];if(c.value==="Model/adapter")return"Model";if(x.some(d=>c.value.includes(d))){let d=c.value;return x.forEach(v=>{d=d.replace(v,"")}),j(d)}else return j(c.value)},w=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.description;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},k=c=>{h(c===m?u*-1:c===0?-1:1),g(c)},p=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.name;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},R=()=>{const c=t.header[m].lower_is_better,x=u*(c?1:-1),d=t.rows.slice();return d.sort((v,S)=>{var M,C;const N=(M=v[m])==null?void 0:M.value,L=(C=S[m])==null?void 0:C.value;return N!==void 0&&L===void 0?-1:L!==void 0&&N===void 0?1:typeof N=="number"&&typeof L=="number"?(N-L)*x:typeof N=="string"&&typeof L=="string"?x===1?N.localeCompare(L):L.localeCompare(N):0}),a>0?d.slice(0,a):d};function f(c){const x=c.lastIndexOf(" - ");return x===-1?c:c.substring(0,x)+"*"+c.substring(x+1)}const _=c=>{const d=f(c).split("*")[0].trim();if(s){const v=s.run_groups.find(S=>S.display_name===d||S.short_display_name===d);if(v)return v.name}return""};return e.jsxs("table",{className:l?"table w-full":"rounded-lg shadow-md table",children:[e.jsx("thead",{children:e.jsx("tr",{children:t.header.filter((c,x)=>o===void 0||o.includes(x)).map((c,x)=>e.jsx("th",{className:`${x===m?"bg-gray-100":"bg-white"} ${x===0?"left-0 z-40":""} ${c.description?"underline decoration-dashed decoration-gray-300 ":""} whitespace-nowrap px-4 sticky top-0`,title:c.description?c.description:"",children:e.jsxs("div",{className:l?"flex gap-2 items-center":"z-20 flex justify-between items-center min-w-48 w-48 max-w-48 text-wrap",children:[e.jsx("span",{className:"inline-block w-full break-words",children:y(c)}),r?e.jsx("button",{className:"link",onClick:()=>k(x),children:e.jsx(Le,{className:"w-6 h-6"})}):null]})},`$${x}`))})}),e.jsx("tbody",{children:R().map((c,x)=>e.jsx("tr",{children:c.filter((d,v)=>o===void 0||o.includes(v)).map((d,v)=>e.jsx("td",{className:`${v===0?"z-20 text-lg sticky left-0":"z-0"} ${x%2===0?"bg-gray-50":"bg-white"}`,children:v==1?e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""}`,children:e.jsx(Y,{value:{...d,href:"/runs/?q="+p(String(c[0].value))},title:`Click value to see all predictions for: ${p(String(c[0].value))}`})}):e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""} ${v===0?"underline decoration-dashed decoration-gray-300 z-10":"z-0"}`,children:e.jsx(Y,{value:{...d},title:String(c[0].value)===d.value?w(String(c[0].value)):`Click value to see predictions for ${String(c[0].value)} for ${_(y(t.header[v]))}: ${p(String(c[0].value))}`})})},`${v}`))},`$${c[0].value}`))})]})}function Ms(){const[s,t]=i.useState(0),[a,n]=i.useState(),[r,o]=i.useState();return i.useEffect(()=>{const l=new AbortController;async function u(){const h=O(l.signal),m=Ee(l.signal),g=await h;o(g);const j=await m;n(j)}return u(),()=>l.abort()},[]),a===void 0||r===void 0?e.jsx($,{}):a.length===0?e.jsxs("div",{children:[e.jsx(B,{title:"Results",subtitle:"Groupings of the processes, methods, and metrics involved in evaluating models, particularly in the context of natural language understanding and question answering.",className:"mb-16"}),e.jsx("div",{children:"No groups found."})]}):e.jsxs("div",{children:[e.jsx(B,{title:"Results",subtitle:"Groupings of the processes, methods, and metrics involved in evaluating models, particularly in the context of natural language understanding and question answering.",className:"mb-16"}),e.jsxs("div",{children:[a.length>1?e.jsx(ce,{children:a.map((l,u)=>e.jsx(X,{active:u===s,onClick:()=>t(u),children:l.title},u))}):null,e.jsx(de,{schema:r,groupTable:a[s],numRowsToDisplay:-1,sortColumnIndex:1,sortable:!0},`${s}`)]})]})}async function Es(s){try{return await(await fetch(A(`${J()}/run_specs.json`),{signal:s})).json()}catch(t){return t instanceof Error&&t.name!=="AbortError"&&console.log(t),[]}}function he({currentPage:s,totalPages:t,onNextPage:a,onPrevPage:n,className:r}){let o="join";return r!==void 0&&(o=`join ${r}`),e.jsxs("div",{className:o,children:[e.jsx("button",{onClick:n,className:"join-item btn",children:"«"}),e.jsxs("button",{className:"join-item btn",children:["Page ",s," of ",t]}),e.jsx("button",{onClick:a,className:"join-item btn",children:"»"})]})}const se=100;function ks(){const[s,t]=ie(),[a,n]=i.useState(),[r,o]=i.useState(Number(s.get("page")||1)),[l,u]=i.useState(!0),[h,m]=i.useState(s.get("q")||"");i.useEffect(()=>{const p=new AbortController;async function R(){const f=await Es(p.signal);n(f)}return R(),()=>p.abort()},[]);const g=p=>{p.preventDefault();const f=p.target.q.value;m(f),t({q:f,page:"1"})};if(a===void 0)return e.jsx($,{});let j=null;if(l)try{j=new RegExp(h)}catch{j=null}const y=a.filter(p=>j?j.test(p.name):p.name.includes(h)),w=y.slice((r-1)*se,r*se),k=Math.ceil(y.length/se);return e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Predictions",subtitle:"All benchmark predictions"}),e.jsxs("form",{className:"flex mb-8",onSubmit:g,children:[e.jsxs("div",{className:"form-control",children:[e.jsx("input",{type:"text",name:"q",placeholder:"Search",className:"input input-bordered",value:h,onChange:p=>m(p.target.value)}),e.jsxs("label",{className:"label",children:[e.jsxs("span",{className:"label-text-alt flex item-center",children:[e.jsx("input",{type:"checkbox",className:"toggle toggle-xs",checked:l,onChange:()=>u(!l)}),e.jsx("span",{className:"ml-2",children:"Regex"})]}),e.jsx("span",{className:"label-text-alt",children:`${y.length} results`})]})]}),e.jsx("div",{className:"form-control ml-4",children:e.jsx("button",{className:"btn",children:e.jsx(ds,{className:"w-6 h-6"})})})]}),e.jsx("div",{className:"overflow-x-auto",children:e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Run"}),e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Groups"}),e.jsx("th",{children:"Adapter method"}),e.jsx("th",{children:"Subject / Task"})]})}),e.jsx("tbody",{children:w.map((p,R)=>e.jsxs("tr",{children:[e.jsx("td",{children:e.jsx(K,{to:`/runs/${p.name}`,children:p.name})}),e.jsx("td",{children:p.adapter_spec.model}),e.jsx("td",{children:p.groups.join(", ")}),e.jsx("td",{children:p.adapter_spec.method}),e.jsx("td",{children:p.scenario_spec.args.subject||p.scenario_spec.args.task||"-"})]},`${p.name}-${R}`))})]})}),k>0?e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const p=Math.min(r+1,k);o(p),s.set("page",String(p)),t(s)},onPrevPage:()=>{const p=Math.max(r-1,1);o(p),s.set("page",String(p)),t(s)},currentPage:r,totalPages:k}):e.jsx("div",{className:"my-8 text-center",children:"No results"})]})}function T(){return window.SUITE!==void 0?window.SUITE:void 0}async function Ss(s,t,a){try{return await(await fetch(A(`/runs/${a||T()}/${s}/scenario.json`),{signal:t})).json()}catch(n){n instanceof Error&&n.name!=="AbortError"&&console.log(n);return}}function ke(s,t){return A(`/runs/${t||T()}/${s}/run_spec.json`)}async function As(s,t,a){try{return await(await fetch(ke(s,a),{signal:t})).json()}catch(n){n instanceof Error&&n.name!=="AbortError"&&console.log(n);return}}function Rs(s,t){return A(`/runs/${t||T()}/${s}/per_instance_stats.json`)}function _s(s,t){return A(`/runs/${t||T()}/${s}/scenario_state.json`)}function Se(){return window.RELEASE!==void 0?window.RELEASE:void 0}async function Cs(s){try{return await(await fetch(A(`/releases/${Se()}/runs_to_run_suites.json`),{signal:s})).json()}catch(t){return t instanceof Error&&t.name!=="AbortError"&&console.log(t),{}}}function Ts(s,t){return Se()?s[t]:window.SUITE}function Is(s){const a={quasi_exact_match:!1,toxic_frac:!0,safety_score:!1,exact_match:!1},n=Object.keys(s);for(const r of n)if(s[r]!==void 0&&a[r]!==void 0)return a[r]?s[r]<.5?[r,!0]:[r,!1]:s[r]>=.5?[r,!0]:[r,!1];return["",!1]}function Ps(s){const[t,a]=Is(s.stats);return t===""?null:a?e.jsx(Hs,{value:`${t.replace(/_/g," ")}: ${s.stats[t]}`}):e.jsx($s,{value:`${t.replace(/_/g," ")}: ${s.stats[t]}`})}function Hs({value:s}){return e.jsx(F,{icon:Xe,color:"green",children:s})}function $s({value:s}){return e.jsx(F,{icon:es,color:"red",children:s})}function H({value:s}){const[t,a]=i.useState(!1),[n,r]=i.useState(!1);return e.jsxs(e.Fragment,{children:[e.jsxs("div",{onMouseOver:()=>a(!0),onMouseOut:()=>a(!1),className:"relative",children:[e.jsx("div",{className:"bg-base-200 p-2 block overflow-auto w-full max-h-[36rem] mb-2 whitespace-pre-wrap localize-text-direction",children:s}),t?e.jsx("button",{className:"bg-white absolute p-2 leading-none height-fit min-h-none right-1 bottom-1 shadow",onClick:()=>r(!0),children:e.jsx(ls,{fill:"black",color:"black",className:"text w-4 h-4"})}):null]}),e.jsx("dialog",{open:n,className:"modal p-16 bg-opacity-80 bg-white",onClick:()=>r(!1),children:e.jsx("div",{className:"modal-box max-w-none p-4 whitespace-pre-wrap bg-base-200 localize-text-direction",children:s})})]})}function Ae({messages:s}){return e.jsx("div",{children:s.map((t,a)=>e.jsxs("div",{children:[e.jsx("div",{children:t.role}),e.jsx(H,{value:t.content})]},a))})}function Re({mediaObject:s}){if(s.content_type.includes("image")){if(s.location===void 0)return null;const t=A(s.location.replace("benchmark_output/","").replace("prod_env/","../"));return e.jsxs("div",{children:[e.jsx("img",{src:t}),e.jsx("br",{})]})}else if(s.content_type.includes("audio")){if(s.location===void 0)return null;const t=A(s.location.replace(/^.*benchmark_output\//,"").replace("prod_env/","../"));return e.jsx("div",{children:e.jsx("audio",{controls:!0,src:t})})}else if(s.content_type.includes("video")){if(s.location===void 0)return null;const t=A(s.location.replace(/^.*benchmark_output\//,"").replace("prod_env/","../"));return e.jsxs("div",{children:[e.jsx("video",{controls:!0,style:{width:"720px"},children:e.jsx("source",{src:t,type:s.content_type})}),e.jsx("br",{})]})}else return s.text&&s.content_type&&s.content_type==="text/plain"&&s.text.length>1?e.jsxs("div",{children:[s.text,e.jsx("br",{}),e.jsx("br",{})]}):e.jsx("div",{})}function _e({multimediaObject:s}){return e.jsx("div",{children:s.media_objects.map(t=>e.jsx(Re,{mediaObject:t}))})}function Ds(s){return Array.isArray(s)?s.length==0?"[]":`[${s.map(t=>String(t).replace(/\n/,"\\n")).join(", ")}]`:String(s)}function Bs({request:s}){return e.jsxs("div",{children:[s.request.prompt.length>0?e.jsxs("div",{children:[e.jsxs("h3",{className:"block text text-gray-400",children:["Prompt (",s.request.prompt.length," Chars)"]}),e.jsx(H,{value:s.request.prompt})]}):s.request.multimodal_prompt?e.jsxs("div",{children:[e.jsx("h3",{className:"block text text-gray-400",children:"Prompt"}),e.jsx(_e,{multimediaObject:s.request.multimodal_prompt})]}):s.request.messages&&s.request.messages.length?e.jsxs("div",{children:[e.jsx("h3",{className:"block text text-gray-400",children:"Prompt"}),e.jsx(Ae,{messages:s.request.messages})]}):e.jsx("h3",{className:"block text text-gray-400",children:"Empty Prompt"}),e.jsx(re,{children:Object.keys(s.request).filter(t=>t!=="prompt").map((t,a)=>e.jsxs(le,{children:[e.jsxs("span",{children:[t,":"]}),s.request&&s.request[t]?e.jsx("span",{children:Ds(s.request[t])}):"null"]},a+1))})]})}function Os(s){return e.jsx("div",{children:s.map((t,a)=>e.jsxs("div",{children:[t.error&&e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:"Error"}),e.jsx(H,{value:t.error})," "]}),t.text&&e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:"Text"}),e.jsx(H,{value:t.text})," "]}),t.media_object&&e.jsx(Re,{mediaObject:t.media_object})]},a))})}function ne(s,t){return Array.isArray(s)?s.flatMap((a,n)=>ne(a,`${t||""}[${n}]`)):s instanceof Object&&s.constructor===Object?Object.entries(s).flatMap(([a,n])=>ne(n,t?`${t}.${a}`:a)):[[t||"",typeof s=="string"?s:JSON.stringify(s)]]}function Fs(s){return e.jsx("div",{children:ne(s).map(([t,a])=>e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:t}),e.jsx(H,{value:a})]},t))})}function Us({predictionAnnotations:s}){return e.jsx("div",{children:s&&s!==void 0?Object.entries(s).map(([t,a])=>e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white my-2",children:[e.jsx("summary",{className:"collapse-title",children:e.jsx(e.Fragment,{children:"View "+t+" annotations"})}),e.jsx("div",{className:"collapse-content",children:Array.isArray(a)?Os(a):Fs(a)})]},t)):null})}function qs({predictions:s,requests:t,metricFieldMap:a}){return s.length<1?null:e.jsx("div",{children:e.jsx("div",{className:"flex flex-wrap justify-start items-start",children:s.map((n,r)=>e.jsxs("div",{className:"w-full",children:[s.length>1?e.jsxs("h2",{children:["Trial ",n.train_trial_index]}):null,e.jsxs("div",{className:"mt-2 w-full",children:[n.thinking_text?e.jsxs(e.Fragment,{children:[e.jsx("h3",{children:e.jsx("span",{className:"mr-4",children:"Thinking"})}),e.jsx(H,{value:n.thinking_text})]}):null,n.base64_images&&n.base64_images.length>0?e.jsxs(e.Fragment,{children:[e.jsx("h3",{className:"mr-4",children:"Prediction image"}),n.base64_images.map(o=>e.jsx("img",{src:"data:image;base64,"+o,alt:"Base64 Image"}))]}):e.jsxs(e.Fragment,{children:[e.jsxs("h3",{children:[e.jsx("span",{className:"mr-4",children:"Prediction raw text"}),e.jsx(Ps,{stats:n.stats})]}),e.jsx(H,{value:n.predicted_text}),n.mapped_output?e.jsxs(e.Fragment,{children:[e.jsx("h3",{children:"Prediction mapped output"}),e.jsx(H,{value:String(n.mapped_output)})]}):null]})]}),e.jsx(Us,{predictionAnnotations:n.annotations}),e.jsxs("div",{className:"mx-1",children:[e.jsx("h3",{children:"Metrics"}),e.jsx(re,{children:Object.keys(n.stats).map((o,l)=>e.jsxs(le,{children:[a[o]?e.jsx("span",{title:a[o].description,children:a[o].display_name}):e.jsx("span",{children:o}),e.jsx("span",{children:String(n.stats[o])})]},l))})]}),e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white",children:[e.jsx("summary",{className:"collapse-title",children:"Request details"}),e.jsx("div",{className:"collapse-content",children:e.jsx(Bs,{request:t[r]})})]})]},r))})})}const Ws="correct";function zs({references:s}){return e.jsxs("span",{children:[e.jsx("h3",{children:"References"}),e.jsx("ul",{children:s.map((t,a)=>e.jsxs("li",{className:"bg-base-200 p-2 block overflow-auto w-full max-h-72 mb-2 whitespace-pre-wrap localize-text-direction",children:[t.output.text,t.tags.map(n=>e.jsx(F,{className:"mx-2",color:n===Ws?"green":void 0,children:n}))]},a))})]})}function Ce(s){return e.jsx(H,{value:s===null?"null":typeof s=="object"?JSON.stringify(s):s.toString()})}function Vs(s){return e.jsx("div",{children:s.map(t=>Ce(t))})}function Js({extraData:s}){return e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white my-2",children:[e.jsx("summary",{className:"collapse-title",children:"View instance extra data"}),e.jsx("div",{className:"collapse-content",children:Object.entries(s).map(([t,a])=>e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:t}),Array.isArray(a)?Vs(a):Ce(a)]}))})]})}function Gs({instance:s,requests:t,predictions:a,metricFieldMap:n}){return e.jsxs("div",{children:[e.jsx("h3",{children:"Input"}),s.input.multimedia_content!==void 0?e.jsx(_e,{multimediaObject:s.input.multimedia_content}):s.input.text.includes('
0?e.jsx(zs,{references:s.references}):null}),s.extra_data&&s.extra_data.length?e.jsx(Js,{extraData:s.extra_data}):null,e.jsx("div",{children:a&&t?e.jsx(qs,{predictions:a,requests:t,metricFieldMap:n}):null})]})}async function Qs(s,t,a,n){const r=m=>Uint8Array.from(atob(m),g=>g.charCodeAt(0)),o=await window.crypto.subtle.importKey("raw",r(t),"AES-GCM",!0,["decrypt"]),l=new Uint8Array([...r(s),...r(n)]),u=r(a),h=await window.crypto.subtle.decrypt({name:"AES-GCM",iv:u},o,l);return new TextDecoder().decode(h)}async function V(s,t){if(!s.includes("encrypted_text"))return s;const a=t[s];return a===void 0?(console.error(`Could not find ${s} in encryption data`),s):await Qs(a.ciphertext,a.key,a.iv,a.tag)}function ee(s){return s.includes("gpqa")||s.includes("ewok")}async function Zs(s,t,a,n){try{const o=await(await fetch(A(`/runs/${a||T()}/${s}/instances.json`),{signal:t})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${a||T()}/${s}/encryption_data.json`),{signal:t})).json();for(const h of o){h.input.text=await V(h.input.text,u);for(const m of h.references)m.output.text=await V(m.output.text,u)}}return o}catch(r){return r instanceof Error&&r.name!=="AbortError"&&console.log(r),[]}}async function Ks(s,t,a,n){try{const o=await(await fetch(A(`/runs/${a||T()}/${s}/display_predictions.json`),{signal:t})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${a||T()}/${s}/encryption_data.json`),{signal:t})).json();for(const h of o)h.predicted_text=await V(h.predicted_text,u),h.thinking_text!==void 0&&(h.thinking_text=await V(h.thinking_text,u))}return o}catch(r){return r instanceof Error&&r.name==="AbortError"&&console.log(r),[]}}async function Xs(s,t,a,n){try{const o=await(await fetch(A(`/runs/${a||T()}/${s}/display_requests.json`),{signal:t})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${a||T()}/${s}/encryption_data.json`),{signal:t})).json();for(const h of o)h.request.prompt=await V(h.request.prompt,u)}return o}catch(r){return r instanceof Error&&r.name!=="AbortError"&&console.log(r),[]}}const Q=10;function Ys({runName:s,suite:t,metricFieldMap:a,userAgreed:n}){const[r,o]=ie(),[l,u]=i.useState([]),[h,m]=i.useState(),[g,j]=i.useState(),[y,w]=i.useState(1);i.useEffect(()=>{const f=new AbortController;async function _(){const c=f.signal,[x,d,v]=await Promise.all([Zs(s,c,t,n),Ks(s,c,t,n),Xs(s,c,t,n)]);u(x);const S={};v.forEach(L=>{var I;const M=L.instance_id,C=((I=L.perturbation)==null?void 0:I.name)||"";S[M]===void 0&&(S[M]={}),S[M][C]===void 0&&(S[M][C]=[]),S[M][C].push(L)}),j(S);const N={};d.forEach(L=>{var I;const M=L.instance_id,C=((I=L.perturbation)==null?void 0:I.name)||"";N[M]===void 0&&(N[M]={}),N[M][C]===void 0&&(N[M][C]=[]),N[M][C].push(L)}),m(N)}return _(),()=>f.abort()},[s,t,n]);const k=l.slice((y-1)*Q,(y-1)*Q+Q),p=Math.ceil(l.length/Q);i.useEffect(()=>{const f=r.get("instance");if(f&&!window.helmHasScrolledToInstance&&k.length>0){if(k.findIndex(c=>c.id===f)===-1)return;requestAnimationFrame(()=>{const c=document.getElementById(`instance-${f}`);c&&c.scrollIntoView({behavior:"smooth"})}),window.helmHasScrolledToInstance=!0}},[r,y,o,k]);const R=f=>f.perturbation===void 0?`Instance id: ${f.id} [split: ${f.split}]`:`Instance id: ${f.id} [split: ${f.split}][perturbation: ${f.perturbation.name}]`;return h===void 0||g===void 0?e.jsx($,{}):e.jsxs(e.Fragment,{children:[e.jsx("div",{className:"grid gap-8",children:k.map((f,_)=>{var c,x;return e.jsxs("div",{id:"instance-"+f.id,className:"border p-4",children:[e.jsxs("div",{className:"flex items-center justify-between",children:[e.jsx("h3",{className:"text-xl mb-4",children:R(f)}),e.jsx("button",{className:"btn btn-sm normal-case px-2 py-1",onClick:()=>{const d=window.location.href+(window.location.href.includes("?")?"&instance=":"?instance=")+f.id;navigator.clipboard.writeText(d)},children:"Copy Link"})]}),e.jsx(Gs,{instance:f,requests:g[f.id][((c=f.perturbation)==null?void 0:c.name)||""],predictions:h[f.id][((x=f.perturbation)==null?void 0:x.name)||""],metricFieldMap:a},`${f.id}-${_}`)]})})}),e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const f=Math.min(y+1,p);w(f),r.set("instancesPage",String(f)),o(r)},onPrevPage:()=>{const f=Math.max(y-1,1);w(f),r.set("instancesPage",String(f)),o(r)},currentPage:y,totalPages:p})]})}async function et(s,t,a){try{return await(await fetch(A(`/runs/${a||T()}/${s}/stats.json`),{signal:t})).json()}catch(n){return n instanceof Error&&n.name!=="AbortError"&&console.log(n),[]}}function st({stat:s,metricFieldMap:t}){const a=`${s.name.split!==void 0?` on ${s.name.split}`:""}${s.name.sub_split!==void 0?`/${s.name.sub_split}`:""}${s.name.perturbation!==void 0?` with ${s.name.perturbation.name}`:" original"}`;return t[s.name.name]?e.jsxs("span",{title:t[s.name.name].description,children:[e.jsx("strong",{children:t[s.name.name].display_name||s.name.name}),a]}):e.jsxs("span",{children:[e.jsx("strong",{children:s.name.name}),a]})}const Z=50,pe=["name","mean","min","max","sum","sum_squared","variance","stddev"];function tt({runName:s,suite:t,metricFieldMap:a}){const[n,r]=ie(),[o,l]=i.useState(),[u,h]=i.useState(1),[m,g]=i.useState("");if(i.useEffect(()=>{const w=new AbortController;async function k(){const p=w.signal,R=await et(s,p,t);l(R)}return k(),()=>w.abort()},[s,t]),o===void 0||o.length===0)return e.jsx($,{});const j=Math.ceil(o.length/Z),y=o.slice((u-1)*Z,(u-1)*Z+Z);return e.jsxs("div",{children:[e.jsx("div",{className:"flex justify-start my-4",children:e.jsx("input",{type:"text",className:"input input-bordered w-full max-w-xs",placeholder:"Search for a metric",onChange:w=>g(w.target.value)})}),e.jsx("div",{className:"overflow-x-auto",children:e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsx("tr",{children:pe.map(w=>e.jsx("th",{children:w},w))})}),e.jsx("tbody",{children:y.filter(w=>!m||w.name.name.toLowerCase().includes(m.toLowerCase())).map(w=>e.jsx("tr",{children:pe.map(k=>{const p=w[k];return typeof p=="number"?e.jsx("td",{children:p}):e.jsx("td",{children:e.jsx(st,{stat:w,metricFieldMap:a})},k)})}))})]})}),e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const w=Math.min(u+1,j);h(w),n.set("metricsPage",String(w)),r(n)},onPrevPage:()=>{const w=Math.max(u-1,1);h(w),n.set("metricsPage",String(w)),r(n)},currentPage:u,totalPages:j})]})}function at({runName:s,onAgree:t}){const a=i.useRef(null),n=()=>{a.current!==null&&a.current.value.trim()==="Yes, I agree"?t():alert("Please type 'Yes, I agree' exactly.")},r=s.includes("gpqa")?e.jsx(nt,{}):s.includes("ewok")?e.jsx(rt,{}):null;return e.jsxs("div",{className:"mb-8",children:[r,e.jsxs("p",{className:"mb-4",children:["If you agree to this condition, please type"," ",e.jsx("strong",{children:'"Yes, I agree"'})," in the box below and then click"," ",e.jsx("strong",{children:"Decrypt"}),"."]}),e.jsxs("div",{className:"flex gap-2 mt-2",children:[e.jsx("input",{type:"text",ref:a,className:"input input-bordered",placeholder:'Type "Yes, I agree"'}),e.jsx("button",{onClick:n,className:"btn btn-primary",children:"Decrypt"})]}),e.jsx("hr",{className:"my-4"})]})}function nt(){return e.jsxs("div",{children:[e.jsx("p",{className:"mb-4",children:"The GPQA dataset instances are encrypted by default to comply with the following request:"}),e.jsx("blockquote",{className:"italic border-l-4 border-gray-300 pl-4 text-gray-700 mb-4",children:"“We ask that you do not reveal examples from this dataset in plain text or images online, to minimize the risk of these instances being included in foundation model training corpora.”"})]})}function rt(){return e.jsxs("div",{children:[e.jsx("p",{className:"mb-4",children:"The EWoK dataset instances are encrypted by default to comply with the following request:"}),e.jsx("blockquote",{className:"italic border-l-4 border-gray-300 pl-4 text-gray-700 mb-4",children:"“PLEASE DO NOT distribute any of the EWoK materials or derivatives publicly in plain-text! Any materials should appear in password-protected ZIP files or behind gated authentication mechanisms such as Huggingface datasets.”"})]})}function lt(){var d;const{runName:s}=be(),[t,a]=i.useState(0),[n,r]=i.useState(),[o,l]=i.useState(),[u,h]=i.useState(),[m,g]=i.useState(),[j,y]=i.useState(),[w,k]=i.useState({}),[p,R]=i.useState({}),[f,_]=i.useState(!1);if(i.useEffect(()=>{const v=new AbortController;async function S(){const N=v.signal;if(s===void 0)return()=>v.abort();const L=window.SUITE?window.SUITE:Ts(await Cs(N),s);l(L);const[M,C,I]=await Promise.all([As(s,N,L),Ss(s,N,L),O(N)]);r(M),g(C),R(I.metrics.reduce((D,W)=>(D[W.name]=W,D),{})),k(I.adapter.reduce((D,W)=>(D[W.name]=W,D),{})),y(I.run_groups.find(D=>M==null?void 0:M.groups.includes(D.name))),h(I.models.find(D=>D.name===(M==null?void 0:M.adapter_spec.model)))}return S(),()=>v.abort()},[s]),n===void 0||m===void 0||s===void 0||o===void 0||p===void 0)return e.jsx($,{});const c=(d=j==null?void 0:j.taxonomy)==null?void 0:d.language,x=c?"scenario-language-"+c.toLowerCase():"";return e.jsxs("div",{className:x,children:[e.jsx("div",{className:"flex justify-between gap-8 mb-12",children:e.jsxs("div",{children:[e.jsxs("h1",{className:"text-3xl flex items-center",children:[(j==null?void 0:j.display_name)||m.name,j?e.jsx("a",{href:"/#/groups/"+j.name,children:e.jsx(ns,{className:"w-6 h-6 ml-2"})}):null]}),e.jsx("h3",{className:"text-xl",children:e.jsx(U,{value:(j==null?void 0:j.description)||m.description})}),e.jsx("h1",{className:"text-3xl mt-2",children:(u==null?void 0:u.display_name)||n.adapter_spec.model}),e.jsx("h3",{className:"text-xl",children:e.jsx(U,{value:(u==null?void 0:u.description)||""})}),e.jsx("div",{className:"mt-2 flex gap-2",children:m.tags.map(v=>e.jsx(F,{size:"xs",color:"gray",children:e.jsx("span",{className:"text text-md",children:v})}))})]})}),e.jsxs(z,{children:[e.jsxs("div",{className:"flex justify-between",children:[e.jsx("h3",{className:"text-lg mb-1",children:"Adapter Specification"}),e.jsxs("div",{className:"flex gap-2",children:[e.jsx(ts,{className:"w-6 h-6 mr-1 text text-primary"}),e.jsx("a",{className:"link link-primary link-hover",href:ke(n.name,o),download:"true",target:"_blank",children:"Spec JSON"}),e.jsx("a",{className:"link link-primary link-hover",href:_s(n.name,o),download:"true",target:"_blank",children:"Full JSON"}),e.jsx("a",{className:"link link-primary link-hover",href:Rs(n.name,o),download:"true",target:"_blank",children:"Per-Instance Stats JSON"})]})]}),e.jsx("div",{children:e.jsx(re,{className:"grid md:grid-cols-2 lg:grid-cols-3 gap-x-8",children:Object.entries(n.adapter_spec).map(([v,S],N)=>e.jsxs(le,{className:N<3?"!border-0":"",children:[e.jsx("strong",{className:"mr-1",title:w[v]?w[v].description:void 0,children:`${v}: `}),e.jsx("span",{className:"overflow-x-auto pre-wrap",children:S})]}))})})]}),e.jsx("div",{className:"mt-16 mb-8",children:e.jsxs(ce,{children:[e.jsx(X,{size:"lg",active:t===0,onClick:()=>a(0),children:"Instances + Predictions"}),e.jsx(X,{size:"lg",active:t===1,onClick:()=>a(1),children:"All metrics"})]})}),t===0&&ee(s)&&!f&&e.jsx(at,{runName:s,onAgree:()=>_(!0)}),t===0?e.jsx(Ys,{runName:s,suite:o,metricFieldMap:p,userAgreed:f},f?"instances-agreed":"instances-not-agreed"):e.jsx(tt,{runName:s,suite:o,metricFieldMap:p})]})}function it({schema:s,groupTable:t,numRowsToDisplay:a,sortColumnIndex:n=1,sortable:r=!0,miniStyle:o=!1}){const[l,u]=i.useState(1),[h,m]=i.useState(Math.min(t.header.length-1,n)),g=c=>c.value,j=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.description;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},y=c=>{u(c===h?l*-1:c===0?-1:1),m(c)},w=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.name;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},k=()=>{const c=t.header[h].lower_is_better,x=l*(c?1:-1),d=t.rows.slice();return d.sort((v,S)=>{var M,C;const N=(M=v[h])==null?void 0:M.value,L=(C=S[h])==null?void 0:C.value;return N!==void 0&&L===void 0?-1:L!==void 0&&N===void 0?1:typeof N=="number"&&typeof L=="number"?(N-L)*x:typeof N=="string"&&typeof L=="string"?x===1?N.localeCompare(L):L.localeCompare(N):0}),a>0?d.slice(0,a):d};function p(c){const x=c.lastIndexOf(" - ");return x===-1?c:c.substring(0,x)+"*"+c.substring(x+1)}const R=c=>{const d=p(c).split("*")[0].trim();if(s){const v=s.run_groups.find(S=>S.display_name===d||S.short_display_name===d);if(v)return v.name}return""},f=[];f.push(t.header.map((c,x)=>e.jsx("td",{className:`${x===h?"bg-gray-100":x%2===0?"bg-gray-50":"bg-white"} ${x===0?"top-0 z-20":"z-10"} ${c.description?"underline decoration-dashed decoration-gray-300":""} sticky left-0 justify-between items-center w-48`,title:c.description?c.description:"",children:e.jsxs("div",{className:o?"flex gap-2":"z-10 flex w-full",children:[e.jsx("span",{className:"inline-block w-full break-words",children:g(c)}),r?e.jsx("button",{className:"link",onClick:()=>y(x),children:e.jsx(Le,{className:"w-6 h-6"})}):null]})},`scenario-${x}`))),k().forEach((c,x)=>f.push(c.map((d,v)=>e.jsx("td",{className:`${v%2===0?"bg-gray-50":"bg-white"} ${v===0?"px-4 sticky top-0":""} w-32`,children:v==1?e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""}`,children:e.jsx(Y,{value:{...d,href:"/runs/?q="+w(String(c[0].value))},title:`Click value to see all predictions for: ${w(String(c[0].value))}`})}):e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""} ${v===0?"underline decoration-dashed decoration-gray-300 z-20":"z-0"}`,children:e.jsx(Y,{value:{...d},title:String(c[0].value)===d.value?j(String(c[0].value)):`Click value to see predictions for ${String(c[0].value)} for ${R(g(t.header[v]))}: ${w(String(c[0].value))}`})})},`${x}-${v}`))));const _=f[0].map((c,x)=>f.map(d=>d[x]));return e.jsxs("table",{className:o?"table table-fixed w-full":"rounded-lg shadow-md table table-fixed",children:[e.jsx("thead",{children:e.jsx("tr",{children:_[0]})}),e.jsx("tbody",{children:_.slice(1).map((c,x)=>e.jsx("tr",{children:c},x))})]})}async function Te(s,t){try{return await(await fetch(A(`${J()}/groups/${s}.json`),{signal:t})).json()}catch(a){return a instanceof Error&&a.name!=="AbortError"&&console.log(a),[]}}function ot({schema:s,runGroupName:t,numRowsToDisplay:a=-1}){const[n,r]=i.useState(),[o,l]=i.useState(0);if(i.useEffect(()=>{const h=new AbortController;async function m(){const g=await Te(t,h.signal);r(g)}return m(),()=>h.abort()},[s,t]),n===void 0||n.length===0)return e.jsx($,{});if(n.length===0)return e.jsx("div",{children:"Group currently has no tables."});const u=s.run_groups[0].name=="medhelm_scenarios";return e.jsxs("div",{children:[n.length>1?e.jsx(ce,{children:n.map((h,m)=>e.jsx(X,{active:m===o,onClick:()=>l(m),children:h.title},m))}):null,u?e.jsx(it,{schema:s,groupTable:n[o],numRowsToDisplay:a,sortColumnIndex:1},`${t}-${o}`):e.jsx(de,{schema:s,groupTable:n[o],numRowsToDisplay:a,sortColumnIndex:1},`${t}-${o}`)]})}function te(){const{groupName:s}=be(),t=Ue(),[a,n]=i.useState(void 0),[r,o]=i.useState(),[l,u]=i.useState();i.useEffect(()=>{const g=new AbortController;async function j(){const y=O(g.signal),w=Ee(g.signal),k=await y;n(k);let p;const R=await w,f={};R.forEach(_=>{f[_.title]=[],_.rows.forEach(c=>{const x=c[0].href.replace("?group=","");p===void 0&&(p=x),f[_.title].push({title:String(c[0].value),name:x})})}),o(f),u(p)}return j(),()=>g.abort()},[]);const h=s||l;if(a===void 0||r===void 0||h===void 0)return e.jsx($,{});let m;for(const g of a.run_groups)g.name===h&&(m=g);return e.jsxs(e.Fragment,{children:[e.jsxs("div",{className:"flex flex-row",children:[e.jsx("div",{className:"w-3/4",children:m?e.jsx(B,{title:"Leaderboard: "+m.display_name,subtitle:m.description,markdown:!0}):e.jsx(B,{title:"Leaderboard",subtitle:"The HELM leaderboard shows how the various models perform across different scenarios and metrics.",markdown:!0})}),e.jsx("div",{className:"w-1/4 pt-8",children:e.jsxs("label",{htmlFor:"group",className:"block text-sm font-medium text-gray-700",children:["Select a group:",e.jsx("select",{id:"group",name:"group",onChange:g=>t("/leaderboard/"+g.target.value),className:"mt-1 block w-full pl-3 pr-10 py-2 text-base border-gray-300 focus:outline-none focus:ring focus:border-blue-300 rounded-md",value:h,children:Object.entries(r).map(([g,j])=>e.jsx("optgroup",{label:g,children:j.map(y=>e.jsx("option",{value:y.name,children:y.title},y.name))},g))})]})})]}),e.jsx(ot,{schema:a,runGroupName:h},h)]})}const ct=""+new URL("instruct-flowchart-CQIN4bVV.svg",import.meta.url).href,dt=""+new URL("instruct-graph-B4NER252.svg",import.meta.url).href;function ht(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 font-bold text-center",children:"HELM Instruct: A Multidimensional Instruction Following Evaluation Framework with Absolute Ratings"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://crfm.stanford.edu/2024/02/18/helm-instruct.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{children:["We introduce ",e.jsx("em",{children:"HELM Instruct"}),", a multidimensional evaluation framework for instruction-following LLMs with absolute ratings. The framework takes an instruction, a model, an evaluator, and a criterion to generate a score. In our study, we use HELM Instruct to compare 4 instruction-following models on 7 scenarios based on 4 Human/LM evaluators and 5 criteria. Check out the blog post for more details."]}),e.jsxs("div",{className:"grid my-16 grid-cols-1 md:mx-32 md:grid-cols-2 md:gap-2",children:[e.jsx("img",{src:ct,alt:"Evaluation flowchart",className:"mx-auto block",sizes:"100vw"}),e.jsx("img",{src:dt,alt:"7 scenarios, 4 models, 4 evaluators and 5 criteria",className:"mx-auto block",sizes:"100vw"})]}),e.jsxs("table",{className:"rounded-lg shadow-md table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Average"}),e.jsx("th",{children:"Helpfulness"}),e.jsx("th",{children:"Understandability"}),e.jsx("th",{children:"Completeness"}),e.jsx("th",{children:"Conciseness"}),e.jsx("th",{children:"Harmlessness"})]})}),e.jsxs("tbody",{children:[e.jsxs("tr",{children:[e.jsx("td",{children:"openai_gpt-4-0314"}),e.jsx("td",{children:"4.63"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.85"}),e.jsx("td",{children:"4.50"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.95"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"openai_gpt-3.5-turbo-0613"}),e.jsx("td",{children:"4.60"}),e.jsx("td",{children:"4.34"}),e.jsx("td",{children:"4.86"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.41"}),e.jsx("td",{children:"4.97"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"anthropic_claude-v1.3"}),e.jsx("td",{children:"4.56"}),e.jsx("td",{children:"4.25"}),e.jsx("td",{children:"4.87"}),e.jsx("td",{children:"4.32"}),e.jsx("td",{children:"4.40"}),e.jsx("td",{children:"4.97"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"cohere_command-xlarge-beta"}),e.jsx("td",{children:"4.31"}),e.jsx("td",{children:"3.90"}),e.jsx("td",{children:"4.73"}),e.jsx("td",{children:"3.88"}),e.jsx("td",{children:"4.31"}),e.jsx("td",{children:"4.72"})]})]})]})]})}function Ie({models:s}){return e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[s.length," models"]}),e.jsx("ul",{children:s.map((t,a)=>t.todo?e.jsxs("li",{className:"text-slate-300 mt-1",children:[t.creator_organization," / ",t.display_name]},a):e.jsx(b,{to:"models",children:e.jsxs("li",{className:"text-black mt-1",children:[t.creator_organization," / ",t.display_name]},a)}))})]})}function Pe({runGroups:s}){const t=new Map(s.filter(r=>r.metric_groups!==void 0&&(r.subgroups===void 0||r.subgroups.length===0)).map(r=>[r.name,r])),a=new Set,n=[];return s.forEach(r=>{const o=r.subgroups?r.subgroups:[],l=[];o.forEach(u=>{const h=t.get(u);h&&(l.push(h),a.add(h.name))}),l.length>0&&n.push([r,l])}),e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[a.size," scenarios"]}),e.jsx("ul",{children:n.map(([r,o])=>e.jsxs("li",{className:"my-3",children:[e.jsx(b,{className:"text-black",to:"groups/"+r.name,children:e.jsx("h2",{children:r.display_name})}),e.jsx("ul",{className:"list-disc list-inside",children:o.map(l=>l.todo?e.jsx("li",{className:`${l.todo?"ml-4 text-slate-300":"ml-4"}`,children:l.display_name},l.name):e.jsx(b,{className:"text-black",to:"groups/"+l.name,children:e.jsx("li",{className:`${l.todo?"ml-4 text-slate-300":"ml-4"}`,children:l.display_name},l.name)}))})]},r.name))})]})}const He=""+new URL("helmhero-D9TvmJsp.png",import.meta.url).href;function E({runGroupName:s=void 0,tableIndexToDisplay:t=0,numRowsToDisplay:a=10,sortColumnIndex:n=1}){const[r,o]=i.useState(void 0),[l,u]=i.useState(void 0);return i.useEffect(()=>{const h=new AbortController;async function m(){const g=await O(h.signal);o(g);const j=g.run_groups;if(j.length===0)return;const y=s||j[0].name,w=await Te(y,h.signal);u(w[t])}return m(),()=>h.abort()},[s,t]),r===void 0||l===void 0?e.jsx($,{}):e.jsx("div",{className:"rounded-2xl overflow-hidden border-2 bg-white p-1 mx-2 my-0 overflow-x-auto",style:{overflow:"auto",justifyContent:"space-between"},children:e.jsx(de,{schema:r,groupTable:l,numRowsToDisplay:a,sortColumnIndex:n,displayColumnIndexes:[0,1],sortable:!1,miniStyle:!0})})}function mt(){return e.jsxs("div",{className:"flex flex-col px-4 sm:px-6 py-100 sm:py-10 sm:mb-96 md:mb-96 lg:mb-0 xl:mb-0 2xl:mb-0",children:[e.jsx("div",{className:"flex flex-col text-center mb-10 justify-start",children:e.jsx("h1",{className:"text-3xl sm:text-4xl mb-3 sm:mb-4 mx-2 mt-2",children:e.jsx("strong",{children:"A holistic framework for evaluating foundation models."})})}),e.jsxs("div",{className:"flex flex-col md:flex-col lg:flex-row lg:justify-center",children:[e.jsx("div",{className:"w-full lg:w-1/2 flex justify-center mb-4 lg:mb-0 h-full py-10",children:e.jsx("img",{src:He,alt:"HELM Hero",className:"object-contain w-96"})}),e.jsxs("div",{className:"py-2 rounded-xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-2 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function ge(){const[s,t]=i.useState(void 0);return i.useEffect(()=>{const a=new AbortController;async function n(){const r=await O(a.signal);t(r)}return n(),()=>a.abort()},[]),s?e.jsxs(e.Fragment,{children:[e.jsx(mt,{}),e.jsx("div",{className:"mx-auto text-lg px-16",children:e.jsx("div",{className:"container mx-auto",children:e.jsxs("div",{className:"grid grid-cols-1 sm:grid-cols-2 gap-8",children:[e.jsx(Ie,{models:s.models}),e.jsx(Pe,{runGroups:s.run_groups})]})})})]}):null}function ut(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Massive Multitask Language Understanding (MMLU) on HELM"}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsxs("p",{children:[e.jsx("strong",{children:"Massive Multitask Language Understanding (MMLU)"})," ",e.jsx("a",{href:"https://arxiv.org/pdf/2009.03300.pdf",className:"link",children:"(Hendrycks et al, 2020)"})," ","is a multiple-choice question answering test that covers 57 tasks including elementary mathematics, US history, computer science, law, and more. We publish evaluation results from evaluating various models on MMLU using HELM. Our evaluation results include the following:"]}),e.jsxs("ul",{className:"my-2 list-disc list-inside",children:[e.jsx("li",{children:"Simple, standardized prompts"}),e.jsx("li",{children:"Accuracy breakdown for each of the 57 subjects"}),e.jsx("li",{children:"Full transparency of all raw prompts and predictions"})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2024/05/01/helm-mmlu.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{})})]})]})}const xt=""+new URL("air-overview-DpBbyagA.png",import.meta.url).href;function ft(){const s={fontVariant:"small-caps",fontWeight:"bold"},t=e.jsx("span",{style:s,children:"AIR-Bench 2024"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:t}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsx("img",{src:xt,alt:"AIR 2024 Categories",className:"mx-auto my-4 block w-3/4",sizes:"100vw"}),e.jsxs("p",{children:["We introduce ",t,", the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in our AI Risks study, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. ",t," contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on ",t,", uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, ",t," ","provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2407.17436",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function pt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"ThaiExam"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["In collaboration with"," ",e.jsx("a",{href:"https://www.scbx.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"SCBX"})," ","and"," ",e.jsx("a",{href:"https://www.scb10x.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"SCB 10X"}),", we introduce the ThaiExam HELM leaderboard. ThaiExam is a Thai language benchmark based on examinations for high school students and investment professionals in Thailand. The ThaiExam leaderboard is the first public leaderboard for large language models on Thai language scenarios, and features evaluations of leading language models. Like all other HELM leaderboards, the ThaiExam leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the HELM framework. We hope that this leaderboard will encourage further work in multilingual language model evaluation."]}),e.jsx("div",{className:"flex flex-row justify-center my-4",children:e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Full Leaderboard"})})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function gt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Finance"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["LLMs show great potential for applications in the financial domain, yet there is a lack of financial-domain evaluations for LLMs. To help address this, we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"HELM Finance"})," leaderboard. The HELM Finance leaderboard evaluates leading LLMs on three financial benchmarks (i.e.,"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2109.00122/",children:"FinQA"}),","," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2311.11944/",children:"FinanceBench"}),","," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2020.nlp4convai-1.5/",children:"BANKING77"}),") that utilize real financial documents. Like all other HELM leaderboards, the HELM Finance leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the open-source HELM framework. We hope that this leaderboard provides valuable insights for financial practitioners."]}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through a collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.wellsfargo.com/",children:"Wells Fargo"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsx("div",{className:"flex flex-row justify-center my-4",children:e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Full Leaderboard"})})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const jt=""+new URL("heim-logo-BJtQlEbV.png",import.meta.url).href;function bt({metricFieldMap:s,metricGroups:t}){const a=new Set,n=[];return t.forEach(r=>{const o=[];r.metrics.forEach(l=>{const u=s[l.name];u&&(o.push(u),a.add(u.name))}),o.length>0&&n.push([r,o])}),e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[a.size," metrics"]}),e.jsx("ul",{children:n.map(([r,o])=>e.jsxs("li",{className:"my-3",children:[e.jsx("h4",{children:r.display_name}),e.jsx("ul",{className:"list-disc list-inside",children:o.map(l=>e.jsx("li",{className:"ml-4",children:l.display_name},l.name))})]},r.name))})]})}function vt(){const[s,t]=i.useState(void 0);i.useEffect(()=>{const n=new AbortController;async function r(){const o=await O(n.signal);t(o)}return r(),()=>n.abort()},[]);const a=s?s.metrics.reduce((n,r)=>(n[r.name]=r,n),{}):void 0;return e.jsxs("div",{className:"container mx-auto px-16 text-base",children:[e.jsx("div",{className:"container max-w-screen-lg mx-auto",children:e.jsx("img",{className:"mx-auto w-96",src:jt,alt:"HEIM Logo"})}),e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Holistic Evaluation of Text-To-Image Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2311.04287",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-2",children:["Significant effort has recently been made in developing text-to-image generation models, which take textual prompts as input and generate images. As these models are widely used in real-world applications, there is an urgent need to comprehensively understand their capabilities and risks. However, existing evaluations primarily focus on image-text alignment and image quality. To address this limitation, we introduce a new benchmark,"," ",e.jsx("strong",{children:"Holistic Evaluation of Text-To-Image Models (HEIM)"}),"."]}),e.jsx("p",{className:"my-2",children:"We identify 12 different aspects that are important in real-world model deployment, including:"}),e.jsxs("ul",{className:"my-2 list-disc list-inside unreset",children:[e.jsx("li",{children:"image-text alignment"}),e.jsx("li",{children:"image quality"}),e.jsx("li",{children:"aesthetics"}),e.jsx("li",{children:"originality"}),e.jsx("li",{children:"reasoning"}),e.jsx("li",{children:"knowledge"}),e.jsx("li",{children:"bias"}),e.jsx("li",{children:"toxicity"}),e.jsx("li",{children:"fairness"}),e.jsx("li",{children:"robustness"}),e.jsx("li",{children:"multilinguality"}),e.jsx("li",{children:"efficiency"})]}),e.jsx("p",{className:"my-2",children:"By curating scenarios encompassing these aspects, we evaluate state-of-the-art text-to-image models using this benchmark. Unlike previous evaluations that focused on alignment and quality, HEIM significantly improves coverage by evaluating all models across all aspects. Our results reveal that no single model excels in all aspects, with different models demonstrating strengths in different aspects."}),e.jsx("p",{className:"my-2",children:"For full transparency, this website contains all the prompts, generated images and the results for the automated and human evaluation metrics."}),e.jsx("p",{className:"my-2",children:"Inspired by HELM, we decompose the model evaluation into four key components: aspect, scenario, adaptation, and metric:"}),e.jsx("div",{className:"container max-w-screen-lg mx-auto my-8",children:e.jsx("img",{src:"https://crfm.stanford.edu/heim/latest/images/heim-main.png",alt:"HEIM scenarios, prompts, images and metrics"})}),s&&a?e.jsxs("div",{className:"grid grid-cols-1 md:grid-cols-3 gap-8",children:[e.jsx(Ie,{models:s.models}),e.jsx(Pe,{runGroups:s.run_groups}),e.jsx(bt,{metricFieldMap:a,metricGroups:s.metric_groups})]}):null]})}const wt=""+new URL("vhelm-framework-NxJE4fdA.png",import.meta.url).href,Nt=""+new URL("vhelm-model-ypCL5Yvq.png",import.meta.url).href,yt=""+new URL("vhelm-aspects-NiDQofvP.png",import.meta.url).href;function Lt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Holistic Evaluation of Vision-Language Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2410.07112",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-4",children:["Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermore, they differ in their evaluation procedures and the scope of the evaluation, making it difficult to compare models. To address these issues, we extend the HELM framework to VLMs to present the Holistic Evaluation of Vision Language Models (VHELM). To address these issues, we introduce VHELM, built on HELM for language models. VHELM aggregates various datasets to cover one or more of the 9 aspects:"," ",e.jsx("b",{children:"visual perception"}),", ",e.jsx("b",{children:"bias"}),", ",e.jsx("b",{children:"fairness"}),", ",e.jsx("b",{children:"knowledge"}),", ",e.jsx("b",{children:"multilinguality"}),", ",e.jsx("b",{children:"reasoning"}),", ",e.jsx("b",{children:"robustness"}),","," ",e.jsx("b",{children:"safety"}),", and ",e.jsx("b",{children:"toxicity"}),". In doing so, we produce a comprehensive, multi-dimensional view of the capabilities of the VLMs across these important factors. In addition, we standardize the standard inference parameters, methods of prompting, and evaluation metrics to enable fair comparisons across models. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast. For transparency, we release the raw model generations and complete results on this website."]}),e.jsx("p",{className:"my-4 font-bold",children:"VHELM is intended to be a living benchmark. We hope to continue adding new datasets, models and metrics over time, so please stay tuned!"}),e.jsxs("div",{className:"my-16 flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("img",{src:Nt,alt:"A vision-lanuage model (VLM) takes in an image and a text prompt and generates text.",className:""}),e.jsx("img",{src:wt,alt:"An example of an evaluation for an Aspect (Knowledge) - a Scenario (MMMU) undergoes Adaptation (multimodal multiple choice) for a Model (GPT-4 Omni), then Metrics (Exact match) are computed",className:""})]}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})]})]}),e.jsx("div",{className:"container max-w-screen-lg mx-auto my-8",children:e.jsx("img",{src:yt,alt:"An example of each aspect in VHELM: Visual Perception, Bias, Fairness, Knowledge, Multilinguality, Reasoning, Robustness, Toxicity Mitigation and Safety. ",className:""})})]})}function Mt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Chinese Language Models EVAluation Platform (CLEVA)"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["In collaboration with the"," ",e.jsx("a",{href:"https://lwwangcse.github.io/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"LaVi Lab"})," ","team from"," ",e.jsx("a",{href:"https://www.cuhk.edu.hk/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"The Chinese University of Hong Kong (CUHK)"}),", we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"Chinese Language Models EVAluation Platform (CLEVA)"})," ","leaderboard on HELM. CLEVA is a comprehensive Chinese-language benchmark for holistic evaluation of Chinese-language LLMs, and employs a standardized workflow to assess LLMs' performance across various dimensions."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2308.04813",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Et(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"The Mighty ToRR: A Benchmark for Table Reasoning and Robustness"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://research.ibm.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"IBM Research"}),"."]}),e.jsxs("p",{className:"my-4",children:["Despite its real-world significance, model performance on tabular data remains underexplored, leaving uncertainty about which model to rely on and which prompt configuration to adopt. To address this gap, we create ",e.jsx("strong",{className:"font-bold",children:"ToRR"}),", a benchmark for Table Reasoning and Robustness, a varied benchmark that measures model performance and robustness on table-related tasks. The benchmark includes 10 datasets that cover different types of table reasoning capabilities across varied domains. ToRR goes beyond model performance rankings, and is designed to reflect whether models can handle tabular data consistently and robustly, across a variety of common table representation formats. We present a leaderboard as well as comprehensive analyses of the results of leading models over ToRR. Our results reveal a striking pattern of brittle model behavior, where even strong models are unable to perform robustly on tabular data tasks. Although no specific table format leads to consistently better performance, we show that testing over multiple formats is crucial for reliably estimating model capabilities. Moreover, we show that the reliability boost from testing multiple prompts can be equivalent to adding more test examples. Overall, our findings show that reasoning over table tasks remains a significant challenge."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4 hidden",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const kt=({id:s,title:t,text:a})=>((t==="Classic"||t==="Lite"||t==="Instruct")&&(t="HELM "+t),e.jsx("div",{className:"max-w-sm rounded overflow-hidden bg-gray-100 hover:scale-105 transition-transform duration-300",children:e.jsx("a",{href:oe(void 0,s),children:e.jsxs("div",{className:"px-6 py-4",children:[e.jsxs("div",{className:"font-bold text-xl mb-2",children:[e.jsx("div",{className:"py-3",children:e.jsx("svg",{fill:"#000000",width:"20px",height:"20px",viewBox:"0 0 24 24",xmlns:"http://www.w3.org/2000/svg",children:e.jsx("path",{d:"M22,7H16.333V4a1,1,0,0,0-1-1H8.667a1,1,0,0,0-1,1v7H2a1,1,0,0,0-1,1v8a1,1,0,0,0,1,1H22a1,1,0,0,0,1-1V8A1,1,0,0,0,22,7ZM7.667,19H3V13H7.667Zm6.666,0H9.667V5h4.666ZM21,19H16.333V9H21Z"})})}),t+" →"]}),e.jsx("p",{className:"text-gray-700 text-base",children:a})]})})}));function St(){const[s,t]=i.useState();return i.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(a=>a.json()).then(a=>{t(a)}).catch(a=>{console.error("Error fetching JSON:",a)})},[]),e.jsx("div",{className:"p-10 mb-20",children:e.jsx("div",{className:"grid grid-cols-2 lg:grid-cols-3 gap-4",children:s&&s.map((a,n)=>a.id==="home"?null:e.jsx(kt,{id:a.id,title:a.title,text:a.description},n))})})}function At(){return e.jsxs("div",{className:"flex flex-col md:flex-row px-6 py-32",children:[e.jsxs("div",{className:"flex-1 p-4 flex flex-col justify-center",children:[e.jsx("div",{className:"flex justify-start",children:e.jsxs("div",{children:[e.jsx("h1",{className:"text-4xl mb-4 mx-4 mt-2",children:e.jsx("strong",{children:"A reproducible and transparent framework for evaluating foundation models."})}),e.jsx("h3",{className:`text-xl - mb-4 mx-4 mt-2`,children:"Find leaderboards with many scenarios, metrics, and models with support for multimodality and model-graded evaluation."})]})}),e.jsxs("div",{className:"flex flex-col md:flex-row justify-start mt-6 ml-4",children:[e.jsx("button",{className:"px-6 btn btn-grey rounded-md mb-4 md:mb-0",onClick:()=>window.scrollTo({top:760,behavior:"smooth"}),children:e.jsx("div",{children:"Leaderboards ↓"})}),e.jsx("button",{className:"px-6 btn btn-grey rounded-md md:ml-4",children:e.jsx("a",{href:"https://github.com/stanford-crfm/helm",children:"Github"})})]})]}),e.jsx("div",{className:"mx-4 mt-6 md:mt-0 md:w-1/3",children:e.jsx("img",{src:He,alt:"HELM Hero",className:"object-cover w-full h-full"})})]})}function Rt(){const[s,t]=i.useState(void 0);return i.useEffect(()=>{const a=new AbortController;async function n(){const r=await O(a.signal);t(r)}return n(),()=>a.abort()},[]),s?e.jsxs(e.Fragment,{children:[e.jsx(At,{}),e.jsx("div",{className:"container py-5 mx-auto text-lg",children:e.jsx("div",{className:"flex flex-col sm:flex-row justify-center mb-10 flex sm:gap-8 md:gap-32",children:e.jsx("h1",{className:"text-4xl mx-4 ",children:e.jsx("strong",{children:"HELM Leaderboards"})})})}),e.jsx(St,{})]}):null}const _t=""+new URL("overview-BwypNWnk.png",import.meta.url).href,Ct=""+new URL("process-flow-DWDJC733.png",import.meta.url).href;function Tt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-2 md:gap-8 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2410.22456",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-latex",children:"Latex dataset"}),e.jsx("a",{className:"px-5 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-webpage",children:"Webpage dataset"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-musicsheet",children:"Music sheet dataset"})]}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsxs("p",{children:[e.jsx("strong",{children:"Image2Struct"})," is a benchmark for evaluating vision-language models in practical tasks of extracting structured information from images."]}),e.jsx("br",{}),e.jsx("p",{children:"In our tasks, VLMs are prompted to generate the underlying structured information (i.e., code) from an input image. The code can be compiled, and the output image is evaluated against the input image to produce a score. This round-trip evaluation allows us to quantitatively evaluate VLMs on complex tasks with multiple correct answers. We create a pipeline that downloads fresh, user-submitted data from active online communities upon execution, evaluates the VLMs shortly, and produces a leaderboard."}),e.jsx("br",{}),e.jsx("img",{src:_t,alt:"Evaluation flowchart",className:"mx-auto block w-full",sizes:"100vw"}),e.jsx("br",{}),e.jsx("p",{children:"We introduce 3 tasks:"}),e.jsxs("ul",{className:"my-2 list-disc list-inside",children:[e.jsx("li",{children:"LaTex: equations, tables, plots and algorithms from ArXiV papers."}),e.jsx("li",{children:"Webpages: pages from GitHub written in HTML, CSS and Javascript. ..."}),e.jsx("li",{children:"Music sheets: crops of measures from IMSLP music sheets."})]}),e.jsx("div",{className:"flex flex-row justify-center mt-8",children:e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Full Leaderboard"})})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{numRowsToDisplay:12})})]}),e.jsx("br",{}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("p",{children:"We provide an automated process for collecting new fresh data from online communities, evaluating the models and producing a leaderboard. The pipeline is designed to be executed on a regular basis to keep the leaderboard up-to-date."}),e.jsx("br",{}),e.jsxs("p",{children:["In addition to the automated data collection, we also provide a"," ",e.jsx("i",{children:"wild"})," subset for the LaTeX and webpage tasks that are collected from Wikipedia and various popular websites. These instances do not have a corresponding code, and the evaluation is done by our proposed metric: block EMD (Earth Mover Distance)."]})]}),e.jsx("div",{className:"flex-1",children:e.jsx("img",{src:Ct,alt:"7 scenarios, 4 models, 4 evaluators and 5 criteria",className:"mx-auto block w-full",sizes:"200vw"})})]})]})}function It(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Elements of World Knowledge (EWoK)"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["We present the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2405.09605",children:"Elements of World Knowledge (EWoK)"})," ","leaderboard in collaboration with the EWoK team. EWoK is a benchmark for evaluating world modeling in language models by testing their ability to use knowledge of a concept to match a target text with a plausible/implausible context. EWoK targets specific concepts from multiple knowledge domains known to be vital for world modeling in humans, including social interactions and spatial relations."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2405.09605",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Pt=""+new URL("medhelm-overview-CND0EIsy.png",import.meta.url).href;function Ht(){const s=e.jsx("strong",{className:"font-bold",children:"MedHELM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"MedHELM"}),e.jsx("p",{className:"text-xl my-4 italic text-center",children:"Holistic Evaluation of Large Language Models for Medical Tasks"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[7] text-l",children:[e.jsxs("p",{className:"my-",children:["We introduce ",s,", an extensible evaluation framework for assessing LLM performance for medical tasks. Building on the HELM framework, ",s," comprises a structured taxonomy with 5 categories, 22 subcategories, and 121 distinct clinical tasks as well as 35 distinct benchmarks (14 private, 7 gated-access, and 14 public). The benchmarks represent a spectrum of healthcare scenarios, from diagnostic decision-making to patient communication, providing a more nuanced and medically relevant assessment of AI capabilities in healthcare settings."]}),e.jsx("img",{src:Pt,alt:"MedHELM Task Categories",className:"mx-auto my-4 block w-7/8",sizes:"100vw"}),e.jsxs("p",{className:"my-4",children:[s," establishes a foundation for testing and evaluation of the real-world applicability of language models in healthcare. It is made possible by a unique collaboration between the Center for Research on Foundation Models, Technology and Digital Solutions at Stanford Healthcare, and Microsoft Healthcare and Life Sciences in partnership with faculty in the Departments of Medicine, Computer Science, Anesthesiology, Dermatology, Pediatrics and Biomedical Data Science as well as trainees from the MCiM program at the Clinical Excellence Research Center. The effort is coordinated by the Center for Biomedical Informatics Research."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://www.nature.com/articles/s41591-025-04151-2",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm-helm.readthedocs.io/en/latest/medhelm/",children:"Documentation"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://hai.stanford.edu/news/holistic-evaluation-of-large-language-models-for-medical-applications",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[3] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const $t=""+new URL("medhelm-v1-overview-Cu2tphBB.png",import.meta.url).href;function Dt(){const s=e.jsx("strong",{className:"font-bold",children:"MedHELM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"MedHELM"}),e.jsx("p",{className:"text-xl my-4 italic text-center",children:"Medical and AI experts build a benchmark for evaluation of LLMs grounded in real-world healthcare needs."}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["We introduce ",s,", a comprehensive healthcare benchmark to evaluate language models on real-world clinical tasks using real electronic health records. Building on the HELM framework,"," ",s," comprises a structured taxonomy with 5 categories, 22 subcategories, and 121 distinct clinical tasks as well as 31 diverse datasets (12 private, 6 gated-access, and 13 public). The datasets represent a spectrum of healthcare scenarios, from diagnostic decision-making to patient communication, providing a more nuanced and clinically relevant assessment of AI capabilities in healthcare settings."]}),e.jsx("img",{src:$t,alt:"MedHELM Task Categories",className:"mx-auto my-4 block w-7/8",sizes:"100vw"}),e.jsxs("p",{className:"my-4",children:[s," establishes a foundation for testing and evaluation of the real-world applicability of language models in healthcare. It is made possible by a unique collaboration between the Center for Research on Foundation Models, Technology and Digital Solutions at Stanford Healthcare, and Microsoft Healthcare and Life Sciences in partnership with faculty in the Departments of Medicine, Computer Science, Anesthesiology, Dermatology, Pediatrics and Biomedical Data Science as well as trainees from the MCiM program at the Clinical Excellence Research Center. The effort is coordinated by the Center for Biomedical Informatics Research."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2505.23802",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm-helm.readthedocs.io/en/latest/medhelm/",children:"Documentation"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://hai.stanford.edu/news/holistic-evaluation-of-large-language-models-for-medical-applications",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Bt=""+new URL("helm-safety-COfndXuS.png",import.meta.url).href;function Ot(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"HELM Safety"}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("img",{src:Bt,alt:"Logo",className:"mx-auto p-0 block",style:{width:"300px"}}),e.jsx("p",{children:"Language models demonstrate powerful capabilities and pose significant risks. Given their widespread deployment, standardized public benchmarking of such models is vital. While language models are routinely evaluated on standard capability benchmarks, comparable standardization for benchmarking safety risks lags behind. To address this gap, we introduce HELM-Safety as a collection of 5 safety benchmarks that span 6 risk categories (e.g. violence, fraud, discrimination, sexual, harassment, deception). We present evaluation results for recent leading open weights and closed models."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2024/11/08/helm-safety.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{})})]})]})}function Ft(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Capabilities"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["Building on the HELM framework, we introduce"," ",e.jsx("strong",{className:"font-bold",children:"HELM Capabilities"})," to capture our latest thinking on the evaluation of general capabilities. HELM Capabilities is a new benchmark and leaderboard that consists of a curated set of scenarios for measuring various capabilities of language models. Like all other HELM leaderboards, the HELM Capabilities leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the HELM framework."]}),e.jsxs("div",{className:"flex flex-row justify-center my-4",children:[e.jsx("a",{href:"https://crfm.stanford.edu/2025/03/20/helm-capabilities.html",className:"px-10 btn rounded-md mx-4",children:"Blog Post"}),e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Ut(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"MMLU-Winogrande-Afr: Clinical MMLU and Winogrande in 11 low-resource African languages"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://ghamut.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"Ghamut Corporation"})," ","and the"," ",e.jsx("a",{href:"https://www.gatesfoundation.org/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"Gates Foundation"}),"."]}),e.jsx("p",{className:"my-4",children:"Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2412.12417",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function qt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://aisingapore.org/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"AI Singapore"}),"."]}),e.jsxs("p",{className:"my-4",children:["With the rapid emergence of novel capabilities in Large Language Models (LLMs), the need for rigorous multilingual and multicultural benchmarks that are integrated has become more pronounced. Though existing LLM benchmarks are capable of evaluating specific capabilities of LLMs in English as well as in various mid- to low-resource languages, including those in the Southeast Asian (SEA) region, a comprehensive and authentic evaluation suite for the SEA languages has not been developed thus far. Here, we present"," ",e.jsx("strong",{className:"font-bold",children:"SEA-HELM"}),", a holistic linguistic and cultural LLM evaluation suite that emphasizes SEA languages, comprising five core pillars: (1) NLP Classics, (2) LLM-specifics, (3) SEA Linguistics, (4) SEA Culture, (5) Safety. SEA-HELM currently supports Filipino, Indonesian, Tamil, Thai, and Vietnamese. We also introduce the SEA-HELM leaderboard, which allows users to understand models' multilingual and multicultural performance in a systematic and user-friendly manner."]}),e.jsxs("p",{className:"mb-4 italic",children:["Additional evaluation results are available on the external"," ",e.jsx("a",{href:"https://leaderboard.sea-lion.ai/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"AI Singapore (AISG) SEA-HELM leaderboard"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2502.14301",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"HELM Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://leaderboard.sea-lion.ai/",children:"AISG Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Wt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Speech"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsx("p",{className:"my-4",children:"We present a HELM leaderboard for speech tasks."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function zt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Long Context"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsx("p",{className:"my-4",children:"Recent Large Language Models (LLMs) support processing long inputs with hundreds of thousands or millions of tokens. Long context capabilities are important for many real-world applications, such as processing long text documents, conducting long conversations or following complex instructions. However, support for long inputs does not equate to strong long context capabilities. As such, there is a need for rigorous and comprehensive evaluations of long context capabilities."}),e.jsxs("p",{className:"my-4",children:["To address this, we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"HELM Long Context"})," ","leaderboard, which provides transparent, comparable and reproducible evaluations of long context capabilities of recent models. The benchmark consists of 5 tasks:"]}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/ruler_squad",children:e.jsx("strong",{className:"font-bold",children:"RULER SQuAD"})})," ","— open ended single-hop question answering on passages"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/ruler_hotpotqa",children:e.jsx("strong",{className:"font-bold",children:"RULER HotPotQA"})})," ","— open ended multi-hop question answering on passages"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/infinite_bench_en_qa",children:e.jsx("strong",{className:"font-bold",children:"∞Bench En.MC"})})," ","— multiple choice question answering based on the plot of a novel"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/infinite_bench_en_sum",children:e.jsx("strong",{className:"font-bold",children:"∞Bench En.Sum"})})," ","— summarization of the plot of a novel"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/openai_mrcr",children:e.jsx("strong",{className:"font-bold",children:"OpenAI MRCR"})})," ","— multi-round co-reference resolution on a long, multi-turn, synthetic conversation"]})]}),e.jsx("p",{className:"my-4",children:"The results demonstrate that even though significant progress has been made on long context capabilities, there is still considerable room for improvement."}),e.jsx("p",{className:"my-4",children:"As with all HELM leaderboards, this leaderboard provides full transparency into all LLM requests and responses, and the results are reproducible using the HELM open source framework."}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through research collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.lvmh.com/",children:"LVMH"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2025/09/29/helm-long-context.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Vt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM SQL"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4",children:["Text-to-SQL is the task of converting natural language instructions into SQL code. There has been increasing interest in text-to-SQL for applications by data scientists in various domains. Thus, we introduce the ",e.jsx("strong",{className:"font-bold",children:"HELM SQL"})," ","leaderboard for text-to-SQL evaluations. The HELM SQL leaderboard evaluates leading LLMs on two existing text-to-SQL benchmarks (Spider, BIRD-SQL) that cover a range of professional domains. In addition, we introduce a new benchmark,"," ",e.jsx("strong",{className:"font-bold",children:"CzechBankQA"}),", a text-to-SQL benchmark based on a real public bank customer relational database, to address the lack of coverage of text-to-SQL in the financial domain. CzechBankQA consists of text-to-SQL queries and gold labels provided by professionals at Wells Fargo. We hope that this leaderboard provides useful insights for data science practitioners."]}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through research collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.wellsfargo.com/",children:"Wells Fargo"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4 hidden",href:"#",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Jt(){const s=e.jsx("strong",{className:"font-bold",children:"ViLLM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"ViLLM: Crossing Linguistic Horizon"}),e.jsxs("p",{className:"text-xl my-4 italic text-center",children:[s," is a comprehensive benchmark suite for evaluating the performance of language models in ",e.jsx("strong",{children:"Vietnamese"}),"."]}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["As multilingual large language models (LLMs) continue to advance natural language processing, bridging communication across diverse cultures and languages, their effectiveness in lower-resourced languages like Vietnamese remains limited. Despite being trained on large multilingual corpora, most open-source LLMs struggle with Vietnamese understanding and generation.",e.jsx("strong",{children:" ViLLM"})," addresses this gap by providing a robust evaluation framework tailored specifically for Vietnamese. It includes ",e.jsx("strong",{children:"11 essential scenarios"}),", each targeting a core capability of Vietnamese LLMs:"]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"ViLLM"})," includes 11 carefully designed evaluation scenarios, each addressing a core language modeling capability:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"Question Answering:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/juletxara/xquad_xtreme",children:"XQuAD"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/facebook/mlqa",children:"MLQA"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Summarization:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/Yuhthe/vietnews",children:"VietNews"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/GEM/wiki_lingua",children:"WikiLingua"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Sentiment Analysis:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/vlsp2016",children:"VLSP2016"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-VSFC",children:"UiT-VSFC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Text Classification:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/PhoATIS",children:"PhoATIS"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-VSMEC",children:"UiT-VSMEC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Knowledge:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/zalo_e2eqa",children:"ZaloE2E"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/ViMMRC",children:"UiT-ViMMRC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Toxic Detection:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-ViHSD",children:"UiT-VIHSD"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/tarudesu/ViCTSD",children:"UiT-ViCTSD"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Information Retrieval:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/unicamp-dl/mmarco",children:"mMARCO"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/unicamp-dl/mrobust",children:"mRobust04"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Language Modeling:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/MLQA",children:"MLQA"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/VSEC",children:"VSEC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Reasoning:"})," ",e.jsx("a",{className:"link-primary",href:"",children:"Synthetic reasoning"}),","," ",e.jsx("a",{className:"link-primary",href:"",children:"Natural synthetic reasoning"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Mathematic:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/Vietnamese-MATH",children:"MATH"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Translation:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/vietgpt/opus100_envi",children:"OPUS100"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/PhoMT",children:"PhoMT"})]})]})]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"ViLLM"})," also includes tools to promote the ethical and responsible use of language models:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"Bias Assessment:"})," Detects and mitigates biased patterns in model outputs."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Toxicity Assessment:"})," Monitors and controls the generation of harmful or offensive content."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Fairness Evaluation:"})," Ensures equitable performance across demographic groups and languages."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Robustness Analysis:"})," Evaluates model stability against noisy or adversarial inputs in real-world scenarios."]})]})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://aclanthology.org/2024.findings-naacl.182",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Gt(){const s=e.jsx("strong",{className:"font-bold",children:"SLPHelm"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"SLPHelm: Advancing Speech Language Processing"}),e.jsxs("p",{className:"text-xl my-4 italic text-center",children:[s," is a comprehensive benchmark suite for evaluating the performance of speech language models across multiple languages and tasks."]}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["As speech language models continue to evolve and transform how we interact with technology, there is a growing need for standardized evaluation frameworks that can assess their capabilities across diverse languages and tasks. Despite significant advances in speech processing, many models struggle with multilingual understanding, accent recognition, and domain-specific speech tasks."," ",e.jsx("strong",{children:"SLPHelm"})," addresses these challenges by providing a robust evaluation framework that includes",e.jsx("strong",{children:" 5 key scenarios"})," across ",e.jsx("strong",{children:"15 models"}),", each targeting essential speech processing capabilities:"]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"SLPHelm"})," includes 5 carefully designed evaluation scenarios, each addressing a core speech processing capability:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsx("li",{children:e.jsx("strong",{children:"Disorder Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Transcription Accuracy"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Type Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Symptom Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Diagnosis via Transcription"})})]})]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"SLPHelm"})," evaluates models using comprehensive datasets:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"UltraSuite:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmUltraSuite",children:"UltraSuite"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"ENNI:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/ENNI",children:"ENNI"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"LeNormand:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/LeNormand",children:"LeNormand"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"PERCEPT-GFTA:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/PERCEPT-GFTA",children:"PERCEPT-GFTA"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"UltraSuite w/ Manual Labels:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmManualLabels",children:"SLPHelmManualLabels"})]})]})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Qt=""+new URL("audio-table-Dn5NMMeJ.png",import.meta.url).href;function Zt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Holistic Evaluation of Audio-Language Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2508.21376",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-4",children:["Evaluations of"," ",e.jsx("strong",{className:"font-bold",children:"audio-language models (ALMs)"})," ","— multimodal models that take interleaved audio and text as input and output text — are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters."]}),e.jsxs("p",{className:"my-4",children:["To address these shortfalls, we introduce"," ",e.jsx("strong",{className:"font-bold",children:"AHELM"}),", a benchmark that aggregates various datasets — including"," ",e.jsx("strong",{className:"font-bold",children:"2 new synthetic audio-text datasets"})," ","called ",e.jsx("strong",{className:"font-bold",children:"PARADE"}),", which evaluates the ALMs on avoiding stereotypes, and"," ",e.jsx("strong",{className:"font-bold",children:"CoRe-Bench"}),", which measures reasoning over conversational audio through inferential multi-turn question answering — to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs:"," ",e.jsx("em",{className:"italic",children:"audio perception"}),","," ",e.jsx("em",{className:"italic",children:"knowledge"}),","," ",e.jsx("em",{className:"italic",children:"reasoning"}),","," ",e.jsx("em",{className:"italic",children:"emotion detection"}),","," ",e.jsx("em",{className:"italic",children:"bias"}),", ",e.jsx("em",{className:"italic",children:"fairness"}),","," ",e.jsx("em",{className:"italic",children:"multilinguality"}),","," ",e.jsx("em",{className:"italic",children:"robustness"}),","," ",e.jsx("em",{className:"italic",children:"toxicity"}),", and"," ",e.jsx("em",{className:"italic",children:"safety"}),". We standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models."]}),e.jsxs("div",{className:"my-16 flex flex-col lg:flex-row gap-8",children:[e.jsx("div",{className:"flex-1 text-xl",children:e.jsx("img",{src:Qt,alt:"An example of each aspect in AHELM: Auditory Perception, Knowledge, Reasoning, Emotion Detection, Bias, Fairness, Multilinguality, Robustness, Toxicity and Safety. ",className:""})}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})]})]})]})}function Kt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Arabic"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsxs("p",{className:"my-4",children:["As part of our efforts to better understand the multilingual capabilities of large language models (LLMs), we present"," ",e.jsx("strong",{className:"font-bold",children:"HELM Arabic"}),", a leaderboard for transparent and reproducible evaluation of LLMs on Arabic language benchmarks. This leaderboard was produced in collaboration with"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arabic.ai/",children:"Arabic.AI"}),"."]}),e.jsxs("p",{className:"my-4",children:["HELM Arabic builds on a collection of established Arabic-language evaluation tasks that are widely used in the research community (",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"El Filali et al., 2025"}),"). It includes the following seven benchmarks:"]}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/OALL/AlGhafa-Arabic-LLM-Benchmark-Native",children:"AlGhafa"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2023.arabicnlp-1.21/",children:"Almazrouei et al., 2023"}),") — an Arabic language multiple choice evaluation benchmark derived from publicly available NLP datasets"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/ArabicMMLU",children:"ArabicMMLU"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2024.findings-acl.334/",children:"Koto et al., 2024"}),") — a native Arabic language question answering benchmark using questions sourced from school exams across diverse educational levels in different countries spanning North Africa, the Levant, and the Gulf regions"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/mhardalov/exams",children:"Arabic EXAMS"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2020.emnlp-main.438/",children:"Hardalov et al., 2020"}),") — the Arabic language subset of the EXAMS multilingual question answering benchmark, which consists of high school exam questions across various school subjects"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/MadinahQA",children:"MadinahQA"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2024.findings-acl.334/",children:"Koto et al., 2024"}),") — a question answering benchmark published by MBZUAI that tests knowledge of Arabic language and grammar"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/asas-ai/AraTrust",children:"AraTrust"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"Alghamdi et al., 2025"}),") — an Arab-region-specific safety evaluation dataset consisting of human-written questions including direct attacks, indirect attacks, and harmless requests with sensitive words"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/OALL/ALRAGE",children:"ALRAGE"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"El Filali et al., 2025"}),") — an Arabic language passage-based open-ended model-graded question answering benchmark that reflects retrieval-augmented generation use cases"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/human_translated_arabic_mmlu",children:"ArbMMLU-HT"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2308.16149",children:"Sengupta et al., 2023"}),") — a translation of MMLU to Arabic by human translators published by MBZUAI"]})]}),e.jsxs("p",{className:"my-4",children:["The"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm.stanford.edu/helm/arabic/latest/",children:"leaderboard results"})," ","show that LLMs have made significant progress in Arabic language understanding over the last few years. As with all HELM leaderboards, this leaderboard provides full transparency into all LLM requests and responses, and the results are"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm-helm.readthedocs.io/en/latest/reproducing_leaderboards/",children:"reproducible"})," ","using the"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://github.com/stanford-crfm/helm/",children:"HELM open source framework"}),". We hope that this leaderboard will be a valuable resource for the Arabic NLP community."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2025/12/18/helm-arabic.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Xt(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Arabic"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsxs("p",{className:"my-4",children:["We present"," ",e.jsx("strong",{className:"font-bold",children:"HELM Arabic Enterpise"}),", a leaderboard for transparent and reproducible evaluation of LLMs on Arabic language benchmarks for enterprise use cases. This leaderboard was created in collaboration with"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arabic.ai/",children:"Arabic.AI"}),"."]}),e.jsx("p",{className:"my-4",children:"HELM Arabic Enterprise introduces new datasets for the following tasks:"}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsxs("li",{children:[e.jsx("strong",{className:"font-bold",children:"Content Generation"})," — Given summaries of from real news articles, the LLM is prompted to generate new articles in a corporate style. The generated articles are then graded by an LLM-as-judge for faithfulness, completeness, and style adherence."]}),e.jsxs("li",{children:[e.jsx("strong",{className:"font-bold",children:"Financial"})," — Given questions from English language finance textbooks that have been translated to Arabic using machine translation, the LLM is prompted to answer the questions in one of the following three settings. In the MCQ setting, the LLM must choose between three possible choices. In the boolean setting, the LLM must decide if a given statement is true or false. In the calculation setting, the LLM must perform mathematical calculations to produce a numeric answer."]}),e.jsxs("li",{children:[e.jsx("strong",{className:"font-bold",children:"Legal"})," — Given open-ended questions written by Arabic legal experts, the LLM is prompted to respond with short answers to the questions in one of the following two settings. In the RAG setting, the LLM is also provided with the relevant legal statute in the prompt. In the QA setting, the LLM is not provided with the relevant legal statute, and must answer relying only on its domain knowledge."]})]}),e.jsxs("p",{className:"my-4",children:["The"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm.stanford.edu/helm/arabic-enterprise/latest/",children:"leaderboard results"})," ","show a wide range of scores on these tasks. As with all HELM leaderboards, this leaderboard provides full transparency into all LLM requests and responses, and the results are"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm-helm.readthedocs.io/en/latest/reproducing_leaderboards/",children:"reproducible"})," ","using the"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://github.com/stanford-crfm/helm/",children:"HELM open source framework"}),". We hope that this leaderboard will be a valuable resource for the Arabic NLP community."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#",children:"Blog Post (Upcoming)"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Yt=""+new URL("overview-CVXNopt8.png",import.meta.url).href;function ea(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsxs("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:[e.jsx("strong",{children:"RoboReward"}),": General-purpose Vision-Language Reward Models for Robotics"]}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-4 md:gap-8 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2601.00675",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://crfm.stanford.edu/helm/robo-reward-bench/latest/#/leaderboard",children:"Full Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/teetone/RoboReward",children:"RoboReward Dataset"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/teetone/RoboReward-4B",children:"RoboReward 4B"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/teetone/RoboReward-8B",children:"RoboReward 8B"})]}),e.jsx("p",{className:"my-4",children:"A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotic domains, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives. Vision-language models (VLMs) have shown promise as automatic reward models, yet their effectiveness on real robot tasks is poorly understood."}),e.jsxs("p",{className:"my-4",children:["In this work, we aim to close this gap by introducing (1)"," ",e.jsx("strong",{children:"RoboReward"}),", a robotics reward dataset and benchmark built on large-scale real-robot corpora from Open X-Embodiment (OXE) and RoboArena, and (2) vision-language reward models trained on this dataset (",e.jsx("strong",{children:"RoboReward 4B/8B"}),"). Because OXE is success-heavy and lacks failure examples, we propose a"," ",e.jsx("em",{children:"negative examples data augmentation"})," pipeline that generates calibrated ",e.jsx("em",{children:"negatives"})," and ",e.jsx("em",{children:"near-misses"})," via counterfactual relabeling of successful episodes and temporal clipping to create partial-progress outcomes from the same videos."]}),e.jsx("p",{className:"my-4",children:"Using this framework, we produce an extensive training and evaluation dataset that spans diverse tasks and embodiments and enables systematic evaluation of whether state-of-the-art VLMs can reliably provide rewards for robotics. Our evaluation of leading open-weight and proprietary VLMs reveals that no model excels across all tasks, underscoring substantial room for improvement. We then train general-purpose 4B- and 8B-parameter models that outperform much larger VLMs in assigning rewards for short-horizon robotic tasks. Finally, we deploy the 8B reward VLM in real-robot reinforcement learning and find that it improves policy learning over Gemini Robotics-ER 1.5, a frontier physical reasoning VLM trained on robotics data, by a large margin, while substantially narrowing the gap to RL training with human-provided rewards."}),e.jsxs("div",{className:"my-12 flex flex-col lg:flex-row gap-8 items-start",children:[e.jsx("div",{className:"flex-1",children:e.jsx("img",{src:Yt,alt:"RoboReward overview",className:"w-full max-w-full rounded-lg shadow"})}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-3 btn bg-white rounded-md",children:e.jsx("span",{children:"See more"})})]})]})]})}function sa(){return window.PROJECT_ID==="lite"?e.jsx(ge,{}):window.PROJECT_ID==="instruct"?e.jsx(ht,{}):window.PROJECT_ID==="image2struct"?e.jsx(Tt,{}):window.PROJECT_ID==="heim"?e.jsx(vt,{}):window.PROJECT_ID==="mmlu"?e.jsx(ut,{}):window.PROJECT_ID==="vhelm"?e.jsx(Lt,{}):window.PROJECT_ID==="air-bench"?e.jsx(ft,{}):window.PROJECT_ID==="thaiexam"?e.jsx(pt,{}):window.PROJECT_ID==="finance"?e.jsx(gt,{}):window.PROJECT_ID==="cleva"?e.jsx(Mt,{}):window.PROJECT_ID==="torr"?e.jsx(Et,{}):window.PROJECT_ID==="ewok"?e.jsx(It,{}):window.PROJECT_ID==="medhelm"&&window.RELEASE=="v1.0.0"?e.jsx(Dt,{}):window.PROJECT_ID==="medhelm"?e.jsx(Ht,{}):window.PROJECT_ID==="safety"?e.jsx(Ot,{}):window.PROJECT_ID==="capabilities"?e.jsx(Ft,{}):window.PROJECT_ID==="mmlu-winogrande-afr"?e.jsx(Ut,{}):window.PROJECT_ID==="seahelm"?e.jsx(qt,{}):window.PROJECT_ID==="speech"?e.jsx(Wt,{}):window.PROJECT_ID==="sql"?e.jsx(Vt,{}):window.PROJECT_ID==="long-context"?e.jsx(zt,{}):window.PROJECT_ID==="villm"?e.jsx(Jt,{}):window.PROJECT_ID==="slphelm"?e.jsx(Gt,{}):window.PROJECT_ID==="audio"?e.jsx(Zt,{}):window.PROJECT_ID==="arabic"?e.jsx(Kt,{}):window.PROJECT_ID==="robo-reward-bench"?e.jsx(ea,{}):window.PROJECT_ID==="arabic-enterprise"?e.jsx(Xt,{}):window.PROJECT_ID==="home"?e.jsx(Rt,{}):e.jsx(ge,{})}function ta(){return e.jsx(qe,{children:e.jsx(We,{children:e.jsxs(P,{path:"/",element:e.jsx(fs,{}),children:[e.jsx(P,{index:!0,element:e.jsx(sa,{})}),e.jsx(P,{path:"leaderboard",element:e.jsx(te,{})}),e.jsx(P,{path:"leaderboard/:groupName",element:e.jsx(te,{})}),e.jsx(P,{path:"models",element:e.jsx(vs,{})}),e.jsx(P,{path:"scenarios",element:e.jsx(ws,{})}),e.jsx(P,{path:"groups",element:e.jsx(Ms,{})}),e.jsx(P,{path:"groups/:groupName",element:e.jsx(te,{})}),e.jsx(P,{path:"runs",element:e.jsx(ks,{})}),e.jsx(P,{path:"runs/:runName",element:e.jsx(lt,{})})]})})})}Qe.createRoot(document.getElementById("root")).render(e.jsx(ze.StrictMode,{children:e.jsx(ta,{})})); +import{j as e,g as F,c as z,m as te,s as je,b as $e,p as me,y as De,a as ue,d as re,e as ie}from"./tremor-B1ftEuaD.js";import{d as Be,g as Oe,r as l,L as b,O as Fe,u as le,e as be,f as Ue,H as qe,h as We,i as I,R as ze}from"./react-D3IQTVQZ.js";import{R as Ve}from"./react-markdown-DTLembof.js";import"./recharts-DhnSad7c.js";(function(){const a=document.createElement("link").relList;if(a&&a.supports&&a.supports("modulepreload"))return;for(const r of document.querySelectorAll('link[rel="modulepreload"]'))n(r);new MutationObserver(r=>{for(const o of r)if(o.type==="childList")for(const i of o.addedNodes)i.tagName==="LINK"&&i.rel==="modulepreload"&&n(i)}).observe(document,{childList:!0,subtree:!0});function t(r){const o={};return r.integrity&&(o.integrity=r.integrity),r.referrerPolicy&&(o.referrerPolicy=r.referrerPolicy),r.crossOrigin==="use-credentials"?o.credentials="include":r.crossOrigin==="anonymous"?o.credentials="omit":o.credentials="same-origin",o}function n(r){if(r.ep)return;r.ep=!0;const o=t(r);fetch(r.href,o)}})();var G={},xe;function Je(){if(xe)return G;xe=1;var s=Be();return G.createRoot=s.createRoot,G.hydrateRoot=s.hydrateRoot,G}var Ge=Je();const Qe=Oe(Ge);function Ze({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"M3.75 6.75h16.5M3.75 12h16.5m-16.5 5.25h16.5"}))}const ve=l.forwardRef(Ze);function Ke({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"M9 12.75 11.25 15 15 9.75M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"}))}const Xe=l.forwardRef(Ke);function Ye({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",strokeWidth:1.5,stroke:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{strokeLinecap:"round",strokeLinejoin:"round",d:"m9.75 9.75 4.5 4.5m0-4.5-4.5 4.5M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"}))}const es=l.forwardRef(Ye),we=""+new URL("crfm-logo-Du4T1uWZ.png",import.meta.url).href,Ne=""+new URL("helm-logo-simple-DzOhNN41.png",import.meta.url).href;function ss({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M12 2.25a.75.75 0 0 1 .75.75v11.69l3.22-3.22a.75.75 0 1 1 1.06 1.06l-4.5 4.5a.75.75 0 0 1-1.06 0l-4.5-4.5a.75.75 0 1 1 1.06-1.06l3.22 3.22V3a.75.75 0 0 1 .75-.75Zm-9 13.5a.75.75 0 0 1 .75.75v2.25a1.5 1.5 0 0 0 1.5 1.5h13.5a1.5 1.5 0 0 0 1.5-1.5V16.5a.75.75 0 0 1 1.5 0v2.25a3 3 0 0 1-3 3H5.25a3 3 0 0 1-3-3V16.5a.75.75 0 0 1 .75-.75Z",clipRule:"evenodd"}))}const as=l.forwardRef(ss);function ts({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M15.75 2.25H21a.75.75 0 0 1 .75.75v5.25a.75.75 0 0 1-1.5 0V4.81L8.03 17.03a.75.75 0 0 1-1.06-1.06L19.19 3.75h-3.44a.75.75 0 0 1 0-1.5Zm-10.5 4.5a1.5 1.5 0 0 0-1.5 1.5v10.5a1.5 1.5 0 0 0 1.5 1.5h10.5a1.5 1.5 0 0 0 1.5-1.5V10.5a.75.75 0 0 1 1.5 0v8.25a3 3 0 0 1-3 3H5.25a3 3 0 0 1-3-3V8.25a3 3 0 0 1 3-3h8.25a.75.75 0 0 1 0 1.5H5.25Z",clipRule:"evenodd"}))}const ns=l.forwardRef(ts);function rs({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M15 3.75a.75.75 0 0 1 .75-.75h4.5a.75.75 0 0 1 .75.75v4.5a.75.75 0 0 1-1.5 0V5.56l-3.97 3.97a.75.75 0 1 1-1.06-1.06l3.97-3.97h-2.69a.75.75 0 0 1-.75-.75Zm-12 0A.75.75 0 0 1 3.75 3h4.5a.75.75 0 0 1 0 1.5H5.56l3.97 3.97a.75.75 0 0 1-1.06 1.06L4.5 5.56v2.69a.75.75 0 0 1-1.5 0v-4.5Zm11.47 11.78a.75.75 0 1 1 1.06-1.06l3.97 3.97v-2.69a.75.75 0 0 1 1.5 0v4.5a.75.75 0 0 1-.75.75h-4.5a.75.75 0 0 1 0-1.5h2.69l-3.97-3.97Zm-4.94-1.06a.75.75 0 0 1 0 1.06L5.56 19.5h2.69a.75.75 0 0 1 0 1.5h-4.5a.75.75 0 0 1-.75-.75v-4.5a.75.75 0 0 1 1.5 0v2.69l3.97-3.97a.75.75 0 0 1 1.06 0Z",clipRule:"evenodd"}))}const is=l.forwardRef(rs);function ls({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M12.53 16.28a.75.75 0 0 1-1.06 0l-7.5-7.5a.75.75 0 0 1 1.06-1.06L12 14.69l6.97-6.97a.75.75 0 1 1 1.06 1.06l-7.5 7.5Z",clipRule:"evenodd"}))}const ye=l.forwardRef(ls);function os({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M11.47 4.72a.75.75 0 0 1 1.06 0l3.75 3.75a.75.75 0 0 1-1.06 1.06L12 6.31 8.78 9.53a.75.75 0 0 1-1.06-1.06l3.75-3.75Zm-3.75 9.75a.75.75 0 0 1 1.06 0L12 17.69l3.22-3.22a.75.75 0 1 1 1.06 1.06l-3.75 3.75a.75.75 0 0 1-1.06 0l-3.75-3.75a.75.75 0 0 1 0-1.06Z",clipRule:"evenodd"}))}const Le=l.forwardRef(os);function cs({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 24 24",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M10.5 3.75a6.75 6.75 0 1 0 0 13.5 6.75 6.75 0 0 0 0-13.5ZM2.25 10.5a8.25 8.25 0 1 1 14.59 5.28l4.69 4.69a.75.75 0 1 1-1.06 1.06l-4.69-4.69A8.25 8.25 0 0 1 2.25 10.5Z",clipRule:"evenodd"}))}const ds=l.forwardRef(cs);function oe(s,a){return a?a==="home"?"https://crfm.stanford.edu/helm/":s?`https://crfm.stanford.edu/helm/${a}/${s}/`:`https://crfm.stanford.edu/helm/${a}/latest/`:"#"}function Me(){const[s,a]=l.useState([]),[t,n]=l.useState();return l.useEffect(()=>{if(t&&t.title&&t.title!=="All Leaderboards"){const r=t.title==="Lite"||t.title==="Classic"?"HELM "+t.title:t.title;document.title=r+" - Holistic Evaluation of Language Models (HELM)"}},[t]),l.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(r=>r.json()).then(r=>{if(a(r),window.PROJECT_ID){const o=r.find(i=>i.id===window.PROJECT_ID);n(o)}else{const o=r.find(i=>i.id==="lite");n(o)}}).catch(r=>{console.error("Error fetching JSON:",r)})},[]),t===void 0||t.title===void 0?null:e.jsxs("div",{className:"dropdown z-50",children:[e.jsxs("div",{tabIndex:0,role:"button",className:"btn normal-case bg-white font-bold p-2 border-0 text-lg block whitespace-nowrap z-40","aria-haspopup":"true","aria-controls":"menu",children:[t.title," ",e.jsx(ye,{fill:"black",color:"black",className:"text w-4 h-4 inline"})]}),e.jsx("ul",{tabIndex:0,className:"-translate-x-36 dropdown-content z-[1] menu p-1 shadow-lg bg-base-100 rounded-box w-max text-base",role:"menu",children:s.map((r,o)=>e.jsx("li",{className:"z-40",children:e.jsxs("a",{href:oe(void 0,r.id),className:"block",role:"menuitem",children:[e.jsx("strong",{className:t.title===r.title?"underline":"",children:r.title}),": ",r.description]})},o))})]})}function A(s){return s.startsWith("http://")||s.startsWith("https://")?s:`${window.BENCHMARK_OUTPUT_BASE_URL.replace(/\/$/,"")}/${s.replace(/^\//,"").split("/").map(a=>encodeURIComponent(a)).join("/")}`}function J(){return window.RELEASE?`/releases/${window.RELEASE}`:`/runs/${window.SUITE}`}async function hs(s){try{return await(await fetch(A(`${J()}/summary.json`),{signal:s})).json()}catch(a){return console.log(a),{release:void 0,suites:void 0,suite:void 0,date:""}}}function ms(){const[s,a]=l.useState({release:void 0,suites:void 0,suite:void 0,date:""}),[t,n]=l.useState();l.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(m=>m.json()).then(m=>{if(window.PROJECT_ID){const g=m.find(j=>j.id===window.PROJECT_ID);n(g)}else{const g=m.find(j=>j.id==="lite");n(g)}}).catch(m=>{console.error("Error fetching JSON:",m)})},[]),l.useEffect(()=>{const m=new AbortController;async function g(){const j=await hs(m.signal);a(j)}return g(),()=>m.abort()},[]);const r=t!==void 0&&t.releases!==void 0?t.releases:["v1.0.0"],o=s.release||s.suite||null;if(!o)return null;const i=`Release ${o} (${s.date})`;if(r.length<=1)return e.jsx("div",{children:i});const u=r.indexOf(o),h=u<0?e.jsx(F,{color:"blue",children:"preview"}):u===0?e.jsx(F,{color:"blue",children:"latest"}):e.jsx(F,{color:"yellow",children:"stale"});return e.jsxs("div",{className:"dropdown",children:[e.jsxs("div",{tabIndex:0,role:"button",className:"normal-case bg-white border-0 block whitespace-nowrap","aria-haspopup":"true","aria-controls":"menu",children:[i," ",h," ",e.jsx(ye,{fill:"black",color:"black",className:"inline text w-4 h-4"})]}),e.jsx("ul",{tabIndex:0,className:"dropdown-content z-[50] menu p-1 shadow-lg bg-base-100 rounded-box w-max text-base",role:"menu",children:["latest"].concat(r).map(m=>e.jsx("li",{children:e.jsx("a",{href:oe(m,t?t.id:"lite"),className:"block",role:"menuitem",children:m})},m))})]})}function us(){return e.jsxs("nav",{className:"navbar h-24 px-8 md:px-12 bg-base-100 max-w[1500]px",children:[e.jsx("div",{children:e.jsxs("div",{className:"dropdown md:hidden mr-4",children:[e.jsx("label",{tabIndex:0,className:"btn btn-ghost hover:bg-transparent btn-lg px-0",children:e.jsx(ve,{className:"w-16 h-16"})}),e.jsxs("ul",{tabIndex:0,className:"menu menu-lg dropdown-content mt-3 z-50 p-2 bg-base-100 shadow",children:[e.jsx("li",{children:e.jsx(b,{to:"leaderboard",children:"Leaderboard"})}),e.jsx("li",{children:e.jsx(b,{to:"models",children:"Models"})}),e.jsx("li",{children:e.jsx(b,{to:"scenarios",children:"Scenarios"})}),e.jsx("li",{children:e.jsx(b,{to:"runs",className:"whitespace-nowrap",children:"Predictions"})}),e.jsx("li",{children:e.jsx(b,{to:"https://github.com/stanford-crfm/helm",children:"GitHub"})})]})]})}),e.jsxs("div",{className:"flex-1 items-center",children:[e.jsx("a",{href:"https://crfm.stanford.edu/",className:"w-24",children:e.jsx("img",{src:we,className:"object-contain"})}),e.jsx(b,{to:"/",className:"mx-2 w-32",children:e.jsx("img",{src:Ne,className:"object-contain"})}),e.jsx(Me,{})]}),e.jsx("div",{className:"flex-none hidden md:block",children:e.jsxs("ul",{className:"flex flex-row gap-6 px-1",children:[e.jsx("li",{children:e.jsx(b,{to:"leaderboard",children:"Leaderboard"})}),e.jsx("li",{children:e.jsx(b,{to:"models",children:"Models"})}),e.jsx("li",{children:e.jsx(b,{to:"scenarios",children:"Scenarios"})}),e.jsx("li",{children:e.jsx(b,{to:"runs",children:"Predictions"})}),e.jsx("li",{children:e.jsx(b,{to:"https://github.com/stanford-crfm/helm",children:"GitHub"})}),e.jsx("li",{className:"hidden lg:flex",children:e.jsx(ms,{})})]})})]})}function xs(){return e.jsxs("nav",{className:"navbar h-24 px-8 md:px-12 bg-base-100 max-w[1500]px",children:[e.jsx("div",{children:e.jsx("div",{className:"dropdown md:hidden mr-4",children:e.jsx("label",{tabIndex:0,className:"btn btn-ghost hover:bg-transparent btn-lg px-0",children:e.jsx(ve,{className:"w-16 h-16"})})})}),e.jsxs("div",{className:"flex-1 items-center",children:[e.jsx(b,{to:"https://crfm.stanford.edu/",className:"w-24",children:e.jsx("img",{src:we,className:"object-contain"})}),e.jsx(b,{to:"/",className:"mx-2 w-32",children:e.jsx("img",{src:Ne,className:"object-contain"})}),e.jsx(Me,{})]})]})}function fs(){return e.jsxs(e.Fragment,{children:[window.PROJECT_ID==="home"?e.jsx(xs,{}):e.jsx(us,{}),e.jsx("main",{className:"p-8 pt-0",children:e.jsx("div",{className:"mx-auto max-w-[1500]px",children:e.jsx(Fe,{})})})]})}async function O(s){try{return await(await fetch(A(`${J()}/schema.json`),{signal:s})).json()}catch(a){return a instanceof Error&&a.name!=="AbortError"&&console.log(a),{adapter:[],metric_groups:[],metrics:[],models:[],perturbations:[],run_groups:[]}}}function ps({href:s,children:a}){return e.jsx("a",{href:s,className:"link link-primary link-hover",target:"_blank",rel:"noreferrer",children:a})}function U({value:s}){return e.jsx("span",{children:e.jsx(Ve,{components:{a:ps},children:s})})}function B({title:s,subtitle:a,markdown:t=!1}){return e.jsxs("header",{className:"m-4 ml-0",children:[e.jsx("h1",{className:"text-4xl",children:s}),t&&a!==void 0?e.jsx("h2",{className:"mt-2 text-neutral",children:e.jsx(U,{value:a})}):a!==void 0&&e.jsx("h2",{className:"mt-2 text-neutral",children:a})]})}const gs={open:"green",limited:"yellow",closed:"red"},js={open:"Open",limited:"Limited",closed:"Closed"};function bs({level:s}){return e.jsx(F,{color:gs[s],children:js[s]})}function $(){return e.jsx("div",{className:"w-full",children:e.jsx("div",{className:"block mx-auto my-24 loading loading-spinner loading-lg"})})}function vs(){const[s,a]=l.useState([]);l.useEffect(()=>{const i=new AbortController;async function u(){const h=await O(i.signal);a(h.models)}return u(),()=>i.abort()},[]);const[t,n,r]=s.reduce((i,u)=>{switch(u.access){case"open":i[0]+=1;break;case"limited":i[1]+=1;break;case"closed":i[2]+=1;break}return i},[0,0,0]),o=Object.values(s.reduce((i,u)=>{const h=u.creator_organization;return i[h]===void 0?(i[h]={name:h,models:1},i):(i[h].models+=1,i)},{}));return s.length===0?e.jsx($,{}):e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Models"}),e.jsxs("div",{className:"overflow-x-auto mt-12",children:[e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Creator"}),e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Description"}),e.jsx("th",{children:"Access"})]})}),e.jsx("tbody",{children:s.map(i=>e.jsxs("tr",{children:[e.jsx("td",{className:"text-lg",children:i.creator_organization}),e.jsxs("td",{children:[e.jsx("span",{className:"text-xl",children:i.display_name}),e.jsx("br",{}),e.jsx("span",{children:i.name})]}),e.jsx("td",{children:e.jsx(U,{value:i.description})}),e.jsx("td",{children:e.jsx(bs,{level:i.access})})]}))})]}),e.jsx(B,{title:"Analysis"}),e.jsxs("div",{className:"grid md:grid-cols-3 grid-cols-1 gap-8",children:[e.jsxs(z,{className:"flex flex-col justify-between",children:[e.jsx(te,{children:"Models"}),e.jsx(je,{className:"text-6xl md:!text-[96px]",children:s.length}),e.jsx($e,{values:[t,n,r],colors:["green","yellow","red"]}),e.jsx(me,{categories:["Open","Limited","Closed"],colors:["green","yellow","red"]})]}),e.jsxs(z,{className:"md:col-span-2",children:[e.jsx(te,{children:"Creator Organizations"}),e.jsxs("div",{className:"flex justify-between mt-4",children:[e.jsx(De,{data:o,category:"models",index:"name",variant:"pie",className:"basis-5/12"}),e.jsx(me,{categories:o.map(i=>i.name),className:"basis-7/12"})]})]})]})]})]})}function K({to:s,children:a,inTable:t=!1,title:n=""}){return t?e.jsx(b,{className:"link link-hover",to:s,title:n,children:a}):e.jsx(b,{className:"link link-primary link-hover",to:s,children:a})}function ws(){const[s,a]=l.useState([]),[t,n]=l.useState({});l.useEffect(()=>{const i=new AbortController;async function u(){const h=await O(i.signal);a(h.run_groups.filter(m=>!m.todo&&m.taxonomy&&!m.display_name.includes("CLEVA"))),n(Object.fromEntries(h.metrics.map(m=>[m.name,m])))}return u(),()=>i.abort()},[]);const r=i=>{var g;const u=(g=i.environment)==null?void 0:g.main_name,h=u?t[u]:void 0;if(h===void 0)return"";const m=h.display_name||h.short_display_name||h.name;return h.description?`${m} – ${h.description}`:m},o=Object.values(s.reduce((i,u)=>{var m;const h=((m=u.taxonomy)==null?void 0:m.task)||"Unknown";return i[h]===void 0?(i[h]={name:h,value:1},i):(i[h].value+=1,i)},{}));return s.length===0?e.jsx($,{}):(console.log(s),e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Scenarios",subtitle:"A scenario represents a use case and consists of a dataset of instances."}),e.jsxs("div",{className:"overflow-x-auto mt-12",children:[e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Scenario"}),e.jsx("th",{children:"Task"}),e.jsx("th",{children:"What"}),e.jsx("th",{children:"Who"}),e.jsx("th",{children:"When"}),e.jsx("th",{children:"Language"}),e.jsx("th",{children:"Description"}),e.jsx("th",{children:"Metric"})]})}),e.jsx("tbody",{children:s.map(i=>{var u,h,m,g,j;return e.jsxs("tr",{children:[e.jsxs("td",{children:[e.jsx(K,{to:`/leaderboard/${i.name}`,children:e.jsx("span",{className:"text-lg",children:i.display_name})}),e.jsx("span",{className:"block",children:i.name})]}),e.jsx("td",{children:((u=i.taxonomy)==null?void 0:u.task)||""}),e.jsx("td",{children:((h=i.taxonomy)==null?void 0:h.what)||""}),e.jsx("td",{children:((m=i.taxonomy)==null?void 0:m.who)||""}),e.jsx("td",{children:((g=i.taxonomy)==null?void 0:g.when)||""}),e.jsx("td",{children:((j=i.taxonomy)==null?void 0:j.language)||""}),e.jsx("td",{children:e.jsx(U,{value:i.short_description||i.description})}),e.jsx("td",{children:e.jsx(U,{value:r(i)})})]})})})]}),e.jsx(B,{title:"Analysis"}),e.jsxs("div",{className:"grid md:grid-cols-4 gap-8",children:[e.jsxs(z,{className:"flex flex-col",children:[e.jsx(te,{children:"Total scenarios"}),e.jsx(je,{className:"mx-auto my-6 md:mt-16 !text-[72px] md:!text-[96px]",children:s.length})]}),e.jsx(z,{className:"col-span-3",children:e.jsxs("div",{className:"grid md:grid-cols-2 gap-x-12",children:[e.jsx(ue,{data:o.slice(0,Math.floor(o.length/2))}),e.jsx(ue,{data:o.slice(Math.ceil(o.length/2))})]})})]})]})]}))}function Ns(){return A(`${J()}/groups.json`)}async function Ee(s){try{return await(await fetch(Ns(),{signal:s})).json()}catch(a){return a instanceof Error&&a.name!=="AbortError"&&console.log(a),[]}}function ce({children:s}){return e.jsx("div",{role:"navigation",className:"tabs flex-nowrap border-b-2 border-gray-2 overflow-x-auto overflow-y-hidden",children:s})}function X({active:s=!1,onClick:a=()=>{},size:t="md",children:n}){return e.jsx("div",{onClick:a,className:`whitespace-nowrap text-${t} mb-[-2px] text-md tab tab-bordered${s?" border-2 border-grey-500 rounded":" border-none"}`,children:n})}function ys({title:s,titleId:a,...t},n){return l.createElement("svg",Object.assign({xmlns:"http://www.w3.org/2000/svg",viewBox:"0 0 20 20",fill:"currentColor","aria-hidden":"true","data-slot":"icon",ref:n,"aria-labelledby":a},t),s?l.createElement("title",{id:a},s):null,l.createElement("path",{fillRule:"evenodd",d:"M4.25 5.5a.75.75 0 0 0-.75.75v8.5c0 .414.336.75.75.75h8.5a.75.75 0 0 0 .75-.75v-4a.75.75 0 0 1 1.5 0v4A2.25 2.25 0 0 1 12.75 17h-8.5A2.25 2.25 0 0 1 2 14.75v-8.5A2.25 2.25 0 0 1 4.25 4h5a.75.75 0 0 1 0 1.5h-5Z",clipRule:"evenodd"}),l.createElement("path",{fillRule:"evenodd",d:"M6.194 12.753a.75.75 0 0 0 1.06.053L16.5 4.44v2.81a.75.75 0 0 0 1.5 0v-4.5a.75.75 0 0 0-.75-.75h-4.5a.75.75 0 0 0 0 1.5h2.553l-9.056 8.194a.75.75 0 0 0-.053 1.06Z",clipRule:"evenodd"}))}const fe=l.forwardRef(ys);function q(s){return Number.isNaN(Number(s))?String(s):String(Math.round(Number(s)*1e3)/1e3)}function Ls(s){return s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}function Y({value:s,title:a,hideIcon:t}){if(typeof s.value=="string"&&s.value.includes("⚠")&&(s.value=s.value.replace("⚠","")),s.value===void 0)return"-";if(s.run_spec_names){const n=(()=>{if(s.run_spec_names.length==1)return"/runs/"+s.run_spec_names[0];if(s.run_spec_names.length>1){const r="/runs/?q="+s.run_spec_names.map(i=>`^${Ls(i)}$`).join("|");return encodeURI(r)}})();return n?e.jsx(K,{to:n,inTable:!0,title:a,children:e.jsxs("div",{className:"flex items-center ",children:[q(s.value),!t&&e.jsx(fe,{className:"w-3 h-3 ml-1",stroke:"#cbcbcb",fill:"#cbcbcb"})]})}):a?e.jsx("a",{title:a,children:q(s.value)}):e.jsx(e.Fragment,{children:q(s.value)})}return s.href?e.jsx(K,{to:s.href,inTable:!0,title:a,children:e.jsxs("div",{className:"flex items-center",children:[q(s.value),!t&&e.jsx(fe,{className:"w-3 h-3 ml-1",stroke:"#cbcbcb",fill:"#cbcbcb"})]})}):s.markdown?e.jsx(U,{value:String(s.value)}):a?e.jsx("a",{title:a,children:q(s.value)}):e.jsx(e.Fragment,{children:q(s.value)})}function de({schema:s,groupTable:a,numRowsToDisplay:t,sortColumnIndex:n=1,sortable:r=!0,displayColumnIndexes:o=void 0,miniStyle:i=!1}){const[u,h]=l.useState(1),[m,g]=l.useState(Math.min(a.header.length-1,n));function j(c){return c.length>30?c.substring(0,27)+"...":c}const y=c=>{const x=["AIRBench 2024 -","-book"];if(c.value==="Model/adapter")return"Model";if(x.some(d=>c.value.includes(d))){let d=c.value;return x.forEach(v=>{d=d.replace(v,"")}),j(d)}else return j(c.value)},w=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.description;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},S=c=>{h(c===m?u*-1:c===0?-1:1),g(c)},p=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.name;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},R=()=>{const c=a.header[m].lower_is_better,x=u*(c?1:-1),d=a.rows.slice();return d.sort((v,k)=>{var M,C;const N=(M=v[m])==null?void 0:M.value,L=(C=k[m])==null?void 0:C.value;return N!==void 0&&L===void 0?-1:L!==void 0&&N===void 0?1:typeof N=="number"&&typeof L=="number"?(N-L)*x:typeof N=="string"&&typeof L=="string"?x===1?N.localeCompare(L):L.localeCompare(N):0}),t>0?d.slice(0,t):d};function f(c){const x=c.lastIndexOf(" - ");return x===-1?c:c.substring(0,x)+"*"+c.substring(x+1)}const _=c=>{const d=f(c).split("*")[0].trim();if(s){const v=s.run_groups.find(k=>k.display_name===d||k.short_display_name===d);if(v)return v.name}return""};return e.jsxs("table",{className:i?"table w-full":"rounded-lg shadow-md table",children:[e.jsx("thead",{children:e.jsx("tr",{children:a.header.filter((c,x)=>o===void 0||o.includes(x)).map((c,x)=>e.jsx("th",{className:`${x===m?"bg-gray-100":"bg-white"} ${x===0?"left-0 z-40":""} ${c.description?"underline decoration-dashed decoration-gray-300 ":""} whitespace-nowrap px-4 sticky top-0`,title:c.description?c.description:"",children:e.jsxs("div",{className:i?"flex gap-2 items-center":"z-20 flex justify-between items-center min-w-48 w-48 max-w-48 text-wrap",children:[e.jsx("span",{className:"inline-block w-full break-words",children:y(c)}),r?e.jsx("button",{className:"link",onClick:()=>S(x),children:e.jsx(Le,{className:"w-6 h-6"})}):null]})},`$${x}`))})}),e.jsx("tbody",{children:R().map((c,x)=>e.jsx("tr",{children:c.filter((d,v)=>o===void 0||o.includes(v)).map((d,v)=>e.jsx("td",{className:`${v===0?"z-20 text-lg sticky left-0":"z-0"} ${x%2===0?"bg-gray-50":"bg-white"}`,children:v==1?e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""}`,children:e.jsx(Y,{value:{...d,href:"/runs/?q="+p(String(c[0].value))},title:`Click value to see all predictions for: ${p(String(c[0].value))}`})}):e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""} ${v===0?"underline decoration-dashed decoration-gray-300 z-10":"z-0"}`,children:e.jsx(Y,{value:{...d},title:String(c[0].value)===d.value?w(String(c[0].value)):`Click value to see predictions for ${String(c[0].value)} for ${_(y(a.header[v]))}: ${p(String(c[0].value))}`})})},`${v}`))},`$${c[0].value}`))})]})}function Ms(){const[s,a]=l.useState(0),[t,n]=l.useState(),[r,o]=l.useState();return l.useEffect(()=>{const i=new AbortController;async function u(){const h=O(i.signal),m=Ee(i.signal),g=await h;o(g);const j=await m;n(j)}return u(),()=>i.abort()},[]),t===void 0||r===void 0?e.jsx($,{}):t.length===0?e.jsxs("div",{children:[e.jsx(B,{title:"Results",subtitle:"Groupings of the processes, methods, and metrics involved in evaluating models, particularly in the context of natural language understanding and question answering.",className:"mb-16"}),e.jsx("div",{children:"No groups found."})]}):e.jsxs("div",{children:[e.jsx(B,{title:"Results",subtitle:"Groupings of the processes, methods, and metrics involved in evaluating models, particularly in the context of natural language understanding and question answering.",className:"mb-16"}),e.jsxs("div",{children:[t.length>1?e.jsx(ce,{children:t.map((i,u)=>e.jsx(X,{active:u===s,onClick:()=>a(u),children:i.title},u))}):null,e.jsx(de,{schema:r,groupTable:t[s],numRowsToDisplay:-1,sortColumnIndex:1,sortable:!0},`${s}`)]})]})}async function Es(s){try{return await(await fetch(A(`${J()}/run_specs.json`),{signal:s})).json()}catch(a){return a instanceof Error&&a.name!=="AbortError"&&console.log(a),[]}}function he({currentPage:s,totalPages:a,onNextPage:t,onPrevPage:n,className:r}){let o="join";return r!==void 0&&(o=`join ${r}`),e.jsxs("div",{className:o,children:[e.jsx("button",{onClick:n,className:"join-item btn",children:"«"}),e.jsxs("button",{className:"join-item btn",children:["Page ",s," of ",a]}),e.jsx("button",{onClick:t,className:"join-item btn",children:"»"})]})}const se=100;function Ss(){const[s,a]=le(),[t,n]=l.useState(),[r,o]=l.useState(Number(s.get("page")||1)),[i,u]=l.useState(!0),[h,m]=l.useState(s.get("q")||"");l.useEffect(()=>{const p=new AbortController;async function R(){const f=await Es(p.signal);n(f)}return R(),()=>p.abort()},[]);const g=p=>{p.preventDefault();const f=p.target.q.value;m(f),a({q:f,page:"1"})};if(t===void 0)return e.jsx($,{});let j=null;if(i)try{j=new RegExp(h)}catch{j=null}const y=t.filter(p=>j?j.test(p.name):p.name.includes(h)),w=y.slice((r-1)*se,r*se),S=Math.ceil(y.length/se);return e.jsxs(e.Fragment,{children:[e.jsx(B,{title:"Predictions",subtitle:"All benchmark predictions"}),e.jsxs("form",{className:"flex mb-8",onSubmit:g,children:[e.jsxs("div",{className:"form-control",children:[e.jsx("input",{type:"text",name:"q",placeholder:"Search",className:"input input-bordered",value:h,onChange:p=>m(p.target.value)}),e.jsxs("label",{className:"label",children:[e.jsxs("span",{className:"label-text-alt flex item-center",children:[e.jsx("input",{type:"checkbox",className:"toggle toggle-xs",checked:i,onChange:()=>u(!i)}),e.jsx("span",{className:"ml-2",children:"Regex"})]}),e.jsx("span",{className:"label-text-alt",children:`${y.length} results`})]})]}),e.jsx("div",{className:"form-control ml-4",children:e.jsx("button",{className:"btn",children:e.jsx(ds,{className:"w-6 h-6"})})})]}),e.jsx("div",{className:"overflow-x-auto",children:e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Run"}),e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Groups"}),e.jsx("th",{children:"Adapter method"}),e.jsx("th",{children:"Subject / Task"})]})}),e.jsx("tbody",{children:w.map((p,R)=>e.jsxs("tr",{children:[e.jsx("td",{children:e.jsx(K,{to:`/runs/${p.name}`,children:p.name})}),e.jsx("td",{children:p.adapter_spec.model}),e.jsx("td",{children:p.groups.join(", ")}),e.jsx("td",{children:p.adapter_spec.method}),e.jsx("td",{children:p.scenario_spec.args.subject||p.scenario_spec.args.task||"-"})]},`${p.name}-${R}`))})]})}),S>0?e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const p=Math.min(r+1,S);o(p),s.set("page",String(p)),a(s)},onPrevPage:()=>{const p=Math.max(r-1,1);o(p),s.set("page",String(p)),a(s)},currentPage:r,totalPages:S}):e.jsx("div",{className:"my-8 text-center",children:"No results"})]})}function T(){return window.SUITE!==void 0?window.SUITE:void 0}async function ks(s,a,t){try{return await(await fetch(A(`/runs/${t||T()}/${s}/scenario.json`),{signal:a})).json()}catch(n){n instanceof Error&&n.name!=="AbortError"&&console.log(n);return}}function Se(s,a){return A(`/runs/${a||T()}/${s}/run_spec.json`)}async function As(s,a,t){try{return await(await fetch(Se(s,t),{signal:a})).json()}catch(n){n instanceof Error&&n.name!=="AbortError"&&console.log(n);return}}function Rs(s,a){return A(`/runs/${a||T()}/${s}/per_instance_stats.json`)}function _s(s,a){return A(`/runs/${a||T()}/${s}/scenario_state.json`)}function ke(){return window.RELEASE!==void 0?window.RELEASE:void 0}async function Cs(s){try{return await(await fetch(A(`/releases/${ke()}/runs_to_run_suites.json`),{signal:s})).json()}catch(a){return a instanceof Error&&a.name!=="AbortError"&&console.log(a),{}}}function Ts(s,a){return ke()?s[a]:window.SUITE}function Ps(s){const t={quasi_exact_match:!1,toxic_frac:!0,safety_score:!1,exact_match:!1},n=Object.keys(s);for(const r of n)if(s[r]!==void 0&&t[r]!==void 0)return t[r]?s[r]<.5?[r,!0]:[r,!1]:s[r]>=.5?[r,!0]:[r,!1];return["",!1]}function Is(s){const[a,t]=Ps(s.stats);return a===""?null:t?e.jsx(Hs,{value:`${a.replace(/_/g," ")}: ${s.stats[a]}`}):e.jsx($s,{value:`${a.replace(/_/g," ")}: ${s.stats[a]}`})}function Hs({value:s}){return e.jsx(F,{icon:Xe,color:"green",children:s})}function $s({value:s}){return e.jsx(F,{icon:es,color:"red",children:s})}function H({value:s}){const[a,t]=l.useState(!1),[n,r]=l.useState(!1);return e.jsxs(e.Fragment,{children:[e.jsxs("div",{onMouseOver:()=>t(!0),onMouseOut:()=>t(!1),className:"relative",children:[e.jsx("div",{className:"bg-base-200 p-2 block overflow-auto w-full max-h-[36rem] mb-2 whitespace-pre-wrap localize-text-direction",children:s}),a?e.jsx("button",{className:"bg-white absolute p-2 leading-none height-fit min-h-none right-1 bottom-1 shadow",onClick:()=>r(!0),children:e.jsx(is,{fill:"black",color:"black",className:"text w-4 h-4"})}):null]}),e.jsx("dialog",{open:n,className:"modal p-16 bg-opacity-80 bg-white",onClick:()=>r(!1),children:e.jsx("div",{className:"modal-box max-w-none p-4 whitespace-pre-wrap bg-base-200 localize-text-direction",children:s})})]})}function Ae({messages:s}){return e.jsx("div",{children:s.map((a,t)=>e.jsxs("div",{children:[e.jsx("div",{children:a.role}),e.jsx(H,{value:a.content})]},t))})}function Re({mediaObject:s}){if(s.content_type.includes("image")){if(s.location===void 0)return null;const a=A(s.location.replace("benchmark_output/","").replace("prod_env/","../"));return e.jsxs("div",{children:[e.jsx("img",{src:a}),e.jsx("br",{})]})}else if(s.content_type.includes("audio")){if(s.location===void 0)return null;const a=A(s.location.replace(/^.*benchmark_output\//,"").replace("prod_env/","../"));return e.jsx("div",{children:e.jsx("audio",{controls:!0,src:a})})}else if(s.content_type.includes("video")){if(s.location===void 0)return null;const a=A(s.location.replace(/^.*benchmark_output\//,"").replace("prod_env/","../"));return e.jsxs("div",{children:[e.jsx("video",{controls:!0,style:{width:"720px"},children:e.jsx("source",{src:a,type:s.content_type})}),e.jsx("br",{})]})}else return s.text&&s.content_type&&s.content_type==="text/plain"&&s.text.length>1?e.jsxs("div",{children:[s.text,e.jsx("br",{}),e.jsx("br",{})]}):e.jsx("div",{})}function _e({multimediaObject:s}){return e.jsx("div",{children:s.media_objects.map(a=>e.jsx(Re,{mediaObject:a}))})}function Ds(s){return Array.isArray(s)?s.length==0?"[]":`[${s.map(a=>String(a).replace(/\n/,"\\n")).join(", ")}]`:String(s)}function Bs({request:s}){return e.jsxs("div",{children:[s.request.prompt.length>0?e.jsxs("div",{children:[e.jsxs("h3",{className:"block text text-gray-400",children:["Prompt (",s.request.prompt.length," Chars)"]}),e.jsx(H,{value:s.request.prompt})]}):s.request.multimodal_prompt?e.jsxs("div",{children:[e.jsx("h3",{className:"block text text-gray-400",children:"Prompt"}),e.jsx(_e,{multimediaObject:s.request.multimodal_prompt})]}):s.request.messages&&s.request.messages.length?e.jsxs("div",{children:[e.jsx("h3",{className:"block text text-gray-400",children:"Prompt"}),e.jsx(Ae,{messages:s.request.messages})]}):e.jsx("h3",{className:"block text text-gray-400",children:"Empty Prompt"}),e.jsx(re,{children:Object.keys(s.request).filter(a=>a!=="prompt").map((a,t)=>e.jsxs(ie,{children:[e.jsxs("span",{children:[a,":"]}),s.request&&s.request[a]?e.jsx("span",{children:Ds(s.request[a])}):"null"]},t+1))})]})}function Os(s){return e.jsx("div",{children:s.map((a,t)=>e.jsxs("div",{children:[a.error&&e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:"Error"}),e.jsx(H,{value:a.error})," "]}),a.text&&e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:"Text"}),e.jsx(H,{value:a.text})," "]}),a.media_object&&e.jsx(Re,{mediaObject:a.media_object})]},t))})}function ne(s,a){return Array.isArray(s)?s.flatMap((t,n)=>ne(t,`${a||""}[${n}]`)):s instanceof Object&&s.constructor===Object?Object.entries(s).flatMap(([t,n])=>ne(n,a?`${a}.${t}`:t)):[[a||"",typeof s=="string"?s:JSON.stringify(s)]]}function Fs(s){return e.jsx("div",{children:ne(s).map(([a,t])=>e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:a}),e.jsx(H,{value:t})]},a))})}function Us({predictionAnnotations:s}){return e.jsx("div",{children:s&&s!==void 0?Object.entries(s).map(([a,t])=>e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white my-2",children:[e.jsx("summary",{className:"collapse-title",children:e.jsx(e.Fragment,{children:"View "+a+" annotations"})}),e.jsx("div",{className:"collapse-content",children:Array.isArray(t)?Os(t):Fs(t)})]},a)):null})}function qs({predictions:s,requests:a,metricFieldMap:t}){return s.length<1?null:e.jsx("div",{children:e.jsx("div",{className:"flex flex-wrap justify-start items-start",children:s.map((n,r)=>e.jsxs("div",{className:"w-full",children:[s.length>1?e.jsxs("h2",{children:["Trial ",n.train_trial_index]}):null,e.jsxs("div",{className:"mt-2 w-full",children:[n.thinking_text?e.jsxs(e.Fragment,{children:[e.jsx("h3",{children:e.jsx("span",{className:"mr-4",children:"Thinking"})}),e.jsx(H,{value:n.thinking_text})]}):null,n.base64_images&&n.base64_images.length>0?e.jsxs(e.Fragment,{children:[e.jsx("h3",{className:"mr-4",children:"Prediction image"}),n.base64_images.map(o=>e.jsx("img",{src:"data:image;base64,"+o,alt:"Base64 Image"}))]}):e.jsxs(e.Fragment,{children:[e.jsxs("h3",{children:[e.jsx("span",{className:"mr-4",children:"Prediction raw text"}),e.jsx(Is,{stats:n.stats})]}),e.jsx(H,{value:n.predicted_text}),n.mapped_output?e.jsxs(e.Fragment,{children:[e.jsx("h3",{children:"Prediction mapped output"}),e.jsx(H,{value:String(n.mapped_output)})]}):null]})]}),e.jsx(Us,{predictionAnnotations:n.annotations}),e.jsxs("div",{className:"mx-1",children:[e.jsx("h3",{children:"Metrics"}),e.jsx(re,{children:Object.keys(n.stats).map((o,i)=>e.jsxs(ie,{children:[t[o]?e.jsx("span",{title:t[o].description,children:t[o].display_name}):e.jsx("span",{children:o}),e.jsx("span",{children:String(n.stats[o])})]},i))})]}),e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white",children:[e.jsx("summary",{className:"collapse-title",children:"Request details"}),e.jsx("div",{className:"collapse-content",children:e.jsx(Bs,{request:a[r]})})]})]},r))})})}const Ws="correct";function zs({references:s}){return e.jsxs("span",{children:[e.jsx("h3",{children:"References"}),e.jsx("ul",{children:s.map((a,t)=>e.jsxs("li",{className:"bg-base-200 p-2 block overflow-auto w-full max-h-72 mb-2 whitespace-pre-wrap localize-text-direction",children:[a.output.text,a.tags.map(n=>e.jsx(F,{className:"mx-2",color:n===Ws?"green":void 0,children:n}))]},t))})]})}function Ce(s){return e.jsx(H,{value:s===null?"null":typeof s=="object"?JSON.stringify(s):s.toString()})}function Vs(s){return e.jsx("div",{children:s.map(a=>Ce(a))})}function Js({extraData:s}){return e.jsxs("details",{className:"collapse collapse-arrow border rounded-md bg-white my-2",children:[e.jsx("summary",{className:"collapse-title",children:"View instance extra data"}),e.jsx("div",{className:"collapse-content",children:Object.entries(s).map(([a,t])=>e.jsxs("div",{children:[e.jsx("h3",{className:"ml-1",children:a}),Array.isArray(t)?Vs(t):Ce(t)]}))})]})}function Gs({instance:s,requests:a,predictions:t,metricFieldMap:n}){return e.jsxs("div",{children:[e.jsx("h3",{children:"Input"}),s.input.multimedia_content!==void 0?e.jsx(_e,{multimediaObject:s.input.multimedia_content}):s.input.text.includes('
0?e.jsx(zs,{references:s.references}):null}),s.extra_data&&s.extra_data.length?e.jsx(Js,{extraData:s.extra_data}):null,e.jsx("div",{children:t&&a?e.jsx(qs,{predictions:t,requests:a,metricFieldMap:n}):null})]})}async function Qs(s,a,t,n){const r=m=>Uint8Array.from(atob(m),g=>g.charCodeAt(0)),o=await window.crypto.subtle.importKey("raw",r(a),"AES-GCM",!0,["decrypt"]),i=new Uint8Array([...r(s),...r(n)]),u=r(t),h=await window.crypto.subtle.decrypt({name:"AES-GCM",iv:u},o,i);return new TextDecoder().decode(h)}async function V(s,a){if(!s.includes("encrypted_text"))return s;const t=a[s];return t===void 0?(console.error(`Could not find ${s} in encryption data`),s):await Qs(t.ciphertext,t.key,t.iv,t.tag)}function ee(s){return s.includes("gpqa")||s.includes("ewok")}async function Zs(s,a,t,n){try{const o=await(await fetch(A(`/runs/${t||T()}/${s}/instances.json`),{signal:a})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${t||T()}/${s}/encryption_data.json`),{signal:a})).json();for(const h of o){h.input.text=await V(h.input.text,u);for(const m of h.references)m.output.text=await V(m.output.text,u)}}return o}catch(r){return r instanceof Error&&r.name!=="AbortError"&&console.log(r),[]}}async function Ks(s,a,t,n){try{const o=await(await fetch(A(`/runs/${t||T()}/${s}/display_predictions.json`),{signal:a})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${t||T()}/${s}/encryption_data.json`),{signal:a})).json();for(const h of o)h.predicted_text=await V(h.predicted_text,u),h.thinking_text!==void 0&&(h.thinking_text=await V(h.thinking_text,u))}return o}catch(r){return r instanceof Error&&r.name==="AbortError"&&console.log(r),[]}}async function Xs(s,a,t,n){try{const o=await(await fetch(A(`/runs/${t||T()}/${s}/display_requests.json`),{signal:a})).json();if(ee(s)&&n){const u=await(await fetch(A(`/runs/${t||T()}/${s}/encryption_data.json`),{signal:a})).json();for(const h of o)h.request.prompt=await V(h.request.prompt,u)}return o}catch(r){return r instanceof Error&&r.name!=="AbortError"&&console.log(r),[]}}const Q=10;function Ys({runName:s,suite:a,metricFieldMap:t,userAgreed:n}){const[r,o]=le(),[i,u]=l.useState([]),[h,m]=l.useState(),[g,j]=l.useState(),[y,w]=l.useState(1);l.useEffect(()=>{const f=new AbortController;async function _(){const c=f.signal,[x,d,v]=await Promise.all([Zs(s,c,a,n),Ks(s,c,a,n),Xs(s,c,a,n)]);u(x);const k={};v.forEach(L=>{var P;const M=L.instance_id,C=((P=L.perturbation)==null?void 0:P.name)||"";k[M]===void 0&&(k[M]={}),k[M][C]===void 0&&(k[M][C]=[]),k[M][C].push(L)}),j(k);const N={};d.forEach(L=>{var P;const M=L.instance_id,C=((P=L.perturbation)==null?void 0:P.name)||"";N[M]===void 0&&(N[M]={}),N[M][C]===void 0&&(N[M][C]=[]),N[M][C].push(L)}),m(N)}return _(),()=>f.abort()},[s,a,n]);const S=i.slice((y-1)*Q,(y-1)*Q+Q),p=Math.ceil(i.length/Q);l.useEffect(()=>{const f=r.get("instance");if(f&&!window.helmHasScrolledToInstance&&S.length>0){if(S.findIndex(c=>c.id===f)===-1)return;requestAnimationFrame(()=>{const c=document.getElementById(`instance-${f}`);c&&c.scrollIntoView({behavior:"smooth"})}),window.helmHasScrolledToInstance=!0}},[r,y,o,S]);const R=f=>f.perturbation===void 0?`Instance id: ${f.id} [split: ${f.split}]`:`Instance id: ${f.id} [split: ${f.split}][perturbation: ${f.perturbation.name}]`;return h===void 0||g===void 0?e.jsx($,{}):e.jsxs(e.Fragment,{children:[e.jsx("div",{className:"grid gap-8",children:S.map((f,_)=>{var c,x;return e.jsxs("div",{id:"instance-"+f.id,className:"border p-4",children:[e.jsxs("div",{className:"flex items-center justify-between",children:[e.jsx("h3",{className:"text-xl mb-4",children:R(f)}),e.jsx("button",{className:"btn btn-sm normal-case px-2 py-1",onClick:()=>{const d=window.location.href+(window.location.href.includes("?")?"&instance=":"?instance=")+f.id;navigator.clipboard.writeText(d)},children:"Copy Link"})]}),e.jsx(Gs,{instance:f,requests:g[f.id][((c=f.perturbation)==null?void 0:c.name)||""],predictions:h[f.id][((x=f.perturbation)==null?void 0:x.name)||""],metricFieldMap:t},`${f.id}-${_}`)]})})}),e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const f=Math.min(y+1,p);w(f),r.set("instancesPage",String(f)),o(r)},onPrevPage:()=>{const f=Math.max(y-1,1);w(f),r.set("instancesPage",String(f)),o(r)},currentPage:y,totalPages:p})]})}async function ea(s,a,t){try{return await(await fetch(A(`/runs/${t||T()}/${s}/stats.json`),{signal:a})).json()}catch(n){return n instanceof Error&&n.name!=="AbortError"&&console.log(n),[]}}function sa({stat:s,metricFieldMap:a}){const t=`${s.name.split!==void 0?` on ${s.name.split}`:""}${s.name.sub_split!==void 0?`/${s.name.sub_split}`:""}${s.name.perturbation!==void 0?` with ${s.name.perturbation.name}`:" original"}`;return a[s.name.name]?e.jsxs("span",{title:a[s.name.name].description,children:[e.jsx("strong",{children:a[s.name.name].display_name||s.name.name}),t]}):e.jsxs("span",{children:[e.jsx("strong",{children:s.name.name}),t]})}const Z=50,pe=["name","mean","min","max","sum","sum_squared","variance","stddev"];function aa({runName:s,suite:a,metricFieldMap:t}){const[n,r]=le(),[o,i]=l.useState(),[u,h]=l.useState(1),[m,g]=l.useState("");if(l.useEffect(()=>{const w=new AbortController;async function S(){const p=w.signal,R=await ea(s,p,a);i(R)}return S(),()=>w.abort()},[s,a]),o===void 0||o.length===0)return e.jsx($,{});const j=Math.ceil(o.length/Z),y=o.slice((u-1)*Z,(u-1)*Z+Z);return e.jsxs("div",{children:[e.jsx("div",{className:"flex justify-start my-4",children:e.jsx("input",{type:"text",className:"input input-bordered w-full max-w-xs",placeholder:"Search for a metric",onChange:w=>g(w.target.value)})}),e.jsx("div",{className:"overflow-x-auto",children:e.jsxs("table",{className:"table",children:[e.jsx("thead",{children:e.jsx("tr",{children:pe.map(w=>e.jsx("th",{children:w},w))})}),e.jsx("tbody",{children:y.filter(w=>!m||w.name.name.toLowerCase().includes(m.toLowerCase())).map(w=>e.jsx("tr",{children:pe.map(S=>{const p=w[S];return typeof p=="number"?e.jsx("td",{children:p}):e.jsx("td",{children:e.jsx(sa,{stat:w,metricFieldMap:t})},S)})}))})]})}),e.jsx(he,{className:"flex justify-center my-8",onNextPage:()=>{const w=Math.min(u+1,j);h(w),n.set("metricsPage",String(w)),r(n)},onPrevPage:()=>{const w=Math.max(u-1,1);h(w),n.set("metricsPage",String(w)),r(n)},currentPage:u,totalPages:j})]})}function ta({runName:s,onAgree:a}){const t=l.useRef(null),n=()=>{t.current!==null&&t.current.value.trim()==="Yes, I agree"?a():alert("Please type 'Yes, I agree' exactly.")},r=s.includes("gpqa")?e.jsx(na,{}):s.includes("ewok")?e.jsx(ra,{}):null;return e.jsxs("div",{className:"mb-8",children:[r,e.jsxs("p",{className:"mb-4",children:["If you agree to this condition, please type"," ",e.jsx("strong",{children:'"Yes, I agree"'})," in the box below and then click"," ",e.jsx("strong",{children:"Decrypt"}),"."]}),e.jsxs("div",{className:"flex gap-2 mt-2",children:[e.jsx("input",{type:"text",ref:t,className:"input input-bordered",placeholder:'Type "Yes, I agree"'}),e.jsx("button",{onClick:n,className:"btn btn-primary",children:"Decrypt"})]}),e.jsx("hr",{className:"my-4"})]})}function na(){return e.jsxs("div",{children:[e.jsx("p",{className:"mb-4",children:"The GPQA dataset instances are encrypted by default to comply with the following request:"}),e.jsx("blockquote",{className:"italic border-l-4 border-gray-300 pl-4 text-gray-700 mb-4",children:"“We ask that you do not reveal examples from this dataset in plain text or images online, to minimize the risk of these instances being included in foundation model training corpora.”"})]})}function ra(){return e.jsxs("div",{children:[e.jsx("p",{className:"mb-4",children:"The EWoK dataset instances are encrypted by default to comply with the following request:"}),e.jsx("blockquote",{className:"italic border-l-4 border-gray-300 pl-4 text-gray-700 mb-4",children:"“PLEASE DO NOT distribute any of the EWoK materials or derivatives publicly in plain-text! Any materials should appear in password-protected ZIP files or behind gated authentication mechanisms such as Huggingface datasets.”"})]})}function ia(){var d;const{runName:s}=be(),[a,t]=l.useState(0),[n,r]=l.useState(),[o,i]=l.useState(),[u,h]=l.useState(),[m,g]=l.useState(),[j,y]=l.useState(),[w,S]=l.useState({}),[p,R]=l.useState({}),[f,_]=l.useState(!1);if(l.useEffect(()=>{const v=new AbortController;async function k(){const N=v.signal;if(s===void 0)return()=>v.abort();const L=window.SUITE?window.SUITE:Ts(await Cs(N),s);i(L);const[M,C,P]=await Promise.all([As(s,N,L),ks(s,N,L),O(N)]);r(M),g(C),R(P.metrics.reduce((D,W)=>(D[W.name]=W,D),{})),S(P.adapter.reduce((D,W)=>(D[W.name]=W,D),{})),y(P.run_groups.find(D=>M==null?void 0:M.groups.includes(D.name))),h(P.models.find(D=>D.name===(M==null?void 0:M.adapter_spec.model)))}return k(),()=>v.abort()},[s]),n===void 0||m===void 0||s===void 0||o===void 0||p===void 0)return e.jsx($,{});const c=(d=j==null?void 0:j.taxonomy)==null?void 0:d.language,x=c?"scenario-language-"+c.toLowerCase():"";return e.jsxs("div",{className:x,children:[e.jsx("div",{className:"flex justify-between gap-8 mb-12",children:e.jsxs("div",{children:[e.jsxs("h1",{className:"text-3xl flex items-center",children:[(j==null?void 0:j.display_name)||m.name,j?e.jsx("a",{href:"/#/groups/"+j.name,children:e.jsx(ns,{className:"w-6 h-6 ml-2"})}):null]}),e.jsx("h3",{className:"text-xl",children:e.jsx(U,{value:(j==null?void 0:j.description)||m.description})}),e.jsx("h1",{className:"text-3xl mt-2",children:(u==null?void 0:u.display_name)||n.adapter_spec.model}),e.jsx("h3",{className:"text-xl",children:e.jsx(U,{value:(u==null?void 0:u.description)||""})}),e.jsx("div",{className:"mt-2 flex gap-2",children:m.tags.map(v=>e.jsx(F,{size:"xs",color:"gray",children:e.jsx("span",{className:"text text-md",children:v})}))})]})}),e.jsxs(z,{children:[e.jsxs("div",{className:"flex justify-between",children:[e.jsx("h3",{className:"text-lg mb-1",children:"Adapter Specification"}),e.jsxs("div",{className:"flex gap-2",children:[e.jsx(as,{className:"w-6 h-6 mr-1 text text-primary"}),e.jsx("a",{className:"link link-primary link-hover",href:Se(n.name,o),download:"true",target:"_blank",children:"Spec JSON"}),e.jsx("a",{className:"link link-primary link-hover",href:_s(n.name,o),download:"true",target:"_blank",children:"Full JSON"}),e.jsx("a",{className:"link link-primary link-hover",href:Rs(n.name,o),download:"true",target:"_blank",children:"Per-Instance Stats JSON"})]})]}),e.jsx("div",{children:e.jsx(re,{className:"grid md:grid-cols-2 lg:grid-cols-3 gap-x-8",children:Object.entries(n.adapter_spec).map(([v,k],N)=>e.jsxs(ie,{className:N<3?"!border-0":"",children:[e.jsx("strong",{className:"mr-1",title:w[v]?w[v].description:void 0,children:`${v}: `}),e.jsx("span",{className:"overflow-x-auto pre-wrap",children:k})]}))})})]}),e.jsx("div",{className:"mt-16 mb-8",children:e.jsxs(ce,{children:[e.jsx(X,{size:"lg",active:a===0,onClick:()=>t(0),children:"Instances + Predictions"}),e.jsx(X,{size:"lg",active:a===1,onClick:()=>t(1),children:"All metrics"})]})}),a===0&&ee(s)&&!f&&e.jsx(ta,{runName:s,onAgree:()=>_(!0)}),a===0?e.jsx(Ys,{runName:s,suite:o,metricFieldMap:p,userAgreed:f},f?"instances-agreed":"instances-not-agreed"):e.jsx(aa,{runName:s,suite:o,metricFieldMap:p})]})}function la({schema:s,groupTable:a,numRowsToDisplay:t,sortColumnIndex:n=1,sortable:r=!0,miniStyle:o=!1}){const[i,u]=l.useState(1),[h,m]=l.useState(Math.min(a.header.length-1,n)),g=c=>c.value,j=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.description;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},y=c=>{u(c===h?i*-1:c===0?-1:1),m(c)},w=c=>{if(s){const x=s.models.find(d=>d.display_name===c);if(x){let d=x.name;return d.includes("/")&&(d=d.replace("/","_")),d}}return""},S=()=>{const c=a.header[h].lower_is_better,x=i*(c?1:-1),d=a.rows.slice();return d.sort((v,k)=>{var M,C;const N=(M=v[h])==null?void 0:M.value,L=(C=k[h])==null?void 0:C.value;return N!==void 0&&L===void 0?-1:L!==void 0&&N===void 0?1:typeof N=="number"&&typeof L=="number"?(N-L)*x:typeof N=="string"&&typeof L=="string"?x===1?N.localeCompare(L):L.localeCompare(N):0}),t>0?d.slice(0,t):d};function p(c){const x=c.lastIndexOf(" - ");return x===-1?c:c.substring(0,x)+"*"+c.substring(x+1)}const R=c=>{const d=p(c).split("*")[0].trim();if(s){const v=s.run_groups.find(k=>k.display_name===d||k.short_display_name===d);if(v)return v.name}return""},f=[];f.push(a.header.map((c,x)=>e.jsx("td",{className:`${x===h?"bg-gray-100":x%2===0?"bg-gray-50":"bg-white"} ${x===0?"top-0 z-20":"z-10"} ${c.description?"underline decoration-dashed decoration-gray-300":""} sticky left-0 justify-between items-center w-48`,title:c.description?c.description:"",children:e.jsxs("div",{className:o?"flex gap-2":"z-10 flex w-full",children:[e.jsx("span",{className:"inline-block w-full break-words",children:g(c)}),r?e.jsx("button",{className:"link",onClick:()=>y(x),children:e.jsx(Le,{className:"w-6 h-6"})}):null]})},`scenario-${x}`))),S().forEach((c,x)=>f.push(c.map((d,v)=>e.jsx("td",{className:`${v%2===0?"bg-gray-50":"bg-white"} ${v===0?"px-4 sticky top-0":""} w-32`,children:v==1?e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""}`,children:e.jsx(Y,{value:{...d,href:"/runs/?q="+w(String(c[0].value))},title:`Click value to see all predictions for: ${w(String(c[0].value))}`})}):e.jsx("div",{className:`${d&&d.style&&d.style["font-weight"]&&d.style["font-weight"]==="bold"?"font-bold":""} ${v===0?"underline decoration-dashed decoration-gray-300 z-20":"z-0"}`,children:e.jsx(Y,{value:{...d},title:String(c[0].value)===d.value?j(String(c[0].value)):`Click value to see predictions for ${String(c[0].value)} for ${R(g(a.header[v]))}: ${w(String(c[0].value))}`})})},`${x}-${v}`))));const _=f[0].map((c,x)=>f.map(d=>d[x]));return e.jsxs("table",{className:o?"table table-fixed w-full":"rounded-lg shadow-md table table-fixed",children:[e.jsx("thead",{children:e.jsx("tr",{children:_[0]})}),e.jsx("tbody",{children:_.slice(1).map((c,x)=>e.jsx("tr",{children:c},x))})]})}async function Te(s,a){try{return await(await fetch(A(`${J()}/groups/${s}.json`),{signal:a})).json()}catch(t){return t instanceof Error&&t.name!=="AbortError"&&console.log(t),[]}}function oa({schema:s,runGroupName:a,numRowsToDisplay:t=-1}){const[n,r]=l.useState(),[o,i]=l.useState(0);if(l.useEffect(()=>{const h=new AbortController;async function m(){const g=await Te(a,h.signal);r(g)}return m(),()=>h.abort()},[s,a]),n===void 0||n.length===0)return e.jsx($,{});if(n.length===0)return e.jsx("div",{children:"Group currently has no tables."});const u=s.run_groups[0].name=="medhelm_scenarios";return e.jsxs("div",{children:[n.length>1?e.jsx(ce,{children:n.map((h,m)=>e.jsx(X,{active:m===o,onClick:()=>i(m),children:h.title},m))}):null,u?e.jsx(la,{schema:s,groupTable:n[o],numRowsToDisplay:t,sortColumnIndex:1},`${a}-${o}`):e.jsx(de,{schema:s,groupTable:n[o],numRowsToDisplay:t,sortColumnIndex:1},`${a}-${o}`)]})}function ae(){const{groupName:s}=be(),a=Ue(),[t,n]=l.useState(void 0),[r,o]=l.useState(),[i,u]=l.useState();l.useEffect(()=>{const g=new AbortController;async function j(){const y=O(g.signal),w=Ee(g.signal),S=await y;n(S);let p;const R=await w,f={};R.forEach(_=>{f[_.title]=[],_.rows.forEach(c=>{const x=c[0].href.replace("?group=","");p===void 0&&(p=x),f[_.title].push({title:String(c[0].value),name:x})})}),o(f),u(p)}return j(),()=>g.abort()},[]);const h=s||i;if(t===void 0||r===void 0||h===void 0)return e.jsx($,{});let m;for(const g of t.run_groups)g.name===h&&(m=g);return e.jsxs(e.Fragment,{children:[e.jsxs("div",{className:"flex flex-row",children:[e.jsx("div",{className:"w-3/4",children:m?e.jsx(B,{title:"Leaderboard: "+m.display_name,subtitle:m.description,markdown:!0}):e.jsx(B,{title:"Leaderboard",subtitle:"The HELM leaderboard shows how the various models perform across different scenarios and metrics.",markdown:!0})}),e.jsx("div",{className:"w-1/4 pt-8",children:e.jsxs("label",{htmlFor:"group",className:"block text-sm font-medium text-gray-700",children:["Select a group:",e.jsx("select",{id:"group",name:"group",onChange:g=>a("/leaderboard/"+g.target.value),className:"mt-1 block w-full pl-3 pr-10 py-2 text-base border-gray-300 focus:outline-none focus:ring focus:border-blue-300 rounded-md",value:h,children:Object.entries(r).map(([g,j])=>e.jsx("optgroup",{label:g,children:j.map(y=>e.jsx("option",{value:y.name,children:y.title},y.name))},g))})]})})]}),e.jsx(oa,{schema:t,runGroupName:h},h)]})}const ca=""+new URL("instruct-flowchart-CQIN4bVV.svg",import.meta.url).href,da=""+new URL("instruct-graph-B4NER252.svg",import.meta.url).href;function ha(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 font-bold text-center",children:"HELM Instruct: A Multidimensional Instruction Following Evaluation Framework with Absolute Ratings"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://crfm.stanford.edu/2024/02/18/helm-instruct.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{children:["We introduce ",e.jsx("em",{children:"HELM Instruct"}),", a multidimensional evaluation framework for instruction-following LLMs with absolute ratings. The framework takes an instruction, a model, an evaluator, and a criterion to generate a score. In our study, we use HELM Instruct to compare 4 instruction-following models on 7 scenarios based on 4 Human/LM evaluators and 5 criteria. Check out the blog post for more details."]}),e.jsxs("div",{className:"grid my-16 grid-cols-1 md:mx-32 md:grid-cols-2 md:gap-2",children:[e.jsx("img",{src:ca,alt:"Evaluation flowchart",className:"mx-auto block",sizes:"100vw"}),e.jsx("img",{src:da,alt:"7 scenarios, 4 models, 4 evaluators and 5 criteria",className:"mx-auto block",sizes:"100vw"})]}),e.jsxs("table",{className:"rounded-lg shadow-md table",children:[e.jsx("thead",{children:e.jsxs("tr",{children:[e.jsx("th",{children:"Model"}),e.jsx("th",{children:"Average"}),e.jsx("th",{children:"Helpfulness"}),e.jsx("th",{children:"Understandability"}),e.jsx("th",{children:"Completeness"}),e.jsx("th",{children:"Conciseness"}),e.jsx("th",{children:"Harmlessness"})]})}),e.jsxs("tbody",{children:[e.jsxs("tr",{children:[e.jsx("td",{children:"openai_gpt-4-0314"}),e.jsx("td",{children:"4.63"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.85"}),e.jsx("td",{children:"4.50"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.95"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"openai_gpt-3.5-turbo-0613"}),e.jsx("td",{children:"4.60"}),e.jsx("td",{children:"4.34"}),e.jsx("td",{children:"4.86"}),e.jsx("td",{children:"4.42"}),e.jsx("td",{children:"4.41"}),e.jsx("td",{children:"4.97"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"anthropic_claude-v1.3"}),e.jsx("td",{children:"4.56"}),e.jsx("td",{children:"4.25"}),e.jsx("td",{children:"4.87"}),e.jsx("td",{children:"4.32"}),e.jsx("td",{children:"4.40"}),e.jsx("td",{children:"4.97"})]}),e.jsxs("tr",{children:[e.jsx("td",{children:"cohere_command-xlarge-beta"}),e.jsx("td",{children:"4.31"}),e.jsx("td",{children:"3.90"}),e.jsx("td",{children:"4.73"}),e.jsx("td",{children:"3.88"}),e.jsx("td",{children:"4.31"}),e.jsx("td",{children:"4.72"})]})]})]})]})}function Pe({models:s}){return e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[s.length," models"]}),e.jsx("ul",{children:s.map((a,t)=>a.todo?e.jsxs("li",{className:"text-slate-300 mt-1",children:[a.creator_organization," / ",a.display_name]},t):e.jsx(b,{to:"models",children:e.jsxs("li",{className:"text-black mt-1",children:[a.creator_organization," / ",a.display_name]},t)}))})]})}function Ie({runGroups:s}){const a=new Map(s.filter(r=>r.metric_groups!==void 0&&(r.subgroups===void 0||r.subgroups.length===0)).map(r=>[r.name,r])),t=new Set,n=[];return s.forEach(r=>{const o=r.subgroups?r.subgroups:[],i=[];o.forEach(u=>{const h=a.get(u);h&&(i.push(h),t.add(h.name))}),i.length>0&&n.push([r,i])}),e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[t.size," scenarios"]}),e.jsx("ul",{children:n.map(([r,o])=>e.jsxs("li",{className:"my-3",children:[e.jsx(b,{className:"text-black",to:"groups/"+r.name,children:e.jsx("h2",{children:r.display_name})}),e.jsx("ul",{className:"list-disc list-inside",children:o.map(i=>i.todo?e.jsx("li",{className:`${i.todo?"ml-4 text-slate-300":"ml-4"}`,children:i.display_name},i.name):e.jsx(b,{className:"text-black",to:"groups/"+i.name,children:e.jsx("li",{className:`${i.todo?"ml-4 text-slate-300":"ml-4"}`,children:i.display_name},i.name)}))})]},r.name))})]})}const He=""+new URL("helmhero-D9TvmJsp.png",import.meta.url).href;function E({runGroupName:s=void 0,tableIndexToDisplay:a=0,numRowsToDisplay:t=10,sortColumnIndex:n=1}){const[r,o]=l.useState(void 0),[i,u]=l.useState(void 0);return l.useEffect(()=>{const h=new AbortController;async function m(){const g=await O(h.signal);o(g);const j=g.run_groups;if(j.length===0)return;const y=s||j[0].name,w=await Te(y,h.signal);u(w[a])}return m(),()=>h.abort()},[s,a]),r===void 0||i===void 0?e.jsx($,{}):e.jsx("div",{className:"rounded-2xl overflow-hidden border-2 bg-white p-1 mx-2 my-0 overflow-x-auto",style:{overflow:"auto",justifyContent:"space-between"},children:e.jsx(de,{schema:r,groupTable:i,numRowsToDisplay:t,sortColumnIndex:n,displayColumnIndexes:[0,1],sortable:!1,miniStyle:!0})})}function ma(){return e.jsxs("div",{className:"flex flex-col px-4 sm:px-6 py-100 sm:py-10 sm:mb-96 md:mb-96 lg:mb-0 xl:mb-0 2xl:mb-0",children:[e.jsx("div",{className:"flex flex-col text-center mb-10 justify-start",children:e.jsx("h1",{className:"text-3xl sm:text-4xl mb-3 sm:mb-4 mx-2 mt-2",children:e.jsx("strong",{children:"A holistic framework for evaluating foundation models."})})}),e.jsxs("div",{className:"flex flex-col md:flex-col lg:flex-row lg:justify-center",children:[e.jsx("div",{className:"w-full lg:w-1/2 flex justify-center mb-4 lg:mb-0 h-full py-10",children:e.jsx("img",{src:He,alt:"HELM Hero",className:"object-contain w-96"})}),e.jsxs("div",{className:"py-2 rounded-xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-2 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function ge(){const[s,a]=l.useState(void 0);return l.useEffect(()=>{const t=new AbortController;async function n(){const r=await O(t.signal);a(r)}return n(),()=>t.abort()},[]),s?e.jsxs(e.Fragment,{children:[e.jsx(ma,{}),e.jsx("div",{className:"mx-auto text-lg px-16",children:e.jsx("div",{className:"container mx-auto",children:e.jsxs("div",{className:"grid grid-cols-1 sm:grid-cols-2 gap-8",children:[e.jsx(Pe,{models:s.models}),e.jsx(Ie,{runGroups:s.run_groups})]})})})]}):null}function ua(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Massive Multitask Language Understanding (MMLU) on HELM"}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsxs("p",{children:[e.jsx("strong",{children:"Massive Multitask Language Understanding (MMLU)"})," ",e.jsx("a",{href:"https://arxiv.org/pdf/2009.03300.pdf",className:"link",children:"(Hendrycks et al, 2020)"})," ","is a multiple-choice question answering test that covers 57 tasks including elementary mathematics, US history, computer science, law, and more. We publish evaluation results from evaluating various models on MMLU using HELM. Our evaluation results include the following:"]}),e.jsxs("ul",{className:"my-2 list-disc list-inside",children:[e.jsx("li",{children:"Simple, standardized prompts"}),e.jsx("li",{children:"Accuracy breakdown for each of the 57 subjects"}),e.jsx("li",{children:"Full transparency of all raw prompts and predictions"})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2024/05/01/helm-mmlu.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{})})]})]})}const xa=""+new URL("air-overview-DpBbyagA.png",import.meta.url).href;function fa(){const s={fontVariant:"small-caps",fontWeight:"bold"},a=e.jsx("span",{style:s,children:"AIR-Bench 2024"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:a}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsx("img",{src:xa,alt:"AIR 2024 Categories",className:"mx-auto my-4 block w-3/4",sizes:"100vw"}),e.jsxs("p",{children:["We introduce ",a,", the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in our AI Risks study, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. ",a," contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on ",a,", uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, ",a," ","provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2407.17436",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function pa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"ThaiExam"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["In collaboration with"," ",e.jsx("a",{href:"https://www.scbx.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"SCBX"})," ","and"," ",e.jsx("a",{href:"https://www.scb10x.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"SCB 10X"}),", we introduce the ThaiExam HELM leaderboard. ThaiExam is a Thai language benchmark based on examinations for high school students and investment professionals in Thailand. The ThaiExam leaderboard is the first public leaderboard for large language models on Thai language scenarios, and features evaluations of leading language models. Like all other HELM leaderboards, the ThaiExam leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the HELM framework. We hope that this leaderboard will encourage further work in multilingual language model evaluation."]}),e.jsx("div",{className:"flex flex-row justify-center my-4",children:e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Full Leaderboard"})})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function ga(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Finance"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["LLMs show great potential for applications in the financial domain, yet there is a lack of financial-domain evaluations for LLMs. To help address this, we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"HELM Finance"})," leaderboard. The HELM Finance leaderboard evaluates leading LLMs on three financial benchmarks (i.e.,"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2109.00122/",children:"FinQA"}),","," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2311.11944/",children:"FinanceBench"}),","," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2020.nlp4convai-1.5/",children:"BANKING77"}),") that utilize real financial documents. Like all other HELM leaderboards, the HELM Finance leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the open-source HELM framework. We hope that this leaderboard provides valuable insights for financial practitioners."]}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through a collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.wellsfargo.com/",children:"Wells Fargo"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsx("div",{className:"flex flex-row justify-center my-4",children:e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Full Leaderboard"})})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const ja=""+new URL("heim-logo-BJtQlEbV.png",import.meta.url).href;function ba({metricFieldMap:s,metricGroups:a}){const t=new Set,n=[];return a.forEach(r=>{const o=[];r.metrics.forEach(i=>{const u=s[i.name];u&&(o.push(u),t.add(u.name))}),o.length>0&&n.push([r,o])}),e.jsxs("section",{children:[e.jsxs("h3",{className:"text-3xl",children:[t.size," metrics"]}),e.jsx("ul",{children:n.map(([r,o])=>e.jsxs("li",{className:"my-3",children:[e.jsx("h4",{children:r.display_name}),e.jsx("ul",{className:"list-disc list-inside",children:o.map(i=>e.jsx("li",{className:"ml-4",children:i.display_name},i.name))})]},r.name))})]})}function va(){const[s,a]=l.useState(void 0);l.useEffect(()=>{const n=new AbortController;async function r(){const o=await O(n.signal);a(o)}return r(),()=>n.abort()},[]);const t=s?s.metrics.reduce((n,r)=>(n[r.name]=r,n),{}):void 0;return e.jsxs("div",{className:"container mx-auto px-16 text-base",children:[e.jsx("div",{className:"container max-w-screen-lg mx-auto",children:e.jsx("img",{className:"mx-auto w-96",src:ja,alt:"HEIM Logo"})}),e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Holistic Evaluation of Text-To-Image Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2311.04287",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-2",children:["Significant effort has recently been made in developing text-to-image generation models, which take textual prompts as input and generate images. As these models are widely used in real-world applications, there is an urgent need to comprehensively understand their capabilities and risks. However, existing evaluations primarily focus on image-text alignment and image quality. To address this limitation, we introduce a new benchmark,"," ",e.jsx("strong",{children:"Holistic Evaluation of Text-To-Image Models (HEIM)"}),"."]}),e.jsx("p",{className:"my-2",children:"We identify 12 different aspects that are important in real-world model deployment, including:"}),e.jsxs("ul",{className:"my-2 list-disc list-inside unreset",children:[e.jsx("li",{children:"image-text alignment"}),e.jsx("li",{children:"image quality"}),e.jsx("li",{children:"aesthetics"}),e.jsx("li",{children:"originality"}),e.jsx("li",{children:"reasoning"}),e.jsx("li",{children:"knowledge"}),e.jsx("li",{children:"bias"}),e.jsx("li",{children:"toxicity"}),e.jsx("li",{children:"fairness"}),e.jsx("li",{children:"robustness"}),e.jsx("li",{children:"multilinguality"}),e.jsx("li",{children:"efficiency"})]}),e.jsx("p",{className:"my-2",children:"By curating scenarios encompassing these aspects, we evaluate state-of-the-art text-to-image models using this benchmark. Unlike previous evaluations that focused on alignment and quality, HEIM significantly improves coverage by evaluating all models across all aspects. Our results reveal that no single model excels in all aspects, with different models demonstrating strengths in different aspects."}),e.jsx("p",{className:"my-2",children:"For full transparency, this website contains all the prompts, generated images and the results for the automated and human evaluation metrics."}),e.jsx("p",{className:"my-2",children:"Inspired by HELM, we decompose the model evaluation into four key components: aspect, scenario, adaptation, and metric:"}),e.jsx("div",{className:"container max-w-screen-lg mx-auto my-8",children:e.jsx("img",{src:"https://crfm.stanford.edu/heim/latest/images/heim-main.png",alt:"HEIM scenarios, prompts, images and metrics"})}),s&&t?e.jsxs("div",{className:"grid grid-cols-1 md:grid-cols-3 gap-8",children:[e.jsx(Pe,{models:s.models}),e.jsx(Ie,{runGroups:s.run_groups}),e.jsx(ba,{metricFieldMap:t,metricGroups:s.metric_groups})]}):null]})}const wa=""+new URL("vhelm-framework-NxJE4fdA.png",import.meta.url).href,Na=""+new URL("vhelm-model-ypCL5Yvq.png",import.meta.url).href,ya=""+new URL("vhelm-aspects-NiDQofvP.png",import.meta.url).href;function La(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Holistic Evaluation of Vision-Language Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2410.07112",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-4",children:["Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermore, they differ in their evaluation procedures and the scope of the evaluation, making it difficult to compare models. To address these issues, we extend the HELM framework to VLMs to present the Holistic Evaluation of Vision Language Models (VHELM). To address these issues, we introduce VHELM, built on HELM for language models. VHELM aggregates various datasets to cover one or more of the 9 aspects:"," ",e.jsx("b",{children:"visual perception"}),", ",e.jsx("b",{children:"bias"}),", ",e.jsx("b",{children:"fairness"}),", ",e.jsx("b",{children:"knowledge"}),", ",e.jsx("b",{children:"multilinguality"}),", ",e.jsx("b",{children:"reasoning"}),", ",e.jsx("b",{children:"robustness"}),","," ",e.jsx("b",{children:"safety"}),", and ",e.jsx("b",{children:"toxicity"}),". In doing so, we produce a comprehensive, multi-dimensional view of the capabilities of the VLMs across these important factors. In addition, we standardize the standard inference parameters, methods of prompting, and evaluation metrics to enable fair comparisons across models. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast. For transparency, we release the raw model generations and complete results on this website."]}),e.jsx("p",{className:"my-4 font-bold",children:"VHELM is intended to be a living benchmark. We hope to continue adding new datasets, models and metrics over time, so please stay tuned!"}),e.jsxs("div",{className:"my-16 flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("img",{src:Na,alt:"A vision-lanuage model (VLM) takes in an image and a text prompt and generates text.",className:""}),e.jsx("img",{src:wa,alt:"An example of an evaluation for an Aspect (Knowledge) - a Scenario (MMMU) undergoes Adaptation (multimodal multiple choice) for a Model (GPT-4 Omni), then Metrics (Exact match) are computed",className:""})]}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})]})]}),e.jsx("div",{className:"container max-w-screen-lg mx-auto my-8",children:e.jsx("img",{src:ya,alt:"An example of each aspect in VHELM: Visual Perception, Bias, Fairness, Knowledge, Multilinguality, Reasoning, Robustness, Toxicity Mitigation and Safety. ",className:""})})]})}function Ma(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Chinese Language Models EVAluation Platform (CLEVA)"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["In collaboration with the"," ",e.jsx("a",{href:"https://lwwangcse.github.io/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"LaVi Lab"})," ","team from"," ",e.jsx("a",{href:"https://www.cuhk.edu.hk/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"The Chinese University of Hong Kong (CUHK)"}),", we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"Chinese Language Models EVAluation Platform (CLEVA)"})," ","leaderboard on HELM. CLEVA is a comprehensive Chinese-language benchmark for holistic evaluation of Chinese-language LLMs, and employs a standardized workflow to assess LLMs' performance across various dimensions."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2308.04813",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Ea(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"The Mighty ToRR: A Benchmark for Table Reasoning and Robustness"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://research.ibm.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"IBM Research"}),"."]}),e.jsxs("p",{className:"my-4",children:["Despite its real-world significance, model performance on tabular data remains underexplored, leaving uncertainty about which model to rely on and which prompt configuration to adopt. To address this gap, we create ",e.jsx("strong",{className:"font-bold",children:"ToRR"}),", a benchmark for Table Reasoning and Robustness, a varied benchmark that measures model performance and robustness on table-related tasks. The benchmark includes 10 datasets that cover different types of table reasoning capabilities across varied domains. ToRR goes beyond model performance rankings, and is designed to reflect whether models can handle tabular data consistently and robustly, across a variety of common table representation formats. We present a leaderboard as well as comprehensive analyses of the results of leading models over ToRR. Our results reveal a striking pattern of brittle model behavior, where even strong models are unable to perform robustly on tabular data tasks. Although no specific table format leads to consistently better performance, we show that testing over multiple formats is crucial for reliably estimating model capabilities. Moreover, we show that the reliability boost from testing multiple prompts can be equivalent to adding more test examples. Overall, our findings show that reasoning over table tasks remains a significant challenge."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4 hidden",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Sa=({id:s,title:a,text:t})=>((a==="Classic"||a==="Lite"||a==="Instruct")&&(a="HELM "+a),e.jsx("div",{className:"max-w-sm rounded overflow-hidden bg-gray-100 hover:scale-105 transition-transform duration-300",children:e.jsx("a",{href:oe(void 0,s),children:e.jsxs("div",{className:"px-6 py-4",children:[e.jsxs("div",{className:"font-bold text-xl mb-2",children:[e.jsx("div",{className:"py-3",children:e.jsx("svg",{fill:"#000000",width:"20px",height:"20px",viewBox:"0 0 24 24",xmlns:"http://www.w3.org/2000/svg",children:e.jsx("path",{d:"M22,7H16.333V4a1,1,0,0,0-1-1H8.667a1,1,0,0,0-1,1v7H2a1,1,0,0,0-1,1v8a1,1,0,0,0,1,1H22a1,1,0,0,0,1-1V8A1,1,0,0,0,22,7ZM7.667,19H3V13H7.667Zm6.666,0H9.667V5h4.666ZM21,19H16.333V9H21Z"})})}),a+" →"]}),e.jsx("p",{className:"text-gray-700 text-base",children:t})]})})}));function ka(){const[s,a]=l.useState();return l.useEffect(()=>{fetch("https://crfm.stanford.edu/helm/project_metadata.json").then(t=>t.json()).then(t=>{a(t)}).catch(t=>{console.error("Error fetching JSON:",t)})},[]),e.jsx("div",{className:"p-10 mb-20",children:e.jsx("div",{className:"grid grid-cols-2 lg:grid-cols-3 gap-4",children:s&&s.map((t,n)=>t.id==="home"?null:e.jsx(Sa,{id:t.id,title:t.title,text:t.description},n))})})}function Aa(){return e.jsxs("div",{className:"flex flex-col md:flex-row px-6 py-32",children:[e.jsxs("div",{className:"flex-1 p-4 flex flex-col justify-center",children:[e.jsx("div",{className:"flex justify-start",children:e.jsxs("div",{children:[e.jsx("h1",{className:"text-4xl mb-4 mx-4 mt-2",children:e.jsx("strong",{children:"A reproducible and transparent framework for evaluating foundation models."})}),e.jsx("h3",{className:`text-xl + mb-4 mx-4 mt-2`,children:"Find leaderboards with many scenarios, metrics, and models with support for multimodality and model-graded evaluation."})]})}),e.jsxs("div",{className:"flex flex-col md:flex-row justify-start mt-6 ml-4",children:[e.jsx("button",{className:"px-6 btn btn-grey rounded-md mb-4 md:mb-0",onClick:()=>window.scrollTo({top:760,behavior:"smooth"}),children:e.jsx("div",{children:"Leaderboards ↓"})}),e.jsx("button",{className:"px-6 btn btn-grey rounded-md md:ml-4",children:e.jsx("a",{href:"https://github.com/stanford-crfm/helm",children:"Github"})})]})]}),e.jsx("div",{className:"mx-4 mt-6 md:mt-0 md:w-1/3",children:e.jsx("img",{src:He,alt:"HELM Hero",className:"object-cover w-full h-full"})})]})}function Ra(){const[s,a]=l.useState(void 0);return l.useEffect(()=>{const t=new AbortController;async function n(){const r=await O(t.signal);a(r)}return n(),()=>t.abort()},[]),s?e.jsxs(e.Fragment,{children:[e.jsx(Aa,{}),e.jsx("div",{className:"container py-5 mx-auto text-lg",children:e.jsx("div",{className:"flex flex-col sm:flex-row justify-center mb-10 flex sm:gap-8 md:gap-32",children:e.jsx("h1",{className:"text-4xl mx-4 ",children:e.jsx("strong",{children:"HELM Leaderboards"})})})}),e.jsx(ka,{})]}):null}const _a=""+new URL("overview-BwypNWnk.png",import.meta.url).href,Ca=""+new URL("process-flow-DWDJC733.png",import.meta.url).href;function Ta(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-2 md:gap-8 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2410.22456",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-latex",children:"Latex dataset"}),e.jsx("a",{className:"px-5 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-webpage",children:"Webpage dataset"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/stanford-crfm/i2s-musicsheet",children:"Music sheet dataset"})]}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsxs("p",{children:[e.jsx("strong",{children:"Image2Struct"})," is a benchmark for evaluating vision-language models in practical tasks of extracting structured information from images."]}),e.jsx("br",{}),e.jsx("p",{children:"In our tasks, VLMs are prompted to generate the underlying structured information (i.e., code) from an input image. The code can be compiled, and the output image is evaluated against the input image to produce a score. This round-trip evaluation allows us to quantitatively evaluate VLMs on complex tasks with multiple correct answers. We create a pipeline that downloads fresh, user-submitted data from active online communities upon execution, evaluates the VLMs shortly, and produces a leaderboard."}),e.jsx("br",{}),e.jsx("img",{src:_a,alt:"Evaluation flowchart",className:"mx-auto block w-full",sizes:"100vw"}),e.jsx("br",{}),e.jsx("p",{children:"We introduce 3 tasks:"}),e.jsxs("ul",{className:"my-2 list-disc list-inside",children:[e.jsx("li",{children:"LaTex: equations, tables, plots and algorithms from ArXiV papers."}),e.jsx("li",{children:"Webpages: pages from GitHub written in HTML, CSS and Javascript. ..."}),e.jsx("li",{children:"Music sheets: crops of measures from IMSLP music sheets."})]}),e.jsx("div",{className:"flex flex-row justify-center mt-8",children:e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Full Leaderboard"})})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{numRowsToDisplay:12})})]}),e.jsx("br",{}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("p",{children:"We provide an automated process for collecting new fresh data from online communities, evaluating the models and producing a leaderboard. The pipeline is designed to be executed on a regular basis to keep the leaderboard up-to-date."}),e.jsx("br",{}),e.jsxs("p",{children:["In addition to the automated data collection, we also provide a"," ",e.jsx("i",{children:"wild"})," subset for the LaTeX and webpage tasks that are collected from Wikipedia and various popular websites. These instances do not have a corresponding code, and the evaluation is done by our proposed metric: block EMD (Earth Mover Distance)."]})]}),e.jsx("div",{className:"flex-1",children:e.jsx("img",{src:Ca,alt:"7 scenarios, 4 models, 4 evaluators and 5 criteria",className:"mx-auto block w-full",sizes:"200vw"})})]})]})}function Pa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"Elements of World Knowledge (EWoK)"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["We present the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2405.09605",children:"Elements of World Knowledge (EWoK)"})," ","leaderboard in collaboration with the EWoK team. EWoK is a benchmark for evaluating world modeling in language models by testing their ability to use knowledge of a concept to match a target text with a plausible/implausible context. EWoK targets specific concepts from multiple knowledge domains known to be vital for world modeling in humans, including social interactions and spatial relations."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2405.09605",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Ia=""+new URL("medhelm-overview-CND0EIsy.png",import.meta.url).href;function Ha(){const s=e.jsx("strong",{className:"font-bold",children:"MedHELM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"MedHELM"}),e.jsx("p",{className:"text-xl my-4 italic text-center",children:"Holistic Evaluation of Large Language Models for Medical Tasks"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[7] text-l",children:[e.jsxs("p",{className:"my-",children:["We introduce ",s,", an extensible evaluation framework for assessing LLM performance for medical tasks. Building on the HELM framework, ",s," comprises a structured taxonomy with 5 categories, 22 subcategories, and 121 distinct clinical tasks as well as 35 distinct benchmarks (14 private, 7 gated-access, and 14 public). The benchmarks represent a spectrum of healthcare scenarios, from diagnostic decision-making to patient communication, providing a more nuanced and medically relevant assessment of AI capabilities in healthcare settings."]}),e.jsx("img",{src:Ia,alt:"MedHELM Task Categories",className:"mx-auto my-4 block w-7/8",sizes:"100vw"}),e.jsxs("p",{className:"my-4",children:[s," establishes a foundation for testing and evaluation of the real-world applicability of language models in healthcare. It is made possible by a unique collaboration between the Center for Research on Foundation Models, Technology and Digital Solutions at Stanford Healthcare, and Microsoft Healthcare and Life Sciences in partnership with faculty in the Departments of Medicine, Computer Science, Anesthesiology, Dermatology, Pediatrics and Biomedical Data Science as well as trainees from the MCiM program at the Clinical Excellence Research Center. The effort is coordinated by the Center for Biomedical Informatics Research."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://www.nature.com/articles/s41591-025-04151-2",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm-helm.readthedocs.io/en/latest/medhelm/",children:"Documentation"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://hai.stanford.edu/news/holistic-evaluation-of-large-language-models-for-medical-applications",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[3] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const $a=""+new URL("medhelm-v1-overview-Cu2tphBB.png",import.meta.url).href;function Da(){const s=e.jsx("strong",{className:"font-bold",children:"MedHELM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"MedHELM"}),e.jsx("p",{className:"text-xl my-4 italic text-center",children:"Medical and AI experts build a benchmark for evaluation of LLMs grounded in real-world healthcare needs."}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["We introduce ",s,", a comprehensive healthcare benchmark to evaluate language models on real-world clinical tasks using real electronic health records. Building on the HELM framework,"," ",s," comprises a structured taxonomy with 5 categories, 22 subcategories, and 121 distinct clinical tasks as well as 31 diverse datasets (12 private, 6 gated-access, and 13 public). The datasets represent a spectrum of healthcare scenarios, from diagnostic decision-making to patient communication, providing a more nuanced and clinically relevant assessment of AI capabilities in healthcare settings."]}),e.jsx("img",{src:$a,alt:"MedHELM Task Categories",className:"mx-auto my-4 block w-7/8",sizes:"100vw"}),e.jsxs("p",{className:"my-4",children:[s," establishes a foundation for testing and evaluation of the real-world applicability of language models in healthcare. It is made possible by a unique collaboration between the Center for Research on Foundation Models, Technology and Digital Solutions at Stanford Healthcare, and Microsoft Healthcare and Life Sciences in partnership with faculty in the Departments of Medicine, Computer Science, Anesthesiology, Dermatology, Pediatrics and Biomedical Data Science as well as trainees from the MCiM program at the Clinical Excellence Research Center. The effort is coordinated by the Center for Biomedical Informatics Research."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2505.23802",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm-helm.readthedocs.io/en/latest/medhelm/",children:"Documentation"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://hai.stanford.edu/news/holistic-evaluation-of-large-language-models-for-medical-applications",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Ba=""+new URL("helm-safety-COfndXuS.png",import.meta.url).href;function Oa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"HELM Safety"}),e.jsxs("div",{className:"flex flex-col lg:flex-row items-center gap-8",children:[e.jsxs("div",{className:"flex-1 text-xl",children:[e.jsx("img",{src:Ba,alt:"Logo",className:"mx-auto p-0 block",style:{width:"300px"}}),e.jsx("p",{children:"Language models demonstrate powerful capabilities and pose significant risks. Given their widespread deployment, standardized public benchmarking of such models is vital. While language models are routinely evaluated on standard capability benchmarks, comparable standardization for benchmarking safety risks lags behind. To address this gap, we introduce HELM-Safety as a collection of 5 safety benchmarks that span 6 risk categories (e.g. violence, fraud, discrimination, sexual, harassment, deception). We present evaluation results for recent leading open weights and closed models."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2024/11/08/helm-safety.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsx("div",{className:"flex-1",children:e.jsx(E,{})})]})]})}function Fa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Capabilities"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{children:["Building on the HELM framework, we introduce"," ",e.jsx("strong",{className:"font-bold",children:"HELM Capabilities"})," to capture our latest thinking on the evaluation of general capabilities. HELM Capabilities is a new benchmark and leaderboard that consists of a curated set of scenarios for measuring various capabilities of language models. Like all other HELM leaderboards, the HELM Capabilities leaderboard provides full prompt-level transparency, and the results can be fully reproduced using the HELM framework."]}),e.jsxs("div",{className:"flex flex-row justify-center my-4",children:[e.jsx("a",{href:"https://crfm.stanford.edu/2025/03/20/helm-capabilities.html",className:"px-10 btn rounded-md mx-4",children:"Blog Post"}),e.jsx(b,{to:"leaderboard",className:"px-10 btn rounded-md mx-4",children:"Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Ua(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"MMLU-Winogrande-Afr: Clinical MMLU and Winogrande in 11 low-resource African languages"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://ghamut.com/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"Ghamut Corporation"})," ","and the"," ",e.jsx("a",{href:"https://www.gatesfoundation.org/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"Gates Foundation"}),"."]}),e.jsx("p",{className:"my-4",children:"Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2412.12417",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function qa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4 italic",children:["This leaderboard is a collaboration with"," ",e.jsx("a",{href:"https://aisingapore.org/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"AI Singapore"}),"."]}),e.jsxs("p",{className:"my-4",children:["With the rapid emergence of novel capabilities in Large Language Models (LLMs), the need for rigorous multilingual and multicultural benchmarks that are integrated has become more pronounced. Though existing LLM benchmarks are capable of evaluating specific capabilities of LLMs in English as well as in various mid- to low-resource languages, including those in the Southeast Asian (SEA) region, a comprehensive and authentic evaluation suite for the SEA languages has not been developed thus far. Here, we present"," ",e.jsx("strong",{className:"font-bold",children:"SEA-HELM"}),", a holistic linguistic and cultural LLM evaluation suite that emphasizes SEA languages, comprising five core pillars: (1) NLP Classics, (2) LLM-specifics, (3) SEA Linguistics, (4) SEA Culture, (5) Safety. SEA-HELM currently supports Filipino, Indonesian, Tamil, Thai, and Vietnamese. We also introduce the SEA-HELM leaderboard, which allows users to understand models' multilingual and multicultural performance in a systematic and user-friendly manner."]}),e.jsxs("p",{className:"mb-4 italic",children:["Additional evaluation results are available on the external"," ",e.jsx("a",{href:"https://leaderboard.sea-lion.ai/",className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",children:"AI Singapore (AISG) SEA-HELM leaderboard"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://arxiv.org/abs/2502.14301",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"HELM Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://leaderboard.sea-lion.ai/",children:"AISG Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Wa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM Speech"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsx("p",{className:"my-4",children:"We present a HELM leaderboard for speech tasks."}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function za(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Long Context"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsx("p",{className:"my-4",children:"Recent Large Language Models (LLMs) support processing long inputs with hundreds of thousands or millions of tokens. Long context capabilities are important for many real-world applications, such as processing long text documents, conducting long conversations or following complex instructions. However, support for long inputs does not equate to strong long context capabilities. As such, there is a need for rigorous and comprehensive evaluations of long context capabilities."}),e.jsxs("p",{className:"my-4",children:["To address this, we introduce the"," ",e.jsx("strong",{className:"font-bold",children:"HELM Long Context"})," ","leaderboard, which provides transparent, comparable and reproducible evaluations of long context capabilities of recent models. The benchmark consists of 5 tasks:"]}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/ruler_squad",children:e.jsx("strong",{className:"font-bold",children:"RULER SQuAD"})})," ","— open ended single-hop question answering on passages"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/ruler_hotpotqa",children:e.jsx("strong",{className:"font-bold",children:"RULER HotPotQA"})})," ","— open ended multi-hop question answering on passages"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/infinite_bench_en_qa",children:e.jsx("strong",{className:"font-bold",children:"∞Bench En.MC"})})," ","— multiple choice question answering based on the plot of a novel"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/infinite_bench_en_sum",children:e.jsx("strong",{className:"font-bold",children:"∞Bench En.Sum"})})," ","— summarization of the plot of a novel"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"#/leaderboard/openai_mrcr",children:e.jsx("strong",{className:"font-bold",children:"OpenAI MRCR"})})," ","— multi-round co-reference resolution on a long, multi-turn, synthetic conversation"]})]}),e.jsx("p",{className:"my-4",children:"The results demonstrate that even though significant progress has been made on long context capabilities, there is still considerable room for improvement."}),e.jsx("p",{className:"my-4",children:"As with all HELM leaderboards, this leaderboard provides full transparency into all LLM requests and responses, and the results are reproducible using the HELM open source framework."}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through research collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.lvmh.com/",children:"LVMH"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2025/09/29/helm-long-context.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Va(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"HELM SQL"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"mb-4",children:["Text-to-SQL is the task of converting natural language instructions into SQL code. There has been increasing interest in text-to-SQL for applications by data scientists in various domains. Thus, we introduce the ",e.jsx("strong",{className:"font-bold",children:"HELM SQL"})," ","leaderboard for text-to-SQL evaluations. The HELM SQL leaderboard evaluates leading LLMs on two existing text-to-SQL benchmarks (Spider, BIRD-SQL) that cover a range of professional domains. In addition, we introduce a new benchmark,"," ",e.jsx("strong",{className:"font-bold",children:"CzechBankQA"}),", a text-to-SQL benchmark based on a real public bank customer relational database, to address the lack of coverage of text-to-SQL in the financial domain. CzechBankQA consists of text-to-SQL queries and gold labels provided by professionals at Wells Fargo. We hope that this leaderboard provides useful insights for data science practitioners."]}),e.jsxs("p",{className:"my-4",children:["This leaderboard was produced through research collaboration with"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://www.wellsfargo.com/",children:"Wells Fargo"}),", and was funded by the"," ",e.jsx("a",{className:"font-bold underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://hai.stanford.edu/corporate-affiliate-program",children:"HAI Corporate Affiliate Program"}),"."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4 hidden",href:"#",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Ja(){const s=e.jsx("strong",{className:"font-bold",children:"ViLLM"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"ViLLM: Crossing Linguistic Horizon"}),e.jsxs("p",{className:"text-xl my-4 italic text-center",children:[s," is a comprehensive benchmark suite for evaluating the performance of language models in ",e.jsx("strong",{children:"Vietnamese"}),"."]}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["As multilingual large language models (LLMs) continue to advance natural language processing, bridging communication across diverse cultures and languages, their effectiveness in lower-resourced languages like Vietnamese remains limited. Despite being trained on large multilingual corpora, most open-source LLMs struggle with Vietnamese understanding and generation.",e.jsx("strong",{children:" ViLLM"})," addresses this gap by providing a robust evaluation framework tailored specifically for Vietnamese. It includes ",e.jsx("strong",{children:"11 essential scenarios"}),", each targeting a core capability of Vietnamese LLMs:"]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"ViLLM"})," includes 11 carefully designed evaluation scenarios, each addressing a core language modeling capability:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"Question Answering:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/juletxara/xquad_xtreme",children:"XQuAD"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/facebook/mlqa",children:"MLQA"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Summarization:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/Yuhthe/vietnews",children:"VietNews"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/GEM/wiki_lingua",children:"WikiLingua"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Sentiment Analysis:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/vlsp2016",children:"VLSP2016"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-VSFC",children:"UiT-VSFC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Text Classification:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/PhoATIS",children:"PhoATIS"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-VSMEC",children:"UiT-VSMEC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Knowledge:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/zalo_e2eqa",children:"ZaloE2E"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/ViMMRC",children:"UiT-ViMMRC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Toxic Detection:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/UIT-ViHSD",children:"UiT-VIHSD"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/tarudesu/ViCTSD",children:"UiT-ViCTSD"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Information Retrieval:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/unicamp-dl/mmarco",children:"mMARCO"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/unicamp-dl/mrobust",children:"mRobust04"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Language Modeling:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/MLQA",children:"MLQA"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/VSEC",children:"VSEC"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Reasoning:"})," ",e.jsx("a",{className:"link-primary",href:"",children:"Synthetic reasoning"}),","," ",e.jsx("a",{className:"link-primary",href:"",children:"Natural synthetic reasoning"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Mathematic:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/Vietnamese-MATH",children:"MATH"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Translation:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/vietgpt/opus100_envi",children:"OPUS100"}),","," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/ura-hcmut/PhoMT",children:"PhoMT"})]})]})]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"ViLLM"})," also includes tools to promote the ethical and responsible use of language models:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"Bias Assessment:"})," Detects and mitigates biased patterns in model outputs."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Toxicity Assessment:"})," Monitors and controls the generation of harmful or offensive content."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Fairness Evaluation:"})," Ensures equitable performance across demographic groups and languages."]}),e.jsxs("li",{children:[e.jsx("strong",{children:"Robustness Analysis:"})," Evaluates model stability against noisy or adversarial inputs in real-world scenarios."]})]})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://aclanthology.org/2024.findings-naacl.182",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Ga(){const s=e.jsx("strong",{className:"font-bold",children:"SLPHelm"});return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-8 font-bold text-center",children:"SLPHelm: Advancing Speech Language Processing"}),e.jsxs("p",{className:"text-xl my-4 italic text-center",children:[s," is a comprehensive benchmark suite for evaluating the performance of speech language models across multiple languages and tasks."]}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-1 text-l",children:[e.jsxs("p",{className:"my-4",children:["As speech language models continue to evolve and transform how we interact with technology, there is a growing need for standardized evaluation frameworks that can assess their capabilities across diverse languages and tasks. Despite significant advances in speech processing, many models struggle with multilingual understanding, accent recognition, and domain-specific speech tasks."," ",e.jsx("strong",{children:"SLPHelm"})," addresses these challenges by providing a robust evaluation framework that includes",e.jsx("strong",{children:" 5 key scenarios"})," across ",e.jsx("strong",{children:"15 models"}),", each targeting essential speech processing capabilities:"]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"SLPHelm"})," includes 5 carefully designed evaluation scenarios, each addressing a core speech processing capability:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsx("li",{children:e.jsx("strong",{children:"Disorder Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Transcription Accuracy"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Type Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Symptom Diagnosis"})}),e.jsx("li",{children:e.jsx("strong",{children:"Disorder Diagnosis via Transcription"})})]})]}),e.jsxs("p",{className:"my-4",children:[e.jsx("strong",{children:"SLPHelm"})," evaluates models using comprehensive datasets:",e.jsxs("ul",{className:"list-disc list-inside mt-2",children:[e.jsxs("li",{children:[e.jsx("strong",{children:"UltraSuite:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmUltraSuite",children:"UltraSuite"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"ENNI:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/ENNI",children:"ENNI"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"LeNormand:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/LeNormand",children:"LeNormand"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"PERCEPT-GFTA:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmDataset/tree/main/PERCEPT-GFTA",children:"PERCEPT-GFTA"})]}),e.jsxs("li",{children:[e.jsx("strong",{children:"UltraSuite w/ Manual Labels:"})," ",e.jsx("a",{className:"link-primary",href:"https://huggingface.co/datasets/SAA-Lab/SLPHelmManualLabels",children:"SLPHelmManualLabels"})]})]})]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"py-2 pb-6 rounded-3xl bg-gray-100 h-full",style:{maxWidth:"100%"},children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Qa=""+new URL("audio-table-Dn5NMMeJ.png",import.meta.url).href;function Za(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:"Holistic Evaluation of Audio-Language Models"}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-8 md:gap-32 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2508.21376",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"#/leaderboard",children:"Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://github.com/stanford-crfm/helm",children:"Github"})]}),e.jsxs("p",{className:"my-4",children:["Evaluations of"," ",e.jsx("strong",{className:"font-bold",children:"audio-language models (ALMs)"})," ","— multimodal models that take interleaved audio and text as input and output text — are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters."]}),e.jsxs("p",{className:"my-4",children:["To address these shortfalls, we introduce"," ",e.jsx("strong",{className:"font-bold",children:"AHELM"}),", a benchmark that aggregates various datasets — including"," ",e.jsx("strong",{className:"font-bold",children:"2 new synthetic audio-text datasets"})," ","called ",e.jsx("strong",{className:"font-bold",children:"PARADE"}),", which evaluates the ALMs on avoiding stereotypes, and"," ",e.jsx("strong",{className:"font-bold",children:"CoRe-Bench"}),", which measures reasoning over conversational audio through inferential multi-turn question answering — to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs:"," ",e.jsx("em",{className:"italic",children:"audio perception"}),","," ",e.jsx("em",{className:"italic",children:"knowledge"}),","," ",e.jsx("em",{className:"italic",children:"reasoning"}),","," ",e.jsx("em",{className:"italic",children:"emotion detection"}),","," ",e.jsx("em",{className:"italic",children:"bias"}),", ",e.jsx("em",{className:"italic",children:"fairness"}),","," ",e.jsx("em",{className:"italic",children:"multilinguality"}),","," ",e.jsx("em",{className:"italic",children:"robustness"}),","," ",e.jsx("em",{className:"italic",children:"toxicity"}),", and"," ",e.jsx("em",{className:"italic",children:"safety"}),". We standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models."]}),e.jsxs("div",{className:"my-16 flex flex-col lg:flex-row gap-8",children:[e.jsx("div",{className:"flex-1 text-xl",children:e.jsx("img",{src:Qa,alt:"An example of each aspect in AHELM: Auditory Perception, Knowledge, Reasoning, Emotion Detection, Bias, Fairness, Multilinguality, Robustness, Toxicity and Safety. ",className:""})}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})]})]})]})}function Ka(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Arabic"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsxs("p",{className:"my-4",children:["As part of our efforts to better understand the multilingual capabilities of large language models (LLMs), we present"," ",e.jsx("strong",{className:"font-bold",children:"HELM Arabic"}),", a leaderboard for transparent and reproducible evaluation of LLMs on Arabic language benchmarks. This leaderboard was produced in collaboration with"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arabic.ai/",children:"Arabic.AI"}),"."]}),e.jsxs("p",{className:"my-4",children:["HELM Arabic builds on a collection of established Arabic-language evaluation tasks that are widely used in the research community (",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"El Filali et al., 2025"}),"). It includes the following seven benchmarks:"]}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/OALL/AlGhafa-Arabic-LLM-Benchmark-Native",children:"AlGhafa"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2023.arabicnlp-1.21/",children:"Almazrouei et al., 2023"}),") — an Arabic language multiple choice evaluation benchmark derived from publicly available NLP datasets"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/ArabicMMLU",children:"ArabicMMLU"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2024.findings-acl.334/",children:"Koto et al., 2024"}),") — a native Arabic language question answering benchmark using questions sourced from school exams across diverse educational levels in different countries spanning North Africa, the Levant, and the Gulf regions"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/mhardalov/exams",children:"Arabic EXAMS"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2020.emnlp-main.438/",children:"Hardalov et al., 2020"}),") — the Arabic language subset of the EXAMS multilingual question answering benchmark, which consists of high school exam questions across various school subjects"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/MadinahQA",children:"MadinahQA"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://aclanthology.org/2024.findings-acl.334/",children:"Koto et al., 2024"}),") — a question answering benchmark published by MBZUAI that tests knowledge of Arabic language and grammar"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/asas-ai/AraTrust",children:"AraTrust"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"Alghamdi et al., 2025"}),") — an Arab-region-specific safety evaluation dataset consisting of human-written questions including direct attacks, indirect attacks, and harmless requests with sensitive words"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/OALL/ALRAGE",children:"ALRAGE"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/blog/leaderboard-arabic-v2",children:"El Filali et al., 2025"}),") — an Arabic language passage-based open-ended model-graded question answering benchmark that reflects retrieval-augmented generation use cases"]}),e.jsxs("li",{children:[e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://huggingface.co/datasets/MBZUAI/human_translated_arabic_mmlu",children:"ArbMMLU-HT"})," ","(",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arxiv.org/abs/2308.16149",children:"Sengupta et al., 2023"}),") — a translation of MMLU to Arabic by human translators published by MBZUAI"]})]}),e.jsxs("p",{className:"my-4",children:["The"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm.stanford.edu/helm/arabic/latest/",children:"leaderboard results"})," ","show that LLMs have made significant progress in Arabic language understanding over the last few years. As with all HELM leaderboards, this leaderboard provides full transparency into all LLM requests and responses, and the results are"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://crfm-helm.readthedocs.io/en/latest/reproducing_leaderboards/",children:"reproducible"})," ","using the"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://github.com/stanford-crfm/helm/",children:"HELM open source framework"}),". We hope that this leaderboard will be a valuable resource for the Arabic NLP community."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2025/12/18/helm-arabic.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}function Xa(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsx("h1",{className:"text-3xl my-4 font-bold text-center",children:"HELM Arabic Enterprise"}),e.jsxs("div",{className:"flex flex-col lg:flex-row gap-8",children:[e.jsxs("div",{className:"flex-[1] text-l",children:[e.jsxs("p",{className:"my-4",children:["We present HELM Arabic Enterprise, a leaderboard for transparent, reproducible evaluation of large language models on Arabic-language benchmarks designed around enterprise use cases. The leaderboard was developed in collaboration with"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://arabic.ai/",children:"Arabic.AI"}),"."]}),e.jsx("p",{className:"my-4",children:"Arabic enterprise applications often require more than general conversational ability. Models must generate grounded content, reason over financial concepts, answer domain-specific legal questions, and operate reliably in Arabic across formal, professional, and institutional registers. HELM Arabic Enterprise evaluates these capabilities through six tasks across content generation, financial reasoning, and legal question answering:"}),e.jsxs("ul",{className:"list-disc pl-6",children:[e.jsx("li",{children:"Article Generation"}),e.jsx("li",{children:"Financial Multiple Choice Question Anwering"}),e.jsx("li",{children:"Financial Boolean Verification"}),e.jsx("li",{children:"Financial Calculation"}),e.jsx("li",{children:"Legal Open-book Question Answering"}),e.jsx("li",{children:"Legal Closed-book Question Answering"})]}),e.jsxs("p",{className:"my-4",children:["As with all HELM leaderboards, HELM Arabic Enterprise emphasizes transparency and reproducibility. All model requests, responses, prompts, metrics, and scores are made available for inspection. Results can be reproduced using the"," ",e.jsx("a",{className:"underline text-blue-600 hover:text-blue-800 visited:text-purple-600",href:"https://github.com/stanford-crfm/helm/",children:"open-source HELM framework"}),", allowing researchers and practitioners to audit model behavior rather than relying only on aggregate scores. We hope HELM Arabic Enterprise becomes a useful resource for the Arabic NLP community and for organizations evaluating LLMs for Arabic enterprise applications."]}),e.jsxs("div",{className:"flex flex-row justify-center mt-4",children:[e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"https://crfm.stanford.edu/2026/05/26/helm-arabic-enterprise.html",children:"Blog Post"}),e.jsx("a",{className:"px-10 btn rounded-md mx-4",href:"#/leaderboard",children:"Full Leaderboard"})]})]}),e.jsxs("div",{className:"flex-[1] py-2 rounded-3xl bg-gray-100 h-full",children:[e.jsx(E,{}),e.jsx("div",{className:"flex justify-end",children:e.jsx(b,{to:"leaderboard",children:e.jsx("button",{className:"px-4 mx-3 mt-1 btn bg-white rounded-md",children:e.jsx("span",{children:"See More"})})})})]})]})]})}const Ya=""+new URL("overview-CVXNopt8.png",import.meta.url).href;function et(){return e.jsxs("div",{className:"container mx-auto px-16",children:[e.jsxs("h1",{className:"text-3xl mt-16 my-8 font-bold text-center",children:[e.jsx("strong",{children:"RoboReward"}),": General-purpose Vision-Language Reward Models for Robotics"]}),e.jsxs("div",{className:"flex flex-col sm:flex-row justify-center gap-2 sm:gap-4 md:gap-8 my-8",children:[e.jsx("a",{className:"px-10 btn rounded-md",href:"https://arxiv.org/abs/2601.00675",children:"Paper"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://crfm.stanford.edu/helm/robo-reward-bench/latest/#/leaderboard",children:"Full Leaderboard"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/datasets/teetone/RoboReward",children:"RoboReward Dataset"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/teetone/RoboReward-4B",children:"RoboReward 4B"}),e.jsx("a",{className:"px-10 btn rounded-md",href:"https://huggingface.co/teetone/RoboReward-8B",children:"RoboReward 8B"})]}),e.jsx("p",{className:"my-4",children:"A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotic domains, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives. Vision-language models (VLMs) have shown promise as automatic reward models, yet their effectiveness on real robot tasks is poorly understood."}),e.jsxs("p",{className:"my-4",children:["In this work, we aim to close this gap by introducing (1)"," ",e.jsx("strong",{children:"RoboReward"}),", a robotics reward dataset and benchmark built on large-scale real-robot corpora from Open X-Embodiment (OXE) and RoboArena, and (2) vision-language reward models trained on this dataset (",e.jsx("strong",{children:"RoboReward 4B/8B"}),"). Because OXE is success-heavy and lacks failure examples, we propose a"," ",e.jsx("em",{children:"negative examples data augmentation"})," pipeline that generates calibrated ",e.jsx("em",{children:"negatives"})," and ",e.jsx("em",{children:"near-misses"})," via counterfactual relabeling of successful episodes and temporal clipping to create partial-progress outcomes from the same videos."]}),e.jsx("p",{className:"my-4",children:"Using this framework, we produce an extensive training and evaluation dataset that spans diverse tasks and embodiments and enables systematic evaluation of whether state-of-the-art VLMs can reliably provide rewards for robotics. Our evaluation of leading open-weight and proprietary VLMs reveals that no model excels across all tasks, underscoring substantial room for improvement. We then train general-purpose 4B- and 8B-parameter models that outperform much larger VLMs in assigning rewards for short-horizon robotic tasks. Finally, we deploy the 8B reward VLM in real-robot reinforcement learning and find that it improves policy learning over Gemini Robotics-ER 1.5, a frontier physical reasoning VLM trained on robotics data, by a large margin, while substantially narrowing the gap to RL training with human-provided rewards."}),e.jsxs("div",{className:"my-12 flex flex-col lg:flex-row gap-8 items-start",children:[e.jsx("div",{className:"flex-1",children:e.jsx("img",{src:Ya,alt:"RoboReward overview",className:"w-full max-w-full rounded-lg shadow"})}),e.jsxs("div",{className:"flex-1",children:[e.jsx(E,{}),e.jsx(b,{to:"leaderboard",className:"px-4 mx-3 mt-3 btn bg-white rounded-md",children:e.jsx("span",{children:"See more"})})]})]})]})}function st(){return window.PROJECT_ID==="lite"?e.jsx(ge,{}):window.PROJECT_ID==="instruct"?e.jsx(ha,{}):window.PROJECT_ID==="image2struct"?e.jsx(Ta,{}):window.PROJECT_ID==="heim"?e.jsx(va,{}):window.PROJECT_ID==="mmlu"?e.jsx(ua,{}):window.PROJECT_ID==="vhelm"?e.jsx(La,{}):window.PROJECT_ID==="air-bench"?e.jsx(fa,{}):window.PROJECT_ID==="thaiexam"?e.jsx(pa,{}):window.PROJECT_ID==="finance"?e.jsx(ga,{}):window.PROJECT_ID==="cleva"?e.jsx(Ma,{}):window.PROJECT_ID==="torr"?e.jsx(Ea,{}):window.PROJECT_ID==="ewok"?e.jsx(Pa,{}):window.PROJECT_ID==="medhelm"&&window.RELEASE=="v1.0.0"?e.jsx(Da,{}):window.PROJECT_ID==="medhelm"?e.jsx(Ha,{}):window.PROJECT_ID==="safety"?e.jsx(Oa,{}):window.PROJECT_ID==="capabilities"?e.jsx(Fa,{}):window.PROJECT_ID==="mmlu-winogrande-afr"?e.jsx(Ua,{}):window.PROJECT_ID==="seahelm"?e.jsx(qa,{}):window.PROJECT_ID==="speech"?e.jsx(Wa,{}):window.PROJECT_ID==="sql"?e.jsx(Va,{}):window.PROJECT_ID==="long-context"?e.jsx(za,{}):window.PROJECT_ID==="villm"?e.jsx(Ja,{}):window.PROJECT_ID==="slphelm"?e.jsx(Ga,{}):window.PROJECT_ID==="audio"?e.jsx(Za,{}):window.PROJECT_ID==="arabic"?e.jsx(Ka,{}):window.PROJECT_ID==="robo-reward-bench"?e.jsx(et,{}):window.PROJECT_ID==="arabic-enterprise"?e.jsx(Xa,{}):window.PROJECT_ID==="home"?e.jsx(Ra,{}):e.jsx(ge,{})}function at(){return e.jsx(qe,{children:e.jsx(We,{children:e.jsxs(I,{path:"/",element:e.jsx(fs,{}),children:[e.jsx(I,{index:!0,element:e.jsx(st,{})}),e.jsx(I,{path:"leaderboard",element:e.jsx(ae,{})}),e.jsx(I,{path:"leaderboard/:groupName",element:e.jsx(ae,{})}),e.jsx(I,{path:"models",element:e.jsx(vs,{})}),e.jsx(I,{path:"scenarios",element:e.jsx(ws,{})}),e.jsx(I,{path:"groups",element:e.jsx(Ms,{})}),e.jsx(I,{path:"groups/:groupName",element:e.jsx(ae,{})}),e.jsx(I,{path:"runs",element:e.jsx(Ss,{})}),e.jsx(I,{path:"runs/:runName",element:e.jsx(ia,{})})]})})})}Qe.createRoot(document.getElementById("root")).render(e.jsx(ze.StrictMode,{children:e.jsx(at,{})})); diff --git a/src/helm/benchmark/static_build/assets/react-BhnNyHuP.js b/src/helm/benchmark/static_build/assets/react-D3IQTVQZ.js similarity index 78% rename from src/helm/benchmark/static_build/assets/react-BhnNyHuP.js rename to src/helm/benchmark/static_build/assets/react-D3IQTVQZ.js index 10f72f80f4b..3acee4f72bd 100644 --- a/src/helm/benchmark/static_build/assets/react-BhnNyHuP.js +++ b/src/helm/benchmark/static_build/assets/react-D3IQTVQZ.js @@ -1,4 +1,4 @@ -function cd(o,c){for(var a=0;ap[g]})}}}return Object.freeze(Object.defineProperty(o,Symbol.toStringTag,{value:"Module"}))}var Cp=typeof globalThis<"u"?globalThis:typeof window<"u"?window:typeof global<"u"?global:typeof self<"u"?self:{};function fd(o){return o&&o.__esModule&&Object.prototype.hasOwnProperty.call(o,"default")?o.default:o}var Mi={exports:{}},Y={};/** +function fd(o,c){for(var a=0;ap[g]})}}}return Object.freeze(Object.defineProperty(o,Symbol.toStringTag,{value:"Module"}))}var xp=typeof globalThis<"u"?globalThis:typeof window<"u"?window:typeof global<"u"?global:typeof self<"u"?self:{};function dd(o){return o&&o.__esModule&&Object.prototype.hasOwnProperty.call(o,"default")?o.default:o}var Mi={exports:{}},Y={};/** * @license React * react.production.min.js * @@ -6,7 +6,7 @@ function cd(o,c){for(var a=0;a>>1,E=T[h];if(0>>1;hg(J,D))qg(oe,J)?(T[h]=oe,T[q]=D,h=q):(T[h]=J,T[X]=D,h=X);else if(qg(oe,D))T[h]=oe,T[q]=D,h=q;else break e}}return $}function g(T,$){var D=T.sortIndex-$.sortIndex;return D!==0?D:T.id-$.id}if(typeof performance=="object"&&typeof performance.now=="function"){var w=performance;o.unstable_now=function(){return w.now()}}else{var S=Date,N=S.now();o.unstable_now=function(){return S.now()-N}}var x=[],z=[],B=1,R=null,W=3,re=!1,G=!1,H=!1,L=typeof setTimeout=="function"?setTimeout:null,le=typeof clearTimeout=="function"?clearTimeout:null,ue=typeof setImmediate<"u"?setImmediate:null;typeof navigator<"u"&&navigator.scheduling!==void 0&&navigator.scheduling.isInputPending!==void 0&&navigator.scheduling.isInputPending.bind(navigator.scheduling);function ee(T){for(var $=a(z);$!==null;){if($.callback===null)p(z);else if($.startTime<=T)p(z),$.sortIndex=$.expirationTime,c(x,$);else break;$=a(z)}}function ie(T){if(H=!1,ee(T),!G)if(a(x)!==null)G=!0,Ue(Ce);else{var $=a(z);$!==null&&me(ie,$.startTime-T)}}function Ce(T,$){G=!1,H&&(H=!1,le(Ze),Ze=-1),re=!0;var D=W;try{for(ee($),R=a(x);R!==null&&(!(R.expirationTime>$)||T&&!Zt());){var h=R.callback;if(typeof h=="function"){R.callback=null,W=R.priorityLevel;var E=h(R.expirationTime<=$);$=o.unstable_now(),typeof E=="function"?R.callback=E:R===a(x)&&p(x),ee($)}else p(x);R=a(x)}if(R!==null)var K=!0;else{var X=a(z);X!==null&&me(ie,X.startTime-$),K=!1}return K}finally{R=null,W=D,re=!1}}var Me=!1,Fe=null,Ze=-1,Rt=5,gt=-1;function Zt(){return!(o.unstable_now()-gtT||125h?(T.sortIndex=D,c(z,T),a(x)===null&&T===a(z)&&(H?(le(Ze),Ze=-1):H=!0,me(ie,D-h))):(T.sortIndex=E,c(x,T),G||re||(G=!0,Ue(Ce))),T},o.unstable_shouldYield=Zt,o.unstable_wrapCallback=function(T){var $=W;return function(){var D=W;W=$;try{return T.apply(this,arguments)}finally{W=D}}}})(Fi)),Fi}var Ws;function vd(){return Ws||(Ws=1,Di.exports=md()),Di.exports}/** + */var Vs;function vd(){return Vs||(Vs=1,(function(o){function c(T,$){var D=T.length;T.push($);e:for(;0>>1,E=T[h];if(0>>1;hg(J,D))qg(oe,J)?(T[h]=oe,T[q]=D,h=q):(T[h]=J,T[X]=D,h=X);else if(qg(oe,D))T[h]=oe,T[q]=D,h=q;else break e}}return $}function g(T,$){var D=T.sortIndex-$.sortIndex;return D!==0?D:T.id-$.id}if(typeof performance=="object"&&typeof performance.now=="function"){var w=performance;o.unstable_now=function(){return w.now()}}else{var S=Date,N=S.now();o.unstable_now=function(){return S.now()-N}}var _=[],z=[],B=1,R=null,W=3,re=!1,G=!1,H=!1,L=typeof setTimeout=="function"?setTimeout:null,le=typeof clearTimeout=="function"?clearTimeout:null,ue=typeof setImmediate<"u"?setImmediate:null;typeof navigator<"u"&&navigator.scheduling!==void 0&&navigator.scheduling.isInputPending!==void 0&&navigator.scheduling.isInputPending.bind(navigator.scheduling);function ee(T){for(var $=a(z);$!==null;){if($.callback===null)p(z);else if($.startTime<=T)p(z),$.sortIndex=$.expirationTime,c(_,$);else break;$=a(z)}}function ie(T){if(H=!1,ee(T),!G)if(a(_)!==null)G=!0,Ue(Ce);else{var $=a(z);$!==null&&me(ie,$.startTime-T)}}function Ce(T,$){G=!1,H&&(H=!1,le(Ze),Ze=-1),re=!0;var D=W;try{for(ee($),R=a(_);R!==null&&(!(R.expirationTime>$)||T&&!Zt());){var h=R.callback;if(typeof h=="function"){R.callback=null,W=R.priorityLevel;var E=h(R.expirationTime<=$);$=o.unstable_now(),typeof E=="function"?R.callback=E:R===a(_)&&p(_),ee($)}else p(_);R=a(_)}if(R!==null)var K=!0;else{var X=a(z);X!==null&&me(ie,X.startTime-$),K=!1}return K}finally{R=null,W=D,re=!1}}var Me=!1,Fe=null,Ze=-1,Rt=5,gt=-1;function Zt(){return!(o.unstable_now()-gtT||125h?(T.sortIndex=D,c(z,T),a(_)===null&&T===a(z)&&(H?(le(Ze),Ze=-1):H=!0,me(ie,D-h))):(T.sortIndex=E,c(_,T),G||re||(G=!0,Ue(Ce))),T},o.unstable_shouldYield=Zt,o.unstable_wrapCallback=function(T){var $=W;return function(){var D=W;W=$;try{return T.apply(this,arguments)}finally{W=D}}}})(Fi)),Fi}var Ws;function yd(){return Ws||(Ws=1,Di.exports=vd()),Di.exports}/** * @license React * react-dom.production.min.js * @@ -22,15 +22,15 @@ function cd(o,c){for(var a=0;a"u"||typeof window.document>"u"||typeof window.document.createElement>"u"),x=Object.prototype.hasOwnProperty,z=/^[:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD][:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\-.0-9\u00B7\u0300-\u036F\u203F-\u2040]*$/,B={},R={};function W(e){return x.call(R,e)?!0:x.call(B,e)?!1:z.test(e)?R[e]=!0:(B[e]=!0,!1)}function re(e,t,n,r){if(n!==null&&n.type===0)return!1;switch(typeof t){case"function":case"symbol":return!0;case"boolean":return r?!1:n!==null?!n.acceptsBooleans:(e=e.toLowerCase().slice(0,5),e!=="data-"&&e!=="aria-");default:return!1}}function G(e,t,n,r){if(t===null||typeof t>"u"||re(e,t,n,r))return!0;if(r)return!1;if(n!==null)switch(n.type){case 3:return!t;case 4:return t===!1;case 5:return isNaN(t);case 6:return isNaN(t)||1>t}return!1}function H(e,t,n,r,l,u,i){this.acceptsBooleans=t===2||t===3||t===4,this.attributeName=r,this.attributeNamespace=l,this.mustUseProperty=n,this.propertyName=e,this.type=t,this.sanitizeURL=u,this.removeEmptyString=i}var L={};"children dangerouslySetInnerHTML defaultValue defaultChecked innerHTML suppressContentEditableWarning suppressHydrationWarning style".split(" ").forEach(function(e){L[e]=new H(e,0,!1,e,null,!1,!1)}),[["acceptCharset","accept-charset"],["className","class"],["htmlFor","for"],["httpEquiv","http-equiv"]].forEach(function(e){var t=e[0];L[t]=new H(t,1,!1,e[1],null,!1,!1)}),["contentEditable","draggable","spellCheck","value"].forEach(function(e){L[e]=new H(e,2,!1,e.toLowerCase(),null,!1,!1)}),["autoReverse","externalResourcesRequired","focusable","preserveAlpha"].forEach(function(e){L[e]=new H(e,2,!1,e,null,!1,!1)}),"allowFullScreen async autoFocus autoPlay controls default defer disabled disablePictureInPicture disableRemotePlayback formNoValidate hidden loop noModule noValidate open playsInline readOnly required reversed scoped seamless itemScope".split(" ").forEach(function(e){L[e]=new H(e,3,!1,e.toLowerCase(),null,!1,!1)}),["checked","multiple","muted","selected"].forEach(function(e){L[e]=new H(e,3,!0,e,null,!1,!1)}),["capture","download"].forEach(function(e){L[e]=new H(e,4,!1,e,null,!1,!1)}),["cols","rows","size","span"].forEach(function(e){L[e]=new H(e,6,!1,e,null,!1,!1)}),["rowSpan","start"].forEach(function(e){L[e]=new H(e,5,!1,e.toLowerCase(),null,!1,!1)});var le=/[\-:]([a-z])/g;function ue(e){return e[1].toUpperCase()}"accent-height alignment-baseline arabic-form baseline-shift cap-height clip-path clip-rule color-interpolation color-interpolation-filters color-profile color-rendering dominant-baseline enable-background fill-opacity fill-rule flood-color flood-opacity font-family font-size font-size-adjust font-stretch font-style font-variant font-weight glyph-name glyph-orientation-horizontal glyph-orientation-vertical horiz-adv-x horiz-origin-x image-rendering letter-spacing lighting-color marker-end marker-mid marker-start overline-position overline-thickness paint-order panose-1 pointer-events rendering-intent shape-rendering stop-color stop-opacity strikethrough-position strikethrough-thickness stroke-dasharray stroke-dashoffset stroke-linecap stroke-linejoin stroke-miterlimit stroke-opacity stroke-width text-anchor text-decoration text-rendering underline-position underline-thickness unicode-bidi unicode-range units-per-em v-alphabetic v-hanging v-ideographic v-mathematical vector-effect vert-adv-y vert-origin-x vert-origin-y word-spacing writing-mode xmlns:xlink x-height".split(" ").forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,null,!1,!1)}),"xlink:actuate xlink:arcrole xlink:role xlink:show xlink:title xlink:type".split(" ").forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,"http://www.w3.org/1999/xlink",!1,!1)}),["xml:base","xml:lang","xml:space"].forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,"http://www.w3.org/XML/1998/namespace",!1,!1)}),["tabIndex","crossOrigin"].forEach(function(e){L[e]=new H(e,1,!1,e.toLowerCase(),null,!1,!1)}),L.xlinkHref=new H("xlinkHref",1,!1,"xlink:href","http://www.w3.org/1999/xlink",!0,!1),["src","href","action","formAction"].forEach(function(e){L[e]=new H(e,1,!1,e.toLowerCase(),null,!0,!0)});function ee(e,t,n,r){var l=L.hasOwnProperty(t)?L[t]:null;(l!==null?l.type!==0:r||!(2"u"||typeof window.document>"u"||typeof window.document.createElement>"u"),_=Object.prototype.hasOwnProperty,z=/^[:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD][:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\-.0-9\u00B7\u0300-\u036F\u203F-\u2040]*$/,B={},R={};function W(e){return _.call(R,e)?!0:_.call(B,e)?!1:z.test(e)?R[e]=!0:(B[e]=!0,!1)}function re(e,t,n,r){if(n!==null&&n.type===0)return!1;switch(typeof t){case"function":case"symbol":return!0;case"boolean":return r?!1:n!==null?!n.acceptsBooleans:(e=e.toLowerCase().slice(0,5),e!=="data-"&&e!=="aria-");default:return!1}}function G(e,t,n,r){if(t===null||typeof t>"u"||re(e,t,n,r))return!0;if(r)return!1;if(n!==null)switch(n.type){case 3:return!t;case 4:return t===!1;case 5:return isNaN(t);case 6:return isNaN(t)||1>t}return!1}function H(e,t,n,r,l,u,i){this.acceptsBooleans=t===2||t===3||t===4,this.attributeName=r,this.attributeNamespace=l,this.mustUseProperty=n,this.propertyName=e,this.type=t,this.sanitizeURL=u,this.removeEmptyString=i}var L={};"children dangerouslySetInnerHTML defaultValue defaultChecked innerHTML suppressContentEditableWarning suppressHydrationWarning style".split(" ").forEach(function(e){L[e]=new H(e,0,!1,e,null,!1,!1)}),[["acceptCharset","accept-charset"],["className","class"],["htmlFor","for"],["httpEquiv","http-equiv"]].forEach(function(e){var t=e[0];L[t]=new H(t,1,!1,e[1],null,!1,!1)}),["contentEditable","draggable","spellCheck","value"].forEach(function(e){L[e]=new H(e,2,!1,e.toLowerCase(),null,!1,!1)}),["autoReverse","externalResourcesRequired","focusable","preserveAlpha"].forEach(function(e){L[e]=new H(e,2,!1,e,null,!1,!1)}),"allowFullScreen async autoFocus autoPlay controls default defer disabled disablePictureInPicture disableRemotePlayback formNoValidate hidden loop noModule noValidate open playsInline readOnly required reversed scoped seamless itemScope".split(" ").forEach(function(e){L[e]=new H(e,3,!1,e.toLowerCase(),null,!1,!1)}),["checked","multiple","muted","selected"].forEach(function(e){L[e]=new H(e,3,!0,e,null,!1,!1)}),["capture","download"].forEach(function(e){L[e]=new H(e,4,!1,e,null,!1,!1)}),["cols","rows","size","span"].forEach(function(e){L[e]=new H(e,6,!1,e,null,!1,!1)}),["rowSpan","start"].forEach(function(e){L[e]=new H(e,5,!1,e.toLowerCase(),null,!1,!1)});var le=/[\-:]([a-z])/g;function ue(e){return e[1].toUpperCase()}"accent-height alignment-baseline arabic-form baseline-shift cap-height clip-path clip-rule color-interpolation color-interpolation-filters color-profile color-rendering dominant-baseline enable-background fill-opacity fill-rule flood-color flood-opacity font-family font-size font-size-adjust font-stretch font-style font-variant font-weight glyph-name glyph-orientation-horizontal glyph-orientation-vertical horiz-adv-x horiz-origin-x image-rendering letter-spacing lighting-color marker-end marker-mid marker-start overline-position overline-thickness paint-order panose-1 pointer-events rendering-intent shape-rendering stop-color stop-opacity strikethrough-position strikethrough-thickness stroke-dasharray stroke-dashoffset stroke-linecap stroke-linejoin stroke-miterlimit stroke-opacity stroke-width text-anchor text-decoration text-rendering underline-position underline-thickness unicode-bidi unicode-range units-per-em v-alphabetic v-hanging v-ideographic v-mathematical vector-effect vert-adv-y vert-origin-x vert-origin-y word-spacing writing-mode xmlns:xlink x-height".split(" ").forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,null,!1,!1)}),"xlink:actuate xlink:arcrole xlink:role xlink:show xlink:title xlink:type".split(" ").forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,"http://www.w3.org/1999/xlink",!1,!1)}),["xml:base","xml:lang","xml:space"].forEach(function(e){var t=e.replace(le,ue);L[t]=new H(t,1,!1,e,"http://www.w3.org/XML/1998/namespace",!1,!1)}),["tabIndex","crossOrigin"].forEach(function(e){L[e]=new H(e,1,!1,e.toLowerCase(),null,!1,!1)}),L.xlinkHref=new H("xlinkHref",1,!1,"xlink:href","http://www.w3.org/1999/xlink",!0,!1),["src","href","action","formAction"].forEach(function(e){L[e]=new H(e,1,!1,e.toLowerCase(),null,!0,!0)});function ee(e,t,n,r){var l=L.hasOwnProperty(t)?L[t]:null;(l!==null?l.type!==0:r||!(2s||l[i]!==u[s]){var f=` -`+l[i].replace(" at new "," at ");return e.displayName&&f.includes("")&&(f=f.replace("",e.displayName)),f}while(1<=i&&0<=s);break}}}finally{K=!1,Error.prepareStackTrace=n}return(e=e?e.displayName||e.name:"")?E(e):""}function J(e){switch(e.tag){case 5:return E(e.type);case 16:return E("Lazy");case 13:return E("Suspense");case 19:return E("SuspenseList");case 0:case 2:case 15:return e=X(e.type,!1),e;case 11:return e=X(e.type.render,!1),e;case 1:return e=X(e.type,!0),e;default:return""}}function q(e){if(e==null)return null;if(typeof e=="function")return e.displayName||e.name||null;if(typeof e=="string")return e;switch(e){case Fe:return"Fragment";case Me:return"Portal";case Rt:return"Profiler";case Ze:return"StrictMode";case $e:return"Suspense";case rt:return"SuspenseList"}if(typeof e=="object")switch(e.$$typeof){case Zt:return(e.displayName||"Context")+".Consumer";case gt:return(e._context.displayName||"Context")+".Provider";case ft:var t=e.render;return e=e.displayName,e||(e=t.displayName||t.name||"",e=e!==""?"ForwardRef("+e+")":"ForwardRef"),e;case dt:return t=e.displayName||null,t!==null?t:q(e.type)||"Memo";case Ue:t=e._payload,e=e._init;try{return q(e(t))}catch{}}return null}function oe(e){var t=e.type;switch(e.tag){case 24:return"Cache";case 9:return(t.displayName||"Context")+".Consumer";case 10:return(t._context.displayName||"Context")+".Provider";case 18:return"DehydratedFragment";case 11:return e=t.render,e=e.displayName||e.name||"",t.displayName||(e!==""?"ForwardRef("+e+")":"ForwardRef");case 7:return"Fragment";case 5:return t;case 4:return"Portal";case 3:return"Root";case 6:return"Text";case 16:return q(t);case 8:return t===Ze?"StrictMode":"Mode";case 22:return"Offscreen";case 12:return"Profiler";case 21:return"Scope";case 13:return"Suspense";case 19:return"SuspenseList";case 25:return"TracingMarker";case 1:case 0:case 17:case 2:case 14:case 15:if(typeof t=="function")return t.displayName||t.name||null;if(typeof t=="string")return t}return null}function te(e){switch(typeof e){case"boolean":case"number":case"string":case"undefined":return e;case"object":return e;default:return""}}function fe(e){var t=e.type;return(e=e.nodeName)&&e.toLowerCase()==="input"&&(t==="checkbox"||t==="radio")}function Qe(e){var t=fe(e)?"checked":"value",n=Object.getOwnPropertyDescriptor(e.constructor.prototype,t),r=""+e[t];if(!e.hasOwnProperty(t)&&typeof n<"u"&&typeof n.get=="function"&&typeof n.set=="function"){var l=n.get,u=n.set;return Object.defineProperty(e,t,{configurable:!0,get:function(){return l.call(this)},set:function(i){r=""+i,u.call(this,i)}}),Object.defineProperty(e,t,{enumerable:n.enumerable}),{getValue:function(){return r},setValue:function(i){r=""+i},stopTracking:function(){e._valueTracker=null,delete e[t]}}}}function Nr(e){e._valueTracker||(e._valueTracker=Qe(e))}function $i(e){if(!e)return!1;var t=e._valueTracker;if(!t)return!0;var n=t.getValue(),r="";return e&&(r=fe(e)?e.checked?"true":"false":e.value),e=r,e!==n?(t.setValue(e),!0):!1}function Rr(e){if(e=e||(typeof document<"u"?document:void 0),typeof e>"u")return null;try{return e.activeElement||e.body}catch{return e.body}}function Al(e,t){var n=t.checked;return D({},t,{defaultChecked:void 0,defaultValue:void 0,value:void 0,checked:n??e._wrapperState.initialChecked})}function Qi(e,t){var n=t.defaultValue==null?"":t.defaultValue,r=t.checked!=null?t.checked:t.defaultChecked;n=te(t.value!=null?t.value:n),e._wrapperState={initialChecked:r,initialValue:n,controlled:t.type==="checkbox"||t.type==="radio"?t.checked!=null:t.value!=null}}function Ki(e,t){t=t.checked,t!=null&&ee(e,"checked",t,!1)}function Vl(e,t){Ki(e,t);var n=te(t.value),r=t.type;if(n!=null)r==="number"?(n===0&&e.value===""||e.value!=n)&&(e.value=""+n):e.value!==""+n&&(e.value=""+n);else if(r==="submit"||r==="reset"){e.removeAttribute("value");return}t.hasOwnProperty("value")?Wl(e,t.type,n):t.hasOwnProperty("defaultValue")&&Wl(e,t.type,te(t.defaultValue)),t.checked==null&&t.defaultChecked!=null&&(e.defaultChecked=!!t.defaultChecked)}function Yi(e,t,n){if(t.hasOwnProperty("value")||t.hasOwnProperty("defaultValue")){var r=t.type;if(!(r!=="submit"&&r!=="reset"||t.value!==void 0&&t.value!==null))return;t=""+e._wrapperState.initialValue,n||t===e.value||(e.value=t),e.defaultValue=t}n=e.name,n!==""&&(e.name=""),e.defaultChecked=!!e._wrapperState.initialChecked,n!==""&&(e.name=n)}function Wl(e,t,n){(t!=="number"||Rr(e.ownerDocument)!==e)&&(n==null?e.defaultValue=""+e._wrapperState.initialValue:e.defaultValue!==""+n&&(e.defaultValue=""+n))}var jn=Array.isArray;function pn(e,t,n,r){if(e=e.options,t){t={};for(var l=0;l"+t.valueOf().toString()+"",t=zr.firstChild;e.firstChild;)e.removeChild(e.firstChild);for(;t.firstChild;)e.appendChild(t.firstChild)}});function Bn(e,t){if(t){var n=e.firstChild;if(n&&n===e.lastChild&&n.nodeType===3){n.nodeValue=t;return}}e.textContent=t}var An={animationIterationCount:!0,aspectRatio:!0,borderImageOutset:!0,borderImageSlice:!0,borderImageWidth:!0,boxFlex:!0,boxFlexGroup:!0,boxOrdinalGroup:!0,columnCount:!0,columns:!0,flex:!0,flexGrow:!0,flexPositive:!0,flexShrink:!0,flexNegative:!0,flexOrder:!0,gridArea:!0,gridRow:!0,gridRowEnd:!0,gridRowSpan:!0,gridRowStart:!0,gridColumn:!0,gridColumnEnd:!0,gridColumnSpan:!0,gridColumnStart:!0,fontWeight:!0,lineClamp:!0,lineHeight:!0,opacity:!0,order:!0,orphans:!0,tabSize:!0,widows:!0,zIndex:!0,zoom:!0,fillOpacity:!0,floodOpacity:!0,stopOpacity:!0,strokeDasharray:!0,strokeDashoffset:!0,strokeMiterlimit:!0,strokeOpacity:!0,strokeWidth:!0},pc=["Webkit","ms","Moz","O"];Object.keys(An).forEach(function(e){pc.forEach(function(t){t=t+e.charAt(0).toUpperCase()+e.substring(1),An[t]=An[e]})});function bi(e,t,n){return t==null||typeof t=="boolean"||t===""?"":n||typeof t!="number"||t===0||An.hasOwnProperty(e)&&An[e]?(""+t).trim():t+"px"}function eo(e,t){e=e.style;for(var n in t)if(t.hasOwnProperty(n)){var r=n.indexOf("--")===0,l=bi(n,t[n],r);n==="float"&&(n="cssFloat"),r?e.setProperty(n,l):e[n]=l}}var hc=D({menuitem:!0},{area:!0,base:!0,br:!0,col:!0,embed:!0,hr:!0,img:!0,input:!0,keygen:!0,link:!0,meta:!0,param:!0,source:!0,track:!0,wbr:!0});function Ql(e,t){if(t){if(hc[e]&&(t.children!=null||t.dangerouslySetInnerHTML!=null))throw Error(a(137,e));if(t.dangerouslySetInnerHTML!=null){if(t.children!=null)throw Error(a(60));if(typeof t.dangerouslySetInnerHTML!="object"||!("__html"in t.dangerouslySetInnerHTML))throw Error(a(61))}if(t.style!=null&&typeof t.style!="object")throw Error(a(62))}}function Kl(e,t){if(e.indexOf("-")===-1)return typeof t.is=="string";switch(e){case"annotation-xml":case"color-profile":case"font-face":case"font-face-src":case"font-face-uri":case"font-face-format":case"font-face-name":case"missing-glyph":return!1;default:return!0}}var Yl=null;function Xl(e){return e=e.target||e.srcElement||window,e.correspondingUseElement&&(e=e.correspondingUseElement),e.nodeType===3?e.parentNode:e}var Gl=null,hn=null,mn=null;function to(e){if(e=ar(e)){if(typeof Gl!="function")throw Error(a(280));var t=e.stateNode;t&&(t=qr(t),Gl(e.stateNode,e.type,t))}}function no(e){hn?mn?mn.push(e):mn=[e]:hn=e}function ro(){if(hn){var e=hn,t=mn;if(mn=hn=null,to(e),t)for(e=0;e>>=0,e===0?32:31-(_c(e)/Pc|0)|0}var Ir=64,Dr=4194304;function $n(e){switch(e&-e){case 1:return 1;case 2:return 2;case 4:return 4;case 8:return 8;case 16:return 16;case 32:return 32;case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:return e&4194240;case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:return e&130023424;case 134217728:return 134217728;case 268435456:return 268435456;case 536870912:return 536870912;case 1073741824:return 1073741824;default:return e}}function Fr(e,t){var n=e.pendingLanes;if(n===0)return 0;var r=0,l=e.suspendedLanes,u=e.pingedLanes,i=n&268435455;if(i!==0){var s=i&~l;s!==0?r=$n(s):(u&=i,u!==0&&(r=$n(u)))}else i=n&~l,i!==0?r=$n(i):u!==0&&(r=$n(u));if(r===0)return 0;if(t!==0&&t!==r&&(t&l)===0&&(l=r&-r,u=t&-t,l>=u||l===16&&(u&4194240)!==0))return t;if((r&4)!==0&&(r|=n&16),t=e.entangledLanes,t!==0)for(e=e.entanglements,t&=r;0n;n++)t.push(e);return t}function Qn(e,t,n){e.pendingLanes|=t,t!==536870912&&(e.suspendedLanes=0,e.pingedLanes=0),e=e.eventTimes,t=31-lt(t),e[t]=n}function Lc(e,t){var n=e.pendingLanes&~t;e.pendingLanes=t,e.suspendedLanes=0,e.pingedLanes=0,e.expiredLanes&=t,e.mutableReadLanes&=t,e.entangledLanes&=t,t=e.entanglements;var r=e.eventTimes;for(e=e.expirationTimes;0=bn),Oo=" ",Mo=!1;function Io(e,t){switch(e){case"keyup":return lf.indexOf(t.keyCode)!==-1;case"keydown":return t.keyCode!==229;case"keypress":case"mousedown":case"focusout":return!0;default:return!1}}function Do(e){return e=e.detail,typeof e=="object"&&"data"in e?e.data:null}var gn=!1;function of(e,t){switch(e){case"compositionend":return Do(t);case"keypress":return t.which!==32?null:(Mo=!0,Oo);case"textInput":return e=t.data,e===Oo&&Mo?null:e;default:return null}}function af(e,t){if(gn)return e==="compositionend"||!pu&&Io(e,t)?(e=Po(),Vr=ou=Mt=null,gn=!1,e):null;switch(e){case"paste":return null;case"keypress":if(!(t.ctrlKey||t.altKey||t.metaKey)||t.ctrlKey&&t.altKey){if(t.char&&1=t)return{node:n,offset:t-e};e=r}e:{for(;n;){if(n.nextSibling){n=n.nextSibling;break e}n=n.parentNode}n=void 0}n=Wo(n)}}function $o(e,t){return e&&t?e===t?!0:e&&e.nodeType===3?!1:t&&t.nodeType===3?$o(e,t.parentNode):"contains"in e?e.contains(t):e.compareDocumentPosition?!!(e.compareDocumentPosition(t)&16):!1:!1}function Qo(){for(var e=window,t=Rr();t instanceof e.HTMLIFrameElement;){try{var n=typeof t.contentWindow.location.href=="string"}catch{n=!1}if(n)e=t.contentWindow;else break;t=Rr(e.document)}return t}function vu(e){var t=e&&e.nodeName&&e.nodeName.toLowerCase();return t&&(t==="input"&&(e.type==="text"||e.type==="search"||e.type==="tel"||e.type==="url"||e.type==="password")||t==="textarea"||e.contentEditable==="true")}function yf(e){var t=Qo(),n=e.focusedElem,r=e.selectionRange;if(t!==n&&n&&n.ownerDocument&&$o(n.ownerDocument.documentElement,n)){if(r!==null&&vu(n)){if(t=r.start,e=r.end,e===void 0&&(e=t),"selectionStart"in n)n.selectionStart=t,n.selectionEnd=Math.min(e,n.value.length);else if(e=(t=n.ownerDocument||document)&&t.defaultView||window,e.getSelection){e=e.getSelection();var l=n.textContent.length,u=Math.min(r.start,l);r=r.end===void 0?u:Math.min(r.end,l),!e.extend&&u>r&&(l=r,r=u,u=l),l=Ho(n,u);var i=Ho(n,r);l&&i&&(e.rangeCount!==1||e.anchorNode!==l.node||e.anchorOffset!==l.offset||e.focusNode!==i.node||e.focusOffset!==i.offset)&&(t=t.createRange(),t.setStart(l.node,l.offset),e.removeAllRanges(),u>r?(e.addRange(t),e.extend(i.node,i.offset)):(t.setEnd(i.node,i.offset),e.addRange(t)))}}for(t=[],e=n;e=e.parentNode;)e.nodeType===1&&t.push({element:e,left:e.scrollLeft,top:e.scrollTop});for(typeof n.focus=="function"&&n.focus(),n=0;n=document.documentMode,wn=null,yu=null,rr=null,gu=!1;function Ko(e,t,n){var r=n.window===n?n.document:n.nodeType===9?n:n.ownerDocument;gu||wn==null||wn!==Rr(r)||(r=wn,"selectionStart"in r&&vu(r)?r={start:r.selectionStart,end:r.selectionEnd}:(r=(r.ownerDocument&&r.ownerDocument.defaultView||window).getSelection(),r={anchorNode:r.anchorNode,anchorOffset:r.anchorOffset,focusNode:r.focusNode,focusOffset:r.focusOffset}),rr&&nr(rr,r)||(rr=r,r=Gr(yu,"onSelect"),0xn||(e.current=Lu[xn],Lu[xn]=null,xn--)}function ae(e,t){xn++,Lu[xn]=e.current,e.current=t}var Ut={},ze=Ft(Ut),je=Ft(!1),bt=Ut;function _n(e,t){var n=e.type.contextTypes;if(!n)return Ut;var r=e.stateNode;if(r&&r.__reactInternalMemoizedUnmaskedChildContext===t)return r.__reactInternalMemoizedMaskedChildContext;var l={},u;for(u in n)l[u]=t[u];return r&&(e=e.stateNode,e.__reactInternalMemoizedUnmaskedChildContext=t,e.__reactInternalMemoizedMaskedChildContext=l),l}function Be(e){return e=e.childContextTypes,e!=null}function br(){ce(je),ce(ze)}function oa(e,t,n){if(ze.current!==Ut)throw Error(a(168));ae(ze,t),ae(je,n)}function aa(e,t,n){var r=e.stateNode;if(t=t.childContextTypes,typeof r.getChildContext!="function")return n;r=r.getChildContext();for(var l in r)if(!(l in t))throw Error(a(108,oe(e)||"Unknown",l));return D({},n,r)}function el(e){return e=(e=e.stateNode)&&e.__reactInternalMemoizedMergedChildContext||Ut,bt=ze.current,ae(ze,e),ae(je,je.current),!0}function sa(e,t,n){var r=e.stateNode;if(!r)throw Error(a(169));n?(e=aa(e,t,bt),r.__reactInternalMemoizedMergedChildContext=e,ce(je),ce(ze),ae(ze,e)):ce(je),ae(je,n)}var St=null,tl=!1,Tu=!1;function ca(e){St===null?St=[e]:St.push(e)}function zf(e){tl=!0,ca(e)}function jt(){if(!Tu&&St!==null){Tu=!0;var e=0,t=ne;try{var n=St;for(ne=1;e>=i,l-=i,kt=1<<32-lt(t)+l|n<Q?(Pe=V,V=null):Pe=V.sibling;var b=k(m,V,v[Q],P);if(b===null){V===null&&(V=Pe);break}e&&V&&b.alternate===null&&t(m,V),d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b,V=Pe}if(Q===v.length)return n(m,V),de&&tn(m,Q),j;if(V===null){for(;QQ?(Pe=V,V=null):Pe=V.sibling;var Yt=k(m,V,b.value,P);if(Yt===null){V===null&&(V=Pe);break}e&&V&&Yt.alternate===null&&t(m,V),d=u(Yt,d,Q),A===null?j=Yt:A.sibling=Yt,A=Yt,V=Pe}if(b.done)return n(m,V),de&&tn(m,Q),j;if(V===null){for(;!b.done;Q++,b=v.next())b=_(m,b.value,P),b!==null&&(d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b);return de&&tn(m,Q),j}for(V=r(m,V);!b.done;Q++,b=v.next())b=O(V,m,Q,b.value,P),b!==null&&(e&&b.alternate!==null&&V.delete(b.key===null?Q:b.key),d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b);return e&&V.forEach(function(sd){return t(m,sd)}),de&&tn(m,Q),j}function ge(m,d,v,P){if(typeof v=="object"&&v!==null&&v.type===Fe&&v.key===null&&(v=v.props.children),typeof v=="object"&&v!==null){switch(v.$$typeof){case Ce:e:{for(var j=v.key,A=d;A!==null;){if(A.key===j){if(j=v.type,j===Fe){if(A.tag===7){n(m,A.sibling),d=l(A,v.props.children),d.return=m,m=d;break e}}else if(A.elementType===j||typeof j=="object"&&j!==null&&j.$$typeof===Ue&&va(j)===A.type){n(m,A.sibling),d=l(A,v.props),d.ref=sr(m,A,v),d.return=m,m=d;break e}n(m,A);break}else t(m,A);A=A.sibling}v.type===Fe?(d=cn(v.props.children,m.mode,P,v.key),d.return=m,m=d):(P=zl(v.type,v.key,v.props,null,m.mode,P),P.ref=sr(m,d,v),P.return=m,m=P)}return i(m);case Me:e:{for(A=v.key;d!==null;){if(d.key===A)if(d.tag===4&&d.stateNode.containerInfo===v.containerInfo&&d.stateNode.implementation===v.implementation){n(m,d.sibling),d=l(d,v.children||[]),d.return=m,m=d;break e}else{n(m,d);break}else t(m,d);d=d.sibling}d=Ri(v,m.mode,P),d.return=m,m=d}return i(m);case Ue:return A=v._init,ge(m,d,A(v._payload),P)}if(jn(v))return F(m,d,v,P);if($(v))return U(m,d,v,P);ul(m,v)}return typeof v=="string"&&v!==""||typeof v=="number"?(v=""+v,d!==null&&d.tag===6?(n(m,d.sibling),d=l(d,v),d.return=m,m=d):(n(m,d),d=Ni(v,m.mode,P),d.return=m,m=d),i(m)):n(m,d)}return ge}var zn=ya(!0),ga=ya(!1),il=Ft(null),ol=null,Ln=null,Uu=null;function ju(){Uu=Ln=ol=null}function Bu(e){var t=il.current;ce(il),e._currentValue=t}function Au(e,t,n){for(;e!==null;){var r=e.alternate;if((e.childLanes&t)!==t?(e.childLanes|=t,r!==null&&(r.childLanes|=t)):r!==null&&(r.childLanes&t)!==t&&(r.childLanes|=t),e===n)break;e=e.return}}function Tn(e,t){ol=e,Uu=Ln=null,e=e.dependencies,e!==null&&e.firstContext!==null&&((e.lanes&t)!==0&&(Ae=!0),e.firstContext=null)}function be(e){var t=e._currentValue;if(Uu!==e)if(e={context:e,memoizedValue:t,next:null},Ln===null){if(ol===null)throw Error(a(308));Ln=e,ol.dependencies={lanes:0,firstContext:e}}else Ln=Ln.next=e;return t}var nn=null;function Vu(e){nn===null?nn=[e]:nn.push(e)}function wa(e,t,n,r){var l=t.interleaved;return l===null?(n.next=n,Vu(t)):(n.next=l.next,l.next=n),t.interleaved=n,Ct(e,r)}function Ct(e,t){e.lanes|=t;var n=e.alternate;for(n!==null&&(n.lanes|=t),n=e,e=e.return;e!==null;)e.childLanes|=t,n=e.alternate,n!==null&&(n.childLanes|=t),n=e,e=e.return;return n.tag===3?n.stateNode:null}var Bt=!1;function Wu(e){e.updateQueue={baseState:e.memoizedState,firstBaseUpdate:null,lastBaseUpdate:null,shared:{pending:null,interleaved:null,lanes:0},effects:null}}function Sa(e,t){e=e.updateQueue,t.updateQueue===e&&(t.updateQueue={baseState:e.baseState,firstBaseUpdate:e.firstBaseUpdate,lastBaseUpdate:e.lastBaseUpdate,shared:e.shared,effects:e.effects})}function xt(e,t){return{eventTime:e,lane:t,tag:0,payload:null,callback:null,next:null}}function At(e,t,n){var r=e.updateQueue;if(r===null)return null;if(r=r.shared,(Z&2)!==0){var l=r.pending;return l===null?t.next=t:(t.next=l.next,l.next=t),r.pending=t,Ct(e,n)}return l=r.interleaved,l===null?(t.next=t,Vu(r)):(t.next=l.next,l.next=t),r.interleaved=t,Ct(e,n)}function al(e,t,n){if(t=t.updateQueue,t!==null&&(t=t.shared,(n&4194240)!==0)){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,nu(e,n)}}function ka(e,t){var n=e.updateQueue,r=e.alternate;if(r!==null&&(r=r.updateQueue,n===r)){var l=null,u=null;if(n=n.firstBaseUpdate,n!==null){do{var i={eventTime:n.eventTime,lane:n.lane,tag:n.tag,payload:n.payload,callback:n.callback,next:null};u===null?l=u=i:u=u.next=i,n=n.next}while(n!==null);u===null?l=u=t:u=u.next=t}else l=u=t;n={baseState:r.baseState,firstBaseUpdate:l,lastBaseUpdate:u,shared:r.shared,effects:r.effects},e.updateQueue=n;return}e=n.lastBaseUpdate,e===null?n.firstBaseUpdate=t:e.next=t,n.lastBaseUpdate=t}function sl(e,t,n,r){var l=e.updateQueue;Bt=!1;var u=l.firstBaseUpdate,i=l.lastBaseUpdate,s=l.shared.pending;if(s!==null){l.shared.pending=null;var f=s,y=f.next;f.next=null,i===null?u=y:i.next=y,i=f;var C=e.alternate;C!==null&&(C=C.updateQueue,s=C.lastBaseUpdate,s!==i&&(s===null?C.firstBaseUpdate=y:s.next=y,C.lastBaseUpdate=f))}if(u!==null){var _=l.baseState;i=0,C=y=f=null,s=u;do{var k=s.lane,O=s.eventTime;if((r&k)===k){C!==null&&(C=C.next={eventTime:O,lane:0,tag:s.tag,payload:s.payload,callback:s.callback,next:null});e:{var F=e,U=s;switch(k=t,O=n,U.tag){case 1:if(F=U.payload,typeof F=="function"){_=F.call(O,_,k);break e}_=F;break e;case 3:F.flags=F.flags&-65537|128;case 0:if(F=U.payload,k=typeof F=="function"?F.call(O,_,k):F,k==null)break e;_=D({},_,k);break e;case 2:Bt=!0}}s.callback!==null&&s.lane!==0&&(e.flags|=64,k=l.effects,k===null?l.effects=[s]:k.push(s))}else O={eventTime:O,lane:k,tag:s.tag,payload:s.payload,callback:s.callback,next:null},C===null?(y=C=O,f=_):C=C.next=O,i|=k;if(s=s.next,s===null){if(s=l.shared.pending,s===null)break;k=s,s=k.next,k.next=null,l.lastBaseUpdate=k,l.shared.pending=null}}while(!0);if(C===null&&(f=_),l.baseState=f,l.firstBaseUpdate=y,l.lastBaseUpdate=C,t=l.shared.interleaved,t!==null){l=t;do i|=l.lane,l=l.next;while(l!==t)}else u===null&&(l.shared.lanes=0);un|=i,e.lanes=i,e.memoizedState=_}}function Ea(e,t,n){if(e=t.effects,t.effects=null,e!==null)for(t=0;tn?n:4,e(!0);var r=Yu.transition;Yu.transition={};try{e(!1),t()}finally{ne=n,Yu.transition=r}}function Va(){return et().memoizedState}function Mf(e,t,n){var r=$t(e);if(n={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null},Wa(e))Ha(t,n);else if(n=wa(e,t,n,r),n!==null){var l=De();ct(n,e,r,l),$a(n,t,r)}}function If(e,t,n){var r=$t(e),l={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null};if(Wa(e))Ha(t,l);else{var u=e.alternate;if(e.lanes===0&&(u===null||u.lanes===0)&&(u=t.lastRenderedReducer,u!==null))try{var i=t.lastRenderedState,s=u(i,n);if(l.hasEagerState=!0,l.eagerState=s,ut(s,i)){var f=t.interleaved;f===null?(l.next=l,Vu(t)):(l.next=f.next,f.next=l),t.interleaved=l;return}}catch{}finally{}n=wa(e,t,l,r),n!==null&&(l=De(),ct(n,e,r,l),$a(n,t,r))}}function Wa(e){var t=e.alternate;return e===he||t!==null&&t===he}function Ha(e,t){pr=dl=!0;var n=e.pending;n===null?t.next=t:(t.next=n.next,n.next=t),e.pending=t}function $a(e,t,n){if((n&4194240)!==0){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,nu(e,n)}}var ml={readContext:be,useCallback:Le,useContext:Le,useEffect:Le,useImperativeHandle:Le,useInsertionEffect:Le,useLayoutEffect:Le,useMemo:Le,useReducer:Le,useRef:Le,useState:Le,useDebugValue:Le,useDeferredValue:Le,useTransition:Le,useMutableSource:Le,useSyncExternalStore:Le,useId:Le,unstable_isNewReconciler:!1},Df={readContext:be,useCallback:function(e,t){return vt().memoizedState=[e,t===void 0?null:t],e},useContext:be,useEffect:Ma,useImperativeHandle:function(e,t,n){return n=n!=null?n.concat([e]):null,pl(4194308,4,Fa.bind(null,t,e),n)},useLayoutEffect:function(e,t){return pl(4194308,4,e,t)},useInsertionEffect:function(e,t){return pl(4,2,e,t)},useMemo:function(e,t){var n=vt();return t=t===void 0?null:t,e=e(),n.memoizedState=[e,t],e},useReducer:function(e,t,n){var r=vt();return t=n!==void 0?n(t):t,r.memoizedState=r.baseState=t,e={pending:null,interleaved:null,lanes:0,dispatch:null,lastRenderedReducer:e,lastRenderedState:t},r.queue=e,e=e.dispatch=Mf.bind(null,he,e),[r.memoizedState,e]},useRef:function(e){var t=vt();return e={current:e},t.memoizedState=e},useState:Ta,useDebugValue:ei,useDeferredValue:function(e){return vt().memoizedState=e},useTransition:function(){var e=Ta(!1),t=e[0];return e=Of.bind(null,e[1]),vt().memoizedState=e,[t,e]},useMutableSource:function(){},useSyncExternalStore:function(e,t,n){var r=he,l=vt();if(de){if(n===void 0)throw Error(a(407));n=n()}else{if(n=t(),_e===null)throw Error(a(349));(ln&30)!==0||Pa(r,t,n)}l.memoizedState=n;var u={value:n,getSnapshot:t};return l.queue=u,Ma(Ra.bind(null,r,u,e),[e]),r.flags|=2048,vr(9,Na.bind(null,r,u,n,t),void 0,null),n},useId:function(){var e=vt(),t=_e.identifierPrefix;if(de){var n=Et,r=kt;n=(r&~(1<<32-lt(r)-1)).toString(32)+n,t=":"+t+"R"+n,n=hr++,0")&&(f=f.replace("",e.displayName)),f}while(1<=i&&0<=s);break}}}finally{K=!1,Error.prepareStackTrace=n}return(e=e?e.displayName||e.name:"")?E(e):""}function J(e){switch(e.tag){case 5:return E(e.type);case 16:return E("Lazy");case 13:return E("Suspense");case 19:return E("SuspenseList");case 0:case 2:case 15:return e=X(e.type,!1),e;case 11:return e=X(e.type.render,!1),e;case 1:return e=X(e.type,!0),e;default:return""}}function q(e){if(e==null)return null;if(typeof e=="function")return e.displayName||e.name||null;if(typeof e=="string")return e;switch(e){case Fe:return"Fragment";case Me:return"Portal";case Rt:return"Profiler";case Ze:return"StrictMode";case $e:return"Suspense";case rt:return"SuspenseList"}if(typeof e=="object")switch(e.$$typeof){case Zt:return(e.displayName||"Context")+".Consumer";case gt:return(e._context.displayName||"Context")+".Provider";case ft:var t=e.render;return e=e.displayName,e||(e=t.displayName||t.name||"",e=e!==""?"ForwardRef("+e+")":"ForwardRef"),e;case dt:return t=e.displayName||null,t!==null?t:q(e.type)||"Memo";case Ue:t=e._payload,e=e._init;try{return q(e(t))}catch{}}return null}function oe(e){var t=e.type;switch(e.tag){case 24:return"Cache";case 9:return(t.displayName||"Context")+".Consumer";case 10:return(t._context.displayName||"Context")+".Provider";case 18:return"DehydratedFragment";case 11:return e=t.render,e=e.displayName||e.name||"",t.displayName||(e!==""?"ForwardRef("+e+")":"ForwardRef");case 7:return"Fragment";case 5:return t;case 4:return"Portal";case 3:return"Root";case 6:return"Text";case 16:return q(t);case 8:return t===Ze?"StrictMode":"Mode";case 22:return"Offscreen";case 12:return"Profiler";case 21:return"Scope";case 13:return"Suspense";case 19:return"SuspenseList";case 25:return"TracingMarker";case 1:case 0:case 17:case 2:case 14:case 15:if(typeof t=="function")return t.displayName||t.name||null;if(typeof t=="string")return t}return null}function te(e){switch(typeof e){case"boolean":case"number":case"string":case"undefined":return e;case"object":return e;default:return""}}function fe(e){var t=e.type;return(e=e.nodeName)&&e.toLowerCase()==="input"&&(t==="checkbox"||t==="radio")}function Qe(e){var t=fe(e)?"checked":"value",n=Object.getOwnPropertyDescriptor(e.constructor.prototype,t),r=""+e[t];if(!e.hasOwnProperty(t)&&typeof n<"u"&&typeof n.get=="function"&&typeof n.set=="function"){var l=n.get,u=n.set;return Object.defineProperty(e,t,{configurable:!0,get:function(){return l.call(this)},set:function(i){r=""+i,u.call(this,i)}}),Object.defineProperty(e,t,{enumerable:n.enumerable}),{getValue:function(){return r},setValue:function(i){r=""+i},stopTracking:function(){e._valueTracker=null,delete e[t]}}}}function Nr(e){e._valueTracker||(e._valueTracker=Qe(e))}function $i(e){if(!e)return!1;var t=e._valueTracker;if(!t)return!0;var n=t.getValue(),r="";return e&&(r=fe(e)?e.checked?"true":"false":e.value),e=r,e!==n?(t.setValue(e),!0):!1}function Rr(e){if(e=e||(typeof document<"u"?document:void 0),typeof e>"u")return null;try{return e.activeElement||e.body}catch{return e.body}}function Al(e,t){var n=t.checked;return D({},t,{defaultChecked:void 0,defaultValue:void 0,value:void 0,checked:n??e._wrapperState.initialChecked})}function Qi(e,t){var n=t.defaultValue==null?"":t.defaultValue,r=t.checked!=null?t.checked:t.defaultChecked;n=te(t.value!=null?t.value:n),e._wrapperState={initialChecked:r,initialValue:n,controlled:t.type==="checkbox"||t.type==="radio"?t.checked!=null:t.value!=null}}function Ki(e,t){t=t.checked,t!=null&&ee(e,"checked",t,!1)}function Vl(e,t){Ki(e,t);var n=te(t.value),r=t.type;if(n!=null)r==="number"?(n===0&&e.value===""||e.value!=n)&&(e.value=""+n):e.value!==""+n&&(e.value=""+n);else if(r==="submit"||r==="reset"){e.removeAttribute("value");return}t.hasOwnProperty("value")?Wl(e,t.type,n):t.hasOwnProperty("defaultValue")&&Wl(e,t.type,te(t.defaultValue)),t.checked==null&&t.defaultChecked!=null&&(e.defaultChecked=!!t.defaultChecked)}function Yi(e,t,n){if(t.hasOwnProperty("value")||t.hasOwnProperty("defaultValue")){var r=t.type;if(!(r!=="submit"&&r!=="reset"||t.value!==void 0&&t.value!==null))return;t=""+e._wrapperState.initialValue,n||t===e.value||(e.value=t),e.defaultValue=t}n=e.name,n!==""&&(e.name=""),e.defaultChecked=!!e._wrapperState.initialChecked,n!==""&&(e.name=n)}function Wl(e,t,n){(t!=="number"||Rr(e.ownerDocument)!==e)&&(n==null?e.defaultValue=""+e._wrapperState.initialValue:e.defaultValue!==""+n&&(e.defaultValue=""+n))}var jn=Array.isArray;function pn(e,t,n,r){if(e=e.options,t){t={};for(var l=0;l"+t.valueOf().toString()+"",t=zr.firstChild;e.firstChild;)e.removeChild(e.firstChild);for(;t.firstChild;)e.appendChild(t.firstChild)}});function Bn(e,t){if(t){var n=e.firstChild;if(n&&n===e.lastChild&&n.nodeType===3){n.nodeValue=t;return}}e.textContent=t}var An={animationIterationCount:!0,aspectRatio:!0,borderImageOutset:!0,borderImageSlice:!0,borderImageWidth:!0,boxFlex:!0,boxFlexGroup:!0,boxOrdinalGroup:!0,columnCount:!0,columns:!0,flex:!0,flexGrow:!0,flexPositive:!0,flexShrink:!0,flexNegative:!0,flexOrder:!0,gridArea:!0,gridRow:!0,gridRowEnd:!0,gridRowSpan:!0,gridRowStart:!0,gridColumn:!0,gridColumnEnd:!0,gridColumnSpan:!0,gridColumnStart:!0,fontWeight:!0,lineClamp:!0,lineHeight:!0,opacity:!0,order:!0,orphans:!0,tabSize:!0,widows:!0,zIndex:!0,zoom:!0,fillOpacity:!0,floodOpacity:!0,stopOpacity:!0,strokeDasharray:!0,strokeDashoffset:!0,strokeMiterlimit:!0,strokeOpacity:!0,strokeWidth:!0},hc=["Webkit","ms","Moz","O"];Object.keys(An).forEach(function(e){hc.forEach(function(t){t=t+e.charAt(0).toUpperCase()+e.substring(1),An[t]=An[e]})});function bi(e,t,n){return t==null||typeof t=="boolean"||t===""?"":n||typeof t!="number"||t===0||An.hasOwnProperty(e)&&An[e]?(""+t).trim():t+"px"}function eo(e,t){e=e.style;for(var n in t)if(t.hasOwnProperty(n)){var r=n.indexOf("--")===0,l=bi(n,t[n],r);n==="float"&&(n="cssFloat"),r?e.setProperty(n,l):e[n]=l}}var mc=D({menuitem:!0},{area:!0,base:!0,br:!0,col:!0,embed:!0,hr:!0,img:!0,input:!0,keygen:!0,link:!0,meta:!0,param:!0,source:!0,track:!0,wbr:!0});function Ql(e,t){if(t){if(mc[e]&&(t.children!=null||t.dangerouslySetInnerHTML!=null))throw Error(a(137,e));if(t.dangerouslySetInnerHTML!=null){if(t.children!=null)throw Error(a(60));if(typeof t.dangerouslySetInnerHTML!="object"||!("__html"in t.dangerouslySetInnerHTML))throw Error(a(61))}if(t.style!=null&&typeof t.style!="object")throw Error(a(62))}}function Kl(e,t){if(e.indexOf("-")===-1)return typeof t.is=="string";switch(e){case"annotation-xml":case"color-profile":case"font-face":case"font-face-src":case"font-face-uri":case"font-face-format":case"font-face-name":case"missing-glyph":return!1;default:return!0}}var Yl=null;function Xl(e){return e=e.target||e.srcElement||window,e.correspondingUseElement&&(e=e.correspondingUseElement),e.nodeType===3?e.parentNode:e}var Gl=null,hn=null,mn=null;function to(e){if(e=ar(e)){if(typeof Gl!="function")throw Error(a(280));var t=e.stateNode;t&&(t=qr(t),Gl(e.stateNode,e.type,t))}}function no(e){hn?mn?mn.push(e):mn=[e]:hn=e}function ro(){if(hn){var e=hn,t=mn;if(mn=hn=null,to(e),t)for(e=0;e>>=0,e===0?32:31-(Pc(e)/Nc|0)|0}var Ir=64,Dr=4194304;function $n(e){switch(e&-e){case 1:return 1;case 2:return 2;case 4:return 4;case 8:return 8;case 16:return 16;case 32:return 32;case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:return e&4194240;case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:return e&130023424;case 134217728:return 134217728;case 268435456:return 268435456;case 536870912:return 536870912;case 1073741824:return 1073741824;default:return e}}function Fr(e,t){var n=e.pendingLanes;if(n===0)return 0;var r=0,l=e.suspendedLanes,u=e.pingedLanes,i=n&268435455;if(i!==0){var s=i&~l;s!==0?r=$n(s):(u&=i,u!==0&&(r=$n(u)))}else i=n&~l,i!==0?r=$n(i):u!==0&&(r=$n(u));if(r===0)return 0;if(t!==0&&t!==r&&(t&l)===0&&(l=r&-r,u=t&-t,l>=u||l===16&&(u&4194240)!==0))return t;if((r&4)!==0&&(r|=n&16),t=e.entangledLanes,t!==0)for(e=e.entanglements,t&=r;0n;n++)t.push(e);return t}function Qn(e,t,n){e.pendingLanes|=t,t!==536870912&&(e.suspendedLanes=0,e.pingedLanes=0),e=e.eventTimes,t=31-lt(t),e[t]=n}function Tc(e,t){var n=e.pendingLanes&~t;e.pendingLanes=t,e.suspendedLanes=0,e.pingedLanes=0,e.expiredLanes&=t,e.mutableReadLanes&=t,e.entangledLanes&=t,t=e.entanglements;var r=e.eventTimes;for(e=e.expirationTimes;0=bn),Oo=" ",Mo=!1;function Io(e,t){switch(e){case"keyup":return uf.indexOf(t.keyCode)!==-1;case"keydown":return t.keyCode!==229;case"keypress":case"mousedown":case"focusout":return!0;default:return!1}}function Do(e){return e=e.detail,typeof e=="object"&&"data"in e?e.data:null}var gn=!1;function af(e,t){switch(e){case"compositionend":return Do(t);case"keypress":return t.which!==32?null:(Mo=!0,Oo);case"textInput":return e=t.data,e===Oo&&Mo?null:e;default:return null}}function sf(e,t){if(gn)return e==="compositionend"||!pu&&Io(e,t)?(e=Po(),Vr=ou=Mt=null,gn=!1,e):null;switch(e){case"paste":return null;case"keypress":if(!(t.ctrlKey||t.altKey||t.metaKey)||t.ctrlKey&&t.altKey){if(t.char&&1=t)return{node:n,offset:t-e};e=r}e:{for(;n;){if(n.nextSibling){n=n.nextSibling;break e}n=n.parentNode}n=void 0}n=Wo(n)}}function $o(e,t){return e&&t?e===t?!0:e&&e.nodeType===3?!1:t&&t.nodeType===3?$o(e,t.parentNode):"contains"in e?e.contains(t):e.compareDocumentPosition?!!(e.compareDocumentPosition(t)&16):!1:!1}function Qo(){for(var e=window,t=Rr();t instanceof e.HTMLIFrameElement;){try{var n=typeof t.contentWindow.location.href=="string"}catch{n=!1}if(n)e=t.contentWindow;else break;t=Rr(e.document)}return t}function vu(e){var t=e&&e.nodeName&&e.nodeName.toLowerCase();return t&&(t==="input"&&(e.type==="text"||e.type==="search"||e.type==="tel"||e.type==="url"||e.type==="password")||t==="textarea"||e.contentEditable==="true")}function gf(e){var t=Qo(),n=e.focusedElem,r=e.selectionRange;if(t!==n&&n&&n.ownerDocument&&$o(n.ownerDocument.documentElement,n)){if(r!==null&&vu(n)){if(t=r.start,e=r.end,e===void 0&&(e=t),"selectionStart"in n)n.selectionStart=t,n.selectionEnd=Math.min(e,n.value.length);else if(e=(t=n.ownerDocument||document)&&t.defaultView||window,e.getSelection){e=e.getSelection();var l=n.textContent.length,u=Math.min(r.start,l);r=r.end===void 0?u:Math.min(r.end,l),!e.extend&&u>r&&(l=r,r=u,u=l),l=Ho(n,u);var i=Ho(n,r);l&&i&&(e.rangeCount!==1||e.anchorNode!==l.node||e.anchorOffset!==l.offset||e.focusNode!==i.node||e.focusOffset!==i.offset)&&(t=t.createRange(),t.setStart(l.node,l.offset),e.removeAllRanges(),u>r?(e.addRange(t),e.extend(i.node,i.offset)):(t.setEnd(i.node,i.offset),e.addRange(t)))}}for(t=[],e=n;e=e.parentNode;)e.nodeType===1&&t.push({element:e,left:e.scrollLeft,top:e.scrollTop});for(typeof n.focus=="function"&&n.focus(),n=0;n=document.documentMode,wn=null,yu=null,rr=null,gu=!1;function Ko(e,t,n){var r=n.window===n?n.document:n.nodeType===9?n:n.ownerDocument;gu||wn==null||wn!==Rr(r)||(r=wn,"selectionStart"in r&&vu(r)?r={start:r.selectionStart,end:r.selectionEnd}:(r=(r.ownerDocument&&r.ownerDocument.defaultView||window).getSelection(),r={anchorNode:r.anchorNode,anchorOffset:r.anchorOffset,focusNode:r.focusNode,focusOffset:r.focusOffset}),rr&&nr(rr,r)||(rr=r,r=Gr(yu,"onSelect"),0xn||(e.current=Lu[xn],Lu[xn]=null,xn--)}function ae(e,t){xn++,Lu[xn]=e.current,e.current=t}var Ut={},ze=Ft(Ut),je=Ft(!1),bt=Ut;function _n(e,t){var n=e.type.contextTypes;if(!n)return Ut;var r=e.stateNode;if(r&&r.__reactInternalMemoizedUnmaskedChildContext===t)return r.__reactInternalMemoizedMaskedChildContext;var l={},u;for(u in n)l[u]=t[u];return r&&(e=e.stateNode,e.__reactInternalMemoizedUnmaskedChildContext=t,e.__reactInternalMemoizedMaskedChildContext=l),l}function Be(e){return e=e.childContextTypes,e!=null}function br(){ce(je),ce(ze)}function oa(e,t,n){if(ze.current!==Ut)throw Error(a(168));ae(ze,t),ae(je,n)}function aa(e,t,n){var r=e.stateNode;if(t=t.childContextTypes,typeof r.getChildContext!="function")return n;r=r.getChildContext();for(var l in r)if(!(l in t))throw Error(a(108,oe(e)||"Unknown",l));return D({},n,r)}function el(e){return e=(e=e.stateNode)&&e.__reactInternalMemoizedMergedChildContext||Ut,bt=ze.current,ae(ze,e),ae(je,je.current),!0}function sa(e,t,n){var r=e.stateNode;if(!r)throw Error(a(169));n?(e=aa(e,t,bt),r.__reactInternalMemoizedMergedChildContext=e,ce(je),ce(ze),ae(ze,e)):ce(je),ae(je,n)}var St=null,tl=!1,Tu=!1;function ca(e){St===null?St=[e]:St.push(e)}function Lf(e){tl=!0,ca(e)}function jt(){if(!Tu&&St!==null){Tu=!0;var e=0,t=ne;try{var n=St;for(ne=1;e>=i,l-=i,kt=1<<32-lt(t)+l|n<Q?(Pe=V,V=null):Pe=V.sibling;var b=k(m,V,v[Q],P);if(b===null){V===null&&(V=Pe);break}e&&V&&b.alternate===null&&t(m,V),d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b,V=Pe}if(Q===v.length)return n(m,V),de&&tn(m,Q),j;if(V===null){for(;QQ?(Pe=V,V=null):Pe=V.sibling;var Yt=k(m,V,b.value,P);if(Yt===null){V===null&&(V=Pe);break}e&&V&&Yt.alternate===null&&t(m,V),d=u(Yt,d,Q),A===null?j=Yt:A.sibling=Yt,A=Yt,V=Pe}if(b.done)return n(m,V),de&&tn(m,Q),j;if(V===null){for(;!b.done;Q++,b=v.next())b=x(m,b.value,P),b!==null&&(d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b);return de&&tn(m,Q),j}for(V=r(m,V);!b.done;Q++,b=v.next())b=O(V,m,Q,b.value,P),b!==null&&(e&&b.alternate!==null&&V.delete(b.key===null?Q:b.key),d=u(b,d,Q),A===null?j=b:A.sibling=b,A=b);return e&&V.forEach(function(cd){return t(m,cd)}),de&&tn(m,Q),j}function ge(m,d,v,P){if(typeof v=="object"&&v!==null&&v.type===Fe&&v.key===null&&(v=v.props.children),typeof v=="object"&&v!==null){switch(v.$$typeof){case Ce:e:{for(var j=v.key,A=d;A!==null;){if(A.key===j){if(j=v.type,j===Fe){if(A.tag===7){n(m,A.sibling),d=l(A,v.props.children),d.return=m,m=d;break e}}else if(A.elementType===j||typeof j=="object"&&j!==null&&j.$$typeof===Ue&&va(j)===A.type){n(m,A.sibling),d=l(A,v.props),d.ref=sr(m,A,v),d.return=m,m=d;break e}n(m,A);break}else t(m,A);A=A.sibling}v.type===Fe?(d=cn(v.props.children,m.mode,P,v.key),d.return=m,m=d):(P=zl(v.type,v.key,v.props,null,m.mode,P),P.ref=sr(m,d,v),P.return=m,m=P)}return i(m);case Me:e:{for(A=v.key;d!==null;){if(d.key===A)if(d.tag===4&&d.stateNode.containerInfo===v.containerInfo&&d.stateNode.implementation===v.implementation){n(m,d.sibling),d=l(d,v.children||[]),d.return=m,m=d;break e}else{n(m,d);break}else t(m,d);d=d.sibling}d=Ri(v,m.mode,P),d.return=m,m=d}return i(m);case Ue:return A=v._init,ge(m,d,A(v._payload),P)}if(jn(v))return F(m,d,v,P);if($(v))return U(m,d,v,P);ul(m,v)}return typeof v=="string"&&v!==""||typeof v=="number"?(v=""+v,d!==null&&d.tag===6?(n(m,d.sibling),d=l(d,v),d.return=m,m=d):(n(m,d),d=Ni(v,m.mode,P),d.return=m,m=d),i(m)):n(m,d)}return ge}var zn=ya(!0),ga=ya(!1),il=Ft(null),ol=null,Ln=null,Uu=null;function ju(){Uu=Ln=ol=null}function Bu(e){var t=il.current;ce(il),e._currentValue=t}function Au(e,t,n){for(;e!==null;){var r=e.alternate;if((e.childLanes&t)!==t?(e.childLanes|=t,r!==null&&(r.childLanes|=t)):r!==null&&(r.childLanes&t)!==t&&(r.childLanes|=t),e===n)break;e=e.return}}function Tn(e,t){ol=e,Uu=Ln=null,e=e.dependencies,e!==null&&e.firstContext!==null&&((e.lanes&t)!==0&&(Ae=!0),e.firstContext=null)}function be(e){var t=e._currentValue;if(Uu!==e)if(e={context:e,memoizedValue:t,next:null},Ln===null){if(ol===null)throw Error(a(308));Ln=e,ol.dependencies={lanes:0,firstContext:e}}else Ln=Ln.next=e;return t}var nn=null;function Vu(e){nn===null?nn=[e]:nn.push(e)}function wa(e,t,n,r){var l=t.interleaved;return l===null?(n.next=n,Vu(t)):(n.next=l.next,l.next=n),t.interleaved=n,Ct(e,r)}function Ct(e,t){e.lanes|=t;var n=e.alternate;for(n!==null&&(n.lanes|=t),n=e,e=e.return;e!==null;)e.childLanes|=t,n=e.alternate,n!==null&&(n.childLanes|=t),n=e,e=e.return;return n.tag===3?n.stateNode:null}var Bt=!1;function Wu(e){e.updateQueue={baseState:e.memoizedState,firstBaseUpdate:null,lastBaseUpdate:null,shared:{pending:null,interleaved:null,lanes:0},effects:null}}function Sa(e,t){e=e.updateQueue,t.updateQueue===e&&(t.updateQueue={baseState:e.baseState,firstBaseUpdate:e.firstBaseUpdate,lastBaseUpdate:e.lastBaseUpdate,shared:e.shared,effects:e.effects})}function xt(e,t){return{eventTime:e,lane:t,tag:0,payload:null,callback:null,next:null}}function At(e,t,n){var r=e.updateQueue;if(r===null)return null;if(r=r.shared,(Z&2)!==0){var l=r.pending;return l===null?t.next=t:(t.next=l.next,l.next=t),r.pending=t,Ct(e,n)}return l=r.interleaved,l===null?(t.next=t,Vu(r)):(t.next=l.next,l.next=t),r.interleaved=t,Ct(e,n)}function al(e,t,n){if(t=t.updateQueue,t!==null&&(t=t.shared,(n&4194240)!==0)){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,nu(e,n)}}function ka(e,t){var n=e.updateQueue,r=e.alternate;if(r!==null&&(r=r.updateQueue,n===r)){var l=null,u=null;if(n=n.firstBaseUpdate,n!==null){do{var i={eventTime:n.eventTime,lane:n.lane,tag:n.tag,payload:n.payload,callback:n.callback,next:null};u===null?l=u=i:u=u.next=i,n=n.next}while(n!==null);u===null?l=u=t:u=u.next=t}else l=u=t;n={baseState:r.baseState,firstBaseUpdate:l,lastBaseUpdate:u,shared:r.shared,effects:r.effects},e.updateQueue=n;return}e=n.lastBaseUpdate,e===null?n.firstBaseUpdate=t:e.next=t,n.lastBaseUpdate=t}function sl(e,t,n,r){var l=e.updateQueue;Bt=!1;var u=l.firstBaseUpdate,i=l.lastBaseUpdate,s=l.shared.pending;if(s!==null){l.shared.pending=null;var f=s,y=f.next;f.next=null,i===null?u=y:i.next=y,i=f;var C=e.alternate;C!==null&&(C=C.updateQueue,s=C.lastBaseUpdate,s!==i&&(s===null?C.firstBaseUpdate=y:s.next=y,C.lastBaseUpdate=f))}if(u!==null){var x=l.baseState;i=0,C=y=f=null,s=u;do{var k=s.lane,O=s.eventTime;if((r&k)===k){C!==null&&(C=C.next={eventTime:O,lane:0,tag:s.tag,payload:s.payload,callback:s.callback,next:null});e:{var F=e,U=s;switch(k=t,O=n,U.tag){case 1:if(F=U.payload,typeof F=="function"){x=F.call(O,x,k);break e}x=F;break e;case 3:F.flags=F.flags&-65537|128;case 0:if(F=U.payload,k=typeof F=="function"?F.call(O,x,k):F,k==null)break e;x=D({},x,k);break e;case 2:Bt=!0}}s.callback!==null&&s.lane!==0&&(e.flags|=64,k=l.effects,k===null?l.effects=[s]:k.push(s))}else O={eventTime:O,lane:k,tag:s.tag,payload:s.payload,callback:s.callback,next:null},C===null?(y=C=O,f=x):C=C.next=O,i|=k;if(s=s.next,s===null){if(s=l.shared.pending,s===null)break;k=s,s=k.next,k.next=null,l.lastBaseUpdate=k,l.shared.pending=null}}while(!0);if(C===null&&(f=x),l.baseState=f,l.firstBaseUpdate=y,l.lastBaseUpdate=C,t=l.shared.interleaved,t!==null){l=t;do i|=l.lane,l=l.next;while(l!==t)}else u===null&&(l.shared.lanes=0);un|=i,e.lanes=i,e.memoizedState=x}}function Ea(e,t,n){if(e=t.effects,t.effects=null,e!==null)for(t=0;tn?n:4,e(!0);var r=Yu.transition;Yu.transition={};try{e(!1),t()}finally{ne=n,Yu.transition=r}}function Va(){return et().memoizedState}function If(e,t,n){var r=$t(e);if(n={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null},Wa(e))Ha(t,n);else if(n=wa(e,t,n,r),n!==null){var l=De();ct(n,e,r,l),$a(n,t,r)}}function Df(e,t,n){var r=$t(e),l={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null};if(Wa(e))Ha(t,l);else{var u=e.alternate;if(e.lanes===0&&(u===null||u.lanes===0)&&(u=t.lastRenderedReducer,u!==null))try{var i=t.lastRenderedState,s=u(i,n);if(l.hasEagerState=!0,l.eagerState=s,ut(s,i)){var f=t.interleaved;f===null?(l.next=l,Vu(t)):(l.next=f.next,f.next=l),t.interleaved=l;return}}catch{}finally{}n=wa(e,t,l,r),n!==null&&(l=De(),ct(n,e,r,l),$a(n,t,r))}}function Wa(e){var t=e.alternate;return e===he||t!==null&&t===he}function Ha(e,t){pr=dl=!0;var n=e.pending;n===null?t.next=t:(t.next=n.next,n.next=t),e.pending=t}function $a(e,t,n){if((n&4194240)!==0){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,nu(e,n)}}var ml={readContext:be,useCallback:Le,useContext:Le,useEffect:Le,useImperativeHandle:Le,useInsertionEffect:Le,useLayoutEffect:Le,useMemo:Le,useReducer:Le,useRef:Le,useState:Le,useDebugValue:Le,useDeferredValue:Le,useTransition:Le,useMutableSource:Le,useSyncExternalStore:Le,useId:Le,unstable_isNewReconciler:!1},Ff={readContext:be,useCallback:function(e,t){return vt().memoizedState=[e,t===void 0?null:t],e},useContext:be,useEffect:Ma,useImperativeHandle:function(e,t,n){return n=n!=null?n.concat([e]):null,pl(4194308,4,Fa.bind(null,t,e),n)},useLayoutEffect:function(e,t){return pl(4194308,4,e,t)},useInsertionEffect:function(e,t){return pl(4,2,e,t)},useMemo:function(e,t){var n=vt();return t=t===void 0?null:t,e=e(),n.memoizedState=[e,t],e},useReducer:function(e,t,n){var r=vt();return t=n!==void 0?n(t):t,r.memoizedState=r.baseState=t,e={pending:null,interleaved:null,lanes:0,dispatch:null,lastRenderedReducer:e,lastRenderedState:t},r.queue=e,e=e.dispatch=If.bind(null,he,e),[r.memoizedState,e]},useRef:function(e){var t=vt();return e={current:e},t.memoizedState=e},useState:Ta,useDebugValue:ei,useDeferredValue:function(e){return vt().memoizedState=e},useTransition:function(){var e=Ta(!1),t=e[0];return e=Mf.bind(null,e[1]),vt().memoizedState=e,[t,e]},useMutableSource:function(){},useSyncExternalStore:function(e,t,n){var r=he,l=vt();if(de){if(n===void 0)throw Error(a(407));n=n()}else{if(n=t(),_e===null)throw Error(a(349));(ln&30)!==0||Pa(r,t,n)}l.memoizedState=n;var u={value:n,getSnapshot:t};return l.queue=u,Ma(Ra.bind(null,r,u,e),[e]),r.flags|=2048,vr(9,Na.bind(null,r,u,n,t),void 0,null),n},useId:function(){var e=vt(),t=_e.identifierPrefix;if(de){var n=Et,r=kt;n=(r&~(1<<32-lt(r)-1)).toString(32)+n,t=":"+t+"R"+n,n=hr++,0<\/script>",e=e.removeChild(e.firstChild)):typeof r.is=="string"?e=i.createElement(n,{is:r.is}):(e=i.createElement(n),n==="select"&&(i=e,r.multiple?i.multiple=!0:r.size&&(i.size=r.size))):e=i.createElementNS(e,n),e[ht]=t,e[or]=r,cs(e,t,!1,!1),t.stateNode=e;e:{switch(i=Kl(n,r),n){case"dialog":se("cancel",e),se("close",e),l=r;break;case"iframe":case"object":case"embed":se("load",e),l=r;break;case"video":case"audio":for(l=0;lFn&&(t.flags|=128,r=!0,yr(u,!1),t.lanes=4194304)}else{if(!r)if(e=cl(i),e!==null){if(t.flags|=128,r=!0,n=e.updateQueue,n!==null&&(t.updateQueue=n,t.flags|=4),yr(u,!0),u.tail===null&&u.tailMode==="hidden"&&!i.alternate&&!de)return Te(t),null}else 2*ye()-u.renderingStartTime>Fn&&n!==1073741824&&(t.flags|=128,r=!0,yr(u,!1),t.lanes=4194304);u.isBackwards?(i.sibling=t.child,t.child=i):(n=u.last,n!==null?n.sibling=i:t.child=i,u.last=i)}return u.tail!==null?(t=u.tail,u.rendering=t,u.tail=t.sibling,u.renderingStartTime=ye(),t.sibling=null,n=pe.current,ae(pe,r?n&1|2:n&1),t):(Te(t),null);case 22:case 23:return xi(),r=t.memoizedState!==null,e!==null&&e.memoizedState!==null!==r&&(t.flags|=8192),r&&(t.mode&1)!==0?(Ge&1073741824)!==0&&(Te(t),t.subtreeFlags&6&&(t.flags|=8192)):Te(t),null;case 24:return null;case 25:return null}throw Error(a(156,t.tag))}function Hf(e,t){switch(Mu(t),t.tag){case 1:return Be(t.type)&&br(),e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 3:return On(),ce(je),ce(ze),Ku(),e=t.flags,(e&65536)!==0&&(e&128)===0?(t.flags=e&-65537|128,t):null;case 5:return $u(t),null;case 13:if(ce(pe),e=t.memoizedState,e!==null&&e.dehydrated!==null){if(t.alternate===null)throw Error(a(340));Rn()}return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 19:return ce(pe),null;case 4:return On(),null;case 10:return Bu(t.type._context),null;case 22:case 23:return xi(),null;case 24:return null;default:return null}}var wl=!1,Oe=!1,$f=typeof WeakSet=="function"?WeakSet:Set,I=null;function In(e,t){var n=e.ref;if(n!==null)if(typeof n=="function")try{n(null)}catch(r){ve(e,t,r)}else n.current=null}function di(e,t,n){try{n()}catch(r){ve(e,t,r)}}var ps=!1;function Qf(e,t){if(xu=Br,e=Qo(),vu(e)){if("selectionStart"in e)var n={start:e.selectionStart,end:e.selectionEnd};else e:{n=(n=e.ownerDocument)&&n.defaultView||window;var r=n.getSelection&&n.getSelection();if(r&&r.rangeCount!==0){n=r.anchorNode;var l=r.anchorOffset,u=r.focusNode;r=r.focusOffset;try{n.nodeType,u.nodeType}catch{n=null;break e}var i=0,s=-1,f=-1,y=0,C=0,_=e,k=null;t:for(;;){for(var O;_!==n||l!==0&&_.nodeType!==3||(s=i+l),_!==u||r!==0&&_.nodeType!==3||(f=i+r),_.nodeType===3&&(i+=_.nodeValue.length),(O=_.firstChild)!==null;)k=_,_=O;for(;;){if(_===e)break t;if(k===n&&++y===l&&(s=i),k===u&&++C===r&&(f=i),(O=_.nextSibling)!==null)break;_=k,k=_.parentNode}_=O}n=s===-1||f===-1?null:{start:s,end:f}}else n=null}n=n||{start:0,end:0}}else n=null;for(_u={focusedElem:e,selectionRange:n},Br=!1,I=t;I!==null;)if(t=I,e=t.child,(t.subtreeFlags&1028)!==0&&e!==null)e.return=t,I=e;else for(;I!==null;){t=I;try{var F=t.alternate;if((t.flags&1024)!==0)switch(t.tag){case 0:case 11:case 15:break;case 1:if(F!==null){var U=F.memoizedProps,ge=F.memoizedState,m=t.stateNode,d=m.getSnapshotBeforeUpdate(t.elementType===t.type?U:ot(t.type,U),ge);m.__reactInternalSnapshotBeforeUpdate=d}break;case 3:var v=t.stateNode.containerInfo;v.nodeType===1?v.textContent="":v.nodeType===9&&v.documentElement&&v.removeChild(v.documentElement);break;case 5:case 6:case 4:case 17:break;default:throw Error(a(163))}}catch(P){ve(t,t.return,P)}if(e=t.sibling,e!==null){e.return=t.return,I=e;break}I=t.return}return F=ps,ps=!1,F}function gr(e,t,n){var r=t.updateQueue;if(r=r!==null?r.lastEffect:null,r!==null){var l=r=r.next;do{if((l.tag&e)===e){var u=l.destroy;l.destroy=void 0,u!==void 0&&di(t,n,u)}l=l.next}while(l!==r)}}function Sl(e,t){if(t=t.updateQueue,t=t!==null?t.lastEffect:null,t!==null){var n=t=t.next;do{if((n.tag&e)===e){var r=n.create;n.destroy=r()}n=n.next}while(n!==t)}}function pi(e){var t=e.ref;if(t!==null){var n=e.stateNode;switch(e.tag){case 5:e=n;break;default:e=n}typeof t=="function"?t(e):t.current=e}}function hs(e){var t=e.alternate;t!==null&&(e.alternate=null,hs(t)),e.child=null,e.deletions=null,e.sibling=null,e.tag===5&&(t=e.stateNode,t!==null&&(delete t[ht],delete t[or],delete t[zu],delete t[Nf],delete t[Rf])),e.stateNode=null,e.return=null,e.dependencies=null,e.memoizedProps=null,e.memoizedState=null,e.pendingProps=null,e.stateNode=null,e.updateQueue=null}function ms(e){return e.tag===5||e.tag===3||e.tag===4}function vs(e){e:for(;;){for(;e.sibling===null;){if(e.return===null||ms(e.return))return null;e=e.return}for(e.sibling.return=e.return,e=e.sibling;e.tag!==5&&e.tag!==6&&e.tag!==18;){if(e.flags&2||e.child===null||e.tag===4)continue e;e.child.return=e,e=e.child}if(!(e.flags&2))return e.stateNode}}function hi(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.nodeType===8?n.parentNode.insertBefore(e,t):n.insertBefore(e,t):(n.nodeType===8?(t=n.parentNode,t.insertBefore(e,n)):(t=n,t.appendChild(e)),n=n._reactRootContainer,n!=null||t.onclick!==null||(t.onclick=Jr));else if(r!==4&&(e=e.child,e!==null))for(hi(e,t,n),e=e.sibling;e!==null;)hi(e,t,n),e=e.sibling}function mi(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.insertBefore(e,t):n.appendChild(e);else if(r!==4&&(e=e.child,e!==null))for(mi(e,t,n),e=e.sibling;e!==null;)mi(e,t,n),e=e.sibling}var Ne=null,at=!1;function Vt(e,t,n){for(n=n.child;n!==null;)ys(e,t,n),n=n.sibling}function ys(e,t,n){if(pt&&typeof pt.onCommitFiberUnmount=="function")try{pt.onCommitFiberUnmount(Mr,n)}catch{}switch(n.tag){case 5:Oe||In(n,t);case 6:var r=Ne,l=at;Ne=null,Vt(e,t,n),Ne=r,at=l,Ne!==null&&(at?(e=Ne,n=n.stateNode,e.nodeType===8?e.parentNode.removeChild(n):e.removeChild(n)):Ne.removeChild(n.stateNode));break;case 18:Ne!==null&&(at?(e=Ne,n=n.stateNode,e.nodeType===8?Ru(e.parentNode,n):e.nodeType===1&&Ru(e,n),Zn(e)):Ru(Ne,n.stateNode));break;case 4:r=Ne,l=at,Ne=n.stateNode.containerInfo,at=!0,Vt(e,t,n),Ne=r,at=l;break;case 0:case 11:case 14:case 15:if(!Oe&&(r=n.updateQueue,r!==null&&(r=r.lastEffect,r!==null))){l=r=r.next;do{var u=l,i=u.destroy;u=u.tag,i!==void 0&&((u&2)!==0||(u&4)!==0)&&di(n,t,i),l=l.next}while(l!==r)}Vt(e,t,n);break;case 1:if(!Oe&&(In(n,t),r=n.stateNode,typeof r.componentWillUnmount=="function"))try{r.props=n.memoizedProps,r.state=n.memoizedState,r.componentWillUnmount()}catch(s){ve(n,t,s)}Vt(e,t,n);break;case 21:Vt(e,t,n);break;case 22:n.mode&1?(Oe=(r=Oe)||n.memoizedState!==null,Vt(e,t,n),Oe=r):Vt(e,t,n);break;default:Vt(e,t,n)}}function gs(e){var t=e.updateQueue;if(t!==null){e.updateQueue=null;var n=e.stateNode;n===null&&(n=e.stateNode=new $f),t.forEach(function(r){var l=ed.bind(null,e,r);n.has(r)||(n.add(r),r.then(l,l))})}}function st(e,t){var n=t.deletions;if(n!==null)for(var r=0;rl&&(l=i),r&=~u}if(r=l,r=ye()-r,r=(120>r?120:480>r?480:1080>r?1080:1920>r?1920:3e3>r?3e3:4320>r?4320:1960*Yf(r/1960))-r,10e?16:e,Ht===null)var r=!1;else{if(e=Ht,Ht=null,_l=0,(Z&6)!==0)throw Error(a(331));var l=Z;for(Z|=4,I=e.current;I!==null;){var u=I,i=u.child;if((I.flags&16)!==0){var s=u.deletions;if(s!==null){for(var f=0;fye()-gi?an(e,0):yi|=n),We(e,t)}function Ts(e,t){t===0&&((e.mode&1)===0?t=1:(t=Dr,Dr<<=1,(Dr&130023424)===0&&(Dr=4194304)));var n=De();e=Ct(e,t),e!==null&&(Qn(e,t,n),We(e,n))}function bf(e){var t=e.memoizedState,n=0;t!==null&&(n=t.retryLane),Ts(e,n)}function ed(e,t){var n=0;switch(e.tag){case 13:var r=e.stateNode,l=e.memoizedState;l!==null&&(n=l.retryLane);break;case 19:r=e.stateNode;break;default:throw Error(a(314))}r!==null&&r.delete(t),Ts(e,n)}var Os;Os=function(e,t,n){if(e!==null)if(e.memoizedProps!==t.pendingProps||je.current)Ae=!0;else{if((e.lanes&n)===0&&(t.flags&128)===0)return Ae=!1,Vf(e,t,n);Ae=(e.flags&131072)!==0}else Ae=!1,de&&(t.flags&1048576)!==0&&fa(t,rl,t.index);switch(t.lanes=0,t.tag){case 2:var r=t.type;gl(e,t),e=t.pendingProps;var l=_n(t,ze.current);Tn(t,n),l=Gu(null,t,r,e,l,n);var u=Zu();return t.flags|=1,typeof l=="object"&&l!==null&&typeof l.render=="function"&&l.$$typeof===void 0?(t.tag=1,t.memoizedState=null,t.updateQueue=null,Be(r)?(u=!0,el(t)):u=!1,t.memoizedState=l.state!==null&&l.state!==void 0?l.state:null,Wu(t),l.updater=vl,t.stateNode=l,l._reactInternals=t,ni(t,r,e,n),t=ii(null,t,r,!0,u,n)):(t.tag=0,de&&u&&Ou(t),Ie(null,t,l,n),t=t.child),t;case 16:r=t.elementType;e:{switch(gl(e,t),e=t.pendingProps,l=r._init,r=l(r._payload),t.type=r,l=t.tag=nd(r),e=ot(r,e),l){case 0:t=ui(null,t,r,e,n);break e;case 1:t=ls(null,t,r,e,n);break e;case 11:t=ba(null,t,r,e,n);break e;case 14:t=es(null,t,r,ot(r.type,e),n);break e}throw Error(a(306,r,""))}return t;case 0:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ui(e,t,r,l,n);case 1:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ls(e,t,r,l,n);case 3:e:{if(us(t),e===null)throw Error(a(387));r=t.pendingProps,u=t.memoizedState,l=u.element,Sa(e,t),sl(t,r,null,n);var i=t.memoizedState;if(r=i.element,u.isDehydrated)if(u={element:r,isDehydrated:!1,cache:i.cache,pendingSuspenseBoundaries:i.pendingSuspenseBoundaries,transitions:i.transitions},t.updateQueue.baseState=u,t.memoizedState=u,t.flags&256){l=Mn(Error(a(423)),t),t=is(e,t,r,n,l);break e}else if(r!==l){l=Mn(Error(a(424)),t),t=is(e,t,r,n,l);break e}else for(Xe=Dt(t.stateNode.containerInfo.firstChild),Ye=t,de=!0,it=null,n=ga(t,null,r,n),t.child=n;n;)n.flags=n.flags&-3|4096,n=n.sibling;else{if(Rn(),r===l){t=_t(e,t,n);break e}Ie(e,t,r,n)}t=t.child}return t;case 5:return Ca(t),e===null&&Du(t),r=t.type,l=t.pendingProps,u=e!==null?e.memoizedProps:null,i=l.children,Pu(r,l)?i=null:u!==null&&Pu(r,u)&&(t.flags|=32),rs(e,t),Ie(e,t,i,n),t.child;case 6:return e===null&&Du(t),null;case 13:return os(e,t,n);case 4:return Hu(t,t.stateNode.containerInfo),r=t.pendingProps,e===null?t.child=zn(t,null,r,n):Ie(e,t,r,n),t.child;case 11:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ba(e,t,r,l,n);case 7:return Ie(e,t,t.pendingProps,n),t.child;case 8:return Ie(e,t,t.pendingProps.children,n),t.child;case 12:return Ie(e,t,t.pendingProps.children,n),t.child;case 10:e:{if(r=t.type._context,l=t.pendingProps,u=t.memoizedProps,i=l.value,ae(il,r._currentValue),r._currentValue=i,u!==null)if(ut(u.value,i)){if(u.children===l.children&&!je.current){t=_t(e,t,n);break e}}else for(u=t.child,u!==null&&(u.return=t);u!==null;){var s=u.dependencies;if(s!==null){i=u.child;for(var f=s.firstContext;f!==null;){if(f.context===r){if(u.tag===1){f=xt(-1,n&-n),f.tag=2;var y=u.updateQueue;if(y!==null){y=y.shared;var C=y.pending;C===null?f.next=f:(f.next=C.next,C.next=f),y.pending=f}}u.lanes|=n,f=u.alternate,f!==null&&(f.lanes|=n),Au(u.return,n,t),s.lanes|=n;break}f=f.next}}else if(u.tag===10)i=u.type===t.type?null:u.child;else if(u.tag===18){if(i=u.return,i===null)throw Error(a(341));i.lanes|=n,s=i.alternate,s!==null&&(s.lanes|=n),Au(i,n,t),i=u.sibling}else i=u.child;if(i!==null)i.return=u;else for(i=u;i!==null;){if(i===t){i=null;break}if(u=i.sibling,u!==null){u.return=i.return,i=u;break}i=i.return}u=i}Ie(e,t,l.children,n),t=t.child}return t;case 9:return l=t.type,r=t.pendingProps.children,Tn(t,n),l=be(l),r=r(l),t.flags|=1,Ie(e,t,r,n),t.child;case 14:return r=t.type,l=ot(r,t.pendingProps),l=ot(r.type,l),es(e,t,r,l,n);case 15:return ts(e,t,t.type,t.pendingProps,n);case 17:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),gl(e,t),t.tag=1,Be(r)?(e=!0,el(t)):e=!1,Tn(t,n),Ka(t,r,l),ni(t,r,l,n),ii(null,t,r,!0,e,n);case 19:return ss(e,t,n);case 22:return ns(e,t,n)}throw Error(a(156,t.tag))};function Ms(e,t){return fo(e,t)}function td(e,t,n,r){this.tag=e,this.key=n,this.sibling=this.child=this.return=this.stateNode=this.type=this.elementType=null,this.index=0,this.ref=null,this.pendingProps=t,this.dependencies=this.memoizedState=this.updateQueue=this.memoizedProps=null,this.mode=r,this.subtreeFlags=this.flags=0,this.deletions=null,this.childLanes=this.lanes=0,this.alternate=null}function nt(e,t,n,r){return new td(e,t,n,r)}function Pi(e){return e=e.prototype,!(!e||!e.isReactComponent)}function nd(e){if(typeof e=="function")return Pi(e)?1:0;if(e!=null){if(e=e.$$typeof,e===ft)return 11;if(e===dt)return 14}return 2}function Kt(e,t){var n=e.alternate;return n===null?(n=nt(e.tag,t,e.key,e.mode),n.elementType=e.elementType,n.type=e.type,n.stateNode=e.stateNode,n.alternate=e,e.alternate=n):(n.pendingProps=t,n.type=e.type,n.flags=0,n.subtreeFlags=0,n.deletions=null),n.flags=e.flags&14680064,n.childLanes=e.childLanes,n.lanes=e.lanes,n.child=e.child,n.memoizedProps=e.memoizedProps,n.memoizedState=e.memoizedState,n.updateQueue=e.updateQueue,t=e.dependencies,n.dependencies=t===null?null:{lanes:t.lanes,firstContext:t.firstContext},n.sibling=e.sibling,n.index=e.index,n.ref=e.ref,n}function zl(e,t,n,r,l,u){var i=2;if(r=e,typeof e=="function")Pi(e)&&(i=1);else if(typeof e=="string")i=5;else e:switch(e){case Fe:return cn(n.children,l,u,t);case Ze:i=8,l|=8;break;case Rt:return e=nt(12,n,t,l|2),e.elementType=Rt,e.lanes=u,e;case $e:return e=nt(13,n,t,l),e.elementType=$e,e.lanes=u,e;case rt:return e=nt(19,n,t,l),e.elementType=rt,e.lanes=u,e;case me:return Ll(n,l,u,t);default:if(typeof e=="object"&&e!==null)switch(e.$$typeof){case gt:i=10;break e;case Zt:i=9;break e;case ft:i=11;break e;case dt:i=14;break e;case Ue:i=16,r=null;break e}throw Error(a(130,e==null?e:typeof e,""))}return t=nt(i,n,t,l),t.elementType=e,t.type=r,t.lanes=u,t}function cn(e,t,n,r){return e=nt(7,e,r,t),e.lanes=n,e}function Ll(e,t,n,r){return e=nt(22,e,r,t),e.elementType=me,e.lanes=n,e.stateNode={isHidden:!1},e}function Ni(e,t,n){return e=nt(6,e,null,t),e.lanes=n,e}function Ri(e,t,n){return t=nt(4,e.children!==null?e.children:[],e.key,t),t.lanes=n,t.stateNode={containerInfo:e.containerInfo,pendingChildren:null,implementation:e.implementation},t}function rd(e,t,n,r,l){this.tag=t,this.containerInfo=e,this.finishedWork=this.pingCache=this.current=this.pendingChildren=null,this.timeoutHandle=-1,this.callbackNode=this.pendingContext=this.context=null,this.callbackPriority=0,this.eventTimes=tu(0),this.expirationTimes=tu(-1),this.entangledLanes=this.finishedLanes=this.mutableReadLanes=this.expiredLanes=this.pingedLanes=this.suspendedLanes=this.pendingLanes=0,this.entanglements=tu(0),this.identifierPrefix=r,this.onRecoverableError=l,this.mutableSourceEagerHydrationData=null}function zi(e,t,n,r,l,u,i,s,f){return e=new rd(e,t,n,s,f),t===1?(t=1,u===!0&&(t|=8)):t=0,u=nt(3,null,null,t),e.current=u,u.stateNode=e,u.memoizedState={element:r,isDehydrated:n,cache:null,transitions:null,pendingSuspenseBoundaries:null},Wu(u),e}function ld(e,t,n){var r=3"u"||typeof __REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE!="function"))try{__REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE(o)}catch(c){console.error(c)}}return o(),Ii.exports=yd(),Ii.exports}var xp=gd();/** - * @remix-run/router v1.23.2 +`+u.stack}return{value:e,source:t,stack:l,digest:null}}function ri(e,t,n){return{value:e,source:null,stack:n??null,digest:t??null}}function li(e,t){try{console.error(t.value)}catch(n){setTimeout(function(){throw n})}}var Bf=typeof WeakMap=="function"?WeakMap:Map;function Xa(e,t,n){n=xt(-1,n),n.tag=3,n.payload={element:null};var r=t.value;return n.callback=function(){Cl||(Cl=!0,wi=r),li(e,t)},n}function Ga(e,t,n){n=xt(-1,n),n.tag=3;var r=e.type.getDerivedStateFromError;if(typeof r=="function"){var l=t.value;n.payload=function(){return r(l)},n.callback=function(){li(e,t)}}var u=e.stateNode;return u!==null&&typeof u.componentDidCatch=="function"&&(n.callback=function(){li(e,t),typeof r!="function"&&(Wt===null?Wt=new Set([this]):Wt.add(this));var i=t.stack;this.componentDidCatch(t.value,{componentStack:i!==null?i:""})}),n}function Za(e,t,n){var r=e.pingCache;if(r===null){r=e.pingCache=new Bf;var l=new Set;r.set(t,l)}else l=r.get(t),l===void 0&&(l=new Set,r.set(t,l));l.has(n)||(l.add(n),e=bf.bind(null,e,t,n),t.then(e,e))}function Ja(e){do{var t;if((t=e.tag===13)&&(t=e.memoizedState,t=t!==null?t.dehydrated!==null:!0),t)return e;e=e.return}while(e!==null);return null}function qa(e,t,n,r,l){return(e.mode&1)===0?(e===t?e.flags|=65536:(e.flags|=128,n.flags|=131072,n.flags&=-52805,n.tag===1&&(n.alternate===null?n.tag=17:(t=xt(-1,1),t.tag=2,At(n,t,1))),n.lanes|=1),e):(e.flags|=65536,e.lanes=l,e)}var Af=ie.ReactCurrentOwner,Ae=!1;function Ie(e,t,n,r){t.child=e===null?ga(t,null,n,r):zn(t,e.child,n,r)}function ba(e,t,n,r,l){n=n.render;var u=t.ref;return Tn(t,l),r=Gu(e,t,n,r,u,l),n=Zu(),e!==null&&!Ae?(t.updateQueue=e.updateQueue,t.flags&=-2053,e.lanes&=~l,_t(e,t,l)):(de&&n&&Ou(t),t.flags|=1,Ie(e,t,r,l),t.child)}function es(e,t,n,r,l){if(e===null){var u=n.type;return typeof u=="function"&&!Pi(u)&&u.defaultProps===void 0&&n.compare===null&&n.defaultProps===void 0?(t.tag=15,t.type=u,ts(e,t,u,r,l)):(e=zl(n.type,null,r,t,t.mode,l),e.ref=t.ref,e.return=t,t.child=e)}if(u=e.child,(e.lanes&l)===0){var i=u.memoizedProps;if(n=n.compare,n=n!==null?n:nr,n(i,r)&&e.ref===t.ref)return _t(e,t,l)}return t.flags|=1,e=Kt(u,r),e.ref=t.ref,e.return=t,t.child=e}function ts(e,t,n,r,l){if(e!==null){var u=e.memoizedProps;if(nr(u,r)&&e.ref===t.ref)if(Ae=!1,t.pendingProps=r=u,(e.lanes&l)!==0)(e.flags&131072)!==0&&(Ae=!0);else return t.lanes=e.lanes,_t(e,t,l)}return ui(e,t,n,r,l)}function ns(e,t,n){var r=t.pendingProps,l=r.children,u=e!==null?e.memoizedState:null;if(r.mode==="hidden")if((t.mode&1)===0)t.memoizedState={baseLanes:0,cachePool:null,transitions:null},ae(Dn,Ge),Ge|=n;else{if((n&1073741824)===0)return e=u!==null?u.baseLanes|n:n,t.lanes=t.childLanes=1073741824,t.memoizedState={baseLanes:e,cachePool:null,transitions:null},t.updateQueue=null,ae(Dn,Ge),Ge|=e,null;t.memoizedState={baseLanes:0,cachePool:null,transitions:null},r=u!==null?u.baseLanes:n,ae(Dn,Ge),Ge|=r}else u!==null?(r=u.baseLanes|n,t.memoizedState=null):r=n,ae(Dn,Ge),Ge|=r;return Ie(e,t,l,n),t.child}function rs(e,t){var n=t.ref;(e===null&&n!==null||e!==null&&e.ref!==n)&&(t.flags|=512,t.flags|=2097152)}function ui(e,t,n,r,l){var u=Be(n)?bt:ze.current;return u=_n(t,u),Tn(t,l),n=Gu(e,t,n,r,u,l),r=Zu(),e!==null&&!Ae?(t.updateQueue=e.updateQueue,t.flags&=-2053,e.lanes&=~l,_t(e,t,l)):(de&&r&&Ou(t),t.flags|=1,Ie(e,t,n,l),t.child)}function ls(e,t,n,r,l){if(Be(n)){var u=!0;el(t)}else u=!1;if(Tn(t,l),t.stateNode===null)gl(e,t),Ka(t,n,r),ni(t,n,r,l),r=!0;else if(e===null){var i=t.stateNode,s=t.memoizedProps;i.props=s;var f=i.context,y=n.contextType;typeof y=="object"&&y!==null?y=be(y):(y=Be(n)?bt:ze.current,y=_n(t,y));var C=n.getDerivedStateFromProps,x=typeof C=="function"||typeof i.getSnapshotBeforeUpdate=="function";x||typeof i.UNSAFE_componentWillReceiveProps!="function"&&typeof i.componentWillReceiveProps!="function"||(s!==r||f!==y)&&Ya(t,i,r,y),Bt=!1;var k=t.memoizedState;i.state=k,sl(t,r,i,l),f=t.memoizedState,s!==r||k!==f||je.current||Bt?(typeof C=="function"&&(ti(t,n,C,r),f=t.memoizedState),(s=Bt||Qa(t,n,s,r,k,f,y))?(x||typeof i.UNSAFE_componentWillMount!="function"&&typeof i.componentWillMount!="function"||(typeof i.componentWillMount=="function"&&i.componentWillMount(),typeof i.UNSAFE_componentWillMount=="function"&&i.UNSAFE_componentWillMount()),typeof i.componentDidMount=="function"&&(t.flags|=4194308)):(typeof i.componentDidMount=="function"&&(t.flags|=4194308),t.memoizedProps=r,t.memoizedState=f),i.props=r,i.state=f,i.context=y,r=s):(typeof i.componentDidMount=="function"&&(t.flags|=4194308),r=!1)}else{i=t.stateNode,Sa(e,t),s=t.memoizedProps,y=t.type===t.elementType?s:ot(t.type,s),i.props=y,x=t.pendingProps,k=i.context,f=n.contextType,typeof f=="object"&&f!==null?f=be(f):(f=Be(n)?bt:ze.current,f=_n(t,f));var O=n.getDerivedStateFromProps;(C=typeof O=="function"||typeof i.getSnapshotBeforeUpdate=="function")||typeof i.UNSAFE_componentWillReceiveProps!="function"&&typeof i.componentWillReceiveProps!="function"||(s!==x||k!==f)&&Ya(t,i,r,f),Bt=!1,k=t.memoizedState,i.state=k,sl(t,r,i,l);var F=t.memoizedState;s!==x||k!==F||je.current||Bt?(typeof O=="function"&&(ti(t,n,O,r),F=t.memoizedState),(y=Bt||Qa(t,n,y,r,k,F,f)||!1)?(C||typeof i.UNSAFE_componentWillUpdate!="function"&&typeof i.componentWillUpdate!="function"||(typeof i.componentWillUpdate=="function"&&i.componentWillUpdate(r,F,f),typeof i.UNSAFE_componentWillUpdate=="function"&&i.UNSAFE_componentWillUpdate(r,F,f)),typeof i.componentDidUpdate=="function"&&(t.flags|=4),typeof i.getSnapshotBeforeUpdate=="function"&&(t.flags|=1024)):(typeof i.componentDidUpdate!="function"||s===e.memoizedProps&&k===e.memoizedState||(t.flags|=4),typeof i.getSnapshotBeforeUpdate!="function"||s===e.memoizedProps&&k===e.memoizedState||(t.flags|=1024),t.memoizedProps=r,t.memoizedState=F),i.props=r,i.state=F,i.context=f,r=y):(typeof i.componentDidUpdate!="function"||s===e.memoizedProps&&k===e.memoizedState||(t.flags|=4),typeof i.getSnapshotBeforeUpdate!="function"||s===e.memoizedProps&&k===e.memoizedState||(t.flags|=1024),r=!1)}return ii(e,t,n,r,u,l)}function ii(e,t,n,r,l,u){rs(e,t);var i=(t.flags&128)!==0;if(!r&&!i)return l&&sa(t,n,!1),_t(e,t,u);r=t.stateNode,Af.current=t;var s=i&&typeof n.getDerivedStateFromError!="function"?null:r.render();return t.flags|=1,e!==null&&i?(t.child=zn(t,e.child,null,u),t.child=zn(t,null,s,u)):Ie(e,t,s,u),t.memoizedState=r.state,l&&sa(t,n,!0),t.child}function us(e){var t=e.stateNode;t.pendingContext?oa(e,t.pendingContext,t.pendingContext!==t.context):t.context&&oa(e,t.context,!1),Hu(e,t.containerInfo)}function is(e,t,n,r,l){return Rn(),Fu(l),t.flags|=256,Ie(e,t,n,r),t.child}var oi={dehydrated:null,treeContext:null,retryLane:0};function ai(e){return{baseLanes:e,cachePool:null,transitions:null}}function os(e,t,n){var r=t.pendingProps,l=pe.current,u=!1,i=(t.flags&128)!==0,s;if((s=i)||(s=e!==null&&e.memoizedState===null?!1:(l&2)!==0),s?(u=!0,t.flags&=-129):(e===null||e.memoizedState!==null)&&(l|=1),ae(pe,l&1),e===null)return Du(t),e=t.memoizedState,e!==null&&(e=e.dehydrated,e!==null)?((t.mode&1)===0?t.lanes=1:e.data==="$!"?t.lanes=8:t.lanes=1073741824,null):(i=r.children,e=r.fallback,u?(r=t.mode,u=t.child,i={mode:"hidden",children:i},(r&1)===0&&u!==null?(u.childLanes=0,u.pendingProps=i):u=Ll(i,r,0,null),e=cn(e,r,n,null),u.return=t,e.return=t,u.sibling=e,t.child=u,t.child.memoizedState=ai(n),t.memoizedState=oi,e):si(t,i));if(l=e.memoizedState,l!==null&&(s=l.dehydrated,s!==null))return Vf(e,t,i,r,s,l,n);if(u){u=r.fallback,i=t.mode,l=e.child,s=l.sibling;var f={mode:"hidden",children:r.children};return(i&1)===0&&t.child!==l?(r=t.child,r.childLanes=0,r.pendingProps=f,t.deletions=null):(r=Kt(l,f),r.subtreeFlags=l.subtreeFlags&14680064),s!==null?u=Kt(s,u):(u=cn(u,i,n,null),u.flags|=2),u.return=t,r.return=t,r.sibling=u,t.child=r,r=u,u=t.child,i=e.child.memoizedState,i=i===null?ai(n):{baseLanes:i.baseLanes|n,cachePool:null,transitions:i.transitions},u.memoizedState=i,u.childLanes=e.childLanes&~n,t.memoizedState=oi,r}return u=e.child,e=u.sibling,r=Kt(u,{mode:"visible",children:r.children}),(t.mode&1)===0&&(r.lanes=n),r.return=t,r.sibling=null,e!==null&&(n=t.deletions,n===null?(t.deletions=[e],t.flags|=16):n.push(e)),t.child=r,t.memoizedState=null,r}function si(e,t){return t=Ll({mode:"visible",children:t},e.mode,0,null),t.return=e,e.child=t}function yl(e,t,n,r){return r!==null&&Fu(r),zn(t,e.child,null,n),e=si(t,t.pendingProps.children),e.flags|=2,t.memoizedState=null,e}function Vf(e,t,n,r,l,u,i){if(n)return t.flags&256?(t.flags&=-257,r=ri(Error(a(422))),yl(e,t,i,r)):t.memoizedState!==null?(t.child=e.child,t.flags|=128,null):(u=r.fallback,l=t.mode,r=Ll({mode:"visible",children:r.children},l,0,null),u=cn(u,l,i,null),u.flags|=2,r.return=t,u.return=t,r.sibling=u,t.child=r,(t.mode&1)!==0&&zn(t,e.child,null,i),t.child.memoizedState=ai(i),t.memoizedState=oi,u);if((t.mode&1)===0)return yl(e,t,i,null);if(l.data==="$!"){if(r=l.nextSibling&&l.nextSibling.dataset,r)var s=r.dgst;return r=s,u=Error(a(419)),r=ri(u,r,void 0),yl(e,t,i,r)}if(s=(i&e.childLanes)!==0,Ae||s){if(r=_e,r!==null){switch(i&-i){case 4:l=2;break;case 16:l=8;break;case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:l=32;break;case 536870912:l=268435456;break;default:l=0}l=(l&(r.suspendedLanes|i))!==0?0:l,l!==0&&l!==u.retryLane&&(u.retryLane=l,Ct(e,l),ct(r,e,l,-1))}return _i(),r=ri(Error(a(421))),yl(e,t,i,r)}return l.data==="$?"?(t.flags|=128,t.child=e.child,t=ed.bind(null,e),l._reactRetry=t,null):(e=u.treeContext,Xe=Dt(l.nextSibling),Ye=t,de=!0,it=null,e!==null&&(Je[qe++]=kt,Je[qe++]=Et,Je[qe++]=en,kt=e.id,Et=e.overflow,en=t),t=si(t,r.children),t.flags|=4096,t)}function as(e,t,n){e.lanes|=t;var r=e.alternate;r!==null&&(r.lanes|=t),Au(e.return,t,n)}function ci(e,t,n,r,l){var u=e.memoizedState;u===null?e.memoizedState={isBackwards:t,rendering:null,renderingStartTime:0,last:r,tail:n,tailMode:l}:(u.isBackwards=t,u.rendering=null,u.renderingStartTime=0,u.last=r,u.tail=n,u.tailMode=l)}function ss(e,t,n){var r=t.pendingProps,l=r.revealOrder,u=r.tail;if(Ie(e,t,r.children,n),r=pe.current,(r&2)!==0)r=r&1|2,t.flags|=128;else{if(e!==null&&(e.flags&128)!==0)e:for(e=t.child;e!==null;){if(e.tag===13)e.memoizedState!==null&&as(e,n,t);else if(e.tag===19)as(e,n,t);else if(e.child!==null){e.child.return=e,e=e.child;continue}if(e===t)break e;for(;e.sibling===null;){if(e.return===null||e.return===t)break e;e=e.return}e.sibling.return=e.return,e=e.sibling}r&=1}if(ae(pe,r),(t.mode&1)===0)t.memoizedState=null;else switch(l){case"forwards":for(n=t.child,l=null;n!==null;)e=n.alternate,e!==null&&cl(e)===null&&(l=n),n=n.sibling;n=l,n===null?(l=t.child,t.child=null):(l=n.sibling,n.sibling=null),ci(t,!1,l,n,u);break;case"backwards":for(n=null,l=t.child,t.child=null;l!==null;){if(e=l.alternate,e!==null&&cl(e)===null){t.child=l;break}e=l.sibling,l.sibling=n,n=l,l=e}ci(t,!0,n,null,u);break;case"together":ci(t,!1,null,null,void 0);break;default:t.memoizedState=null}return t.child}function gl(e,t){(t.mode&1)===0&&e!==null&&(e.alternate=null,t.alternate=null,t.flags|=2)}function _t(e,t,n){if(e!==null&&(t.dependencies=e.dependencies),un|=t.lanes,(n&t.childLanes)===0)return null;if(e!==null&&t.child!==e.child)throw Error(a(153));if(t.child!==null){for(e=t.child,n=Kt(e,e.pendingProps),t.child=n,n.return=t;e.sibling!==null;)e=e.sibling,n=n.sibling=Kt(e,e.pendingProps),n.return=t;n.sibling=null}return t.child}function Wf(e,t,n){switch(t.tag){case 3:us(t),Rn();break;case 5:Ca(t);break;case 1:Be(t.type)&&el(t);break;case 4:Hu(t,t.stateNode.containerInfo);break;case 10:var r=t.type._context,l=t.memoizedProps.value;ae(il,r._currentValue),r._currentValue=l;break;case 13:if(r=t.memoizedState,r!==null)return r.dehydrated!==null?(ae(pe,pe.current&1),t.flags|=128,null):(n&t.child.childLanes)!==0?os(e,t,n):(ae(pe,pe.current&1),e=_t(e,t,n),e!==null?e.sibling:null);ae(pe,pe.current&1);break;case 19:if(r=(n&t.childLanes)!==0,(e.flags&128)!==0){if(r)return ss(e,t,n);t.flags|=128}if(l=t.memoizedState,l!==null&&(l.rendering=null,l.tail=null,l.lastEffect=null),ae(pe,pe.current),r)break;return null;case 22:case 23:return t.lanes=0,ns(e,t,n)}return _t(e,t,n)}var cs,fi,fs,ds;cs=function(e,t){for(var n=t.child;n!==null;){if(n.tag===5||n.tag===6)e.appendChild(n.stateNode);else if(n.tag!==4&&n.child!==null){n.child.return=n,n=n.child;continue}if(n===t)break;for(;n.sibling===null;){if(n.return===null||n.return===t)return;n=n.return}n.sibling.return=n.return,n=n.sibling}},fi=function(){},fs=function(e,t,n,r){var l=e.memoizedProps;if(l!==r){e=t.stateNode,rn(mt.current);var u=null;switch(n){case"input":l=Al(e,l),r=Al(e,r),u=[];break;case"select":l=D({},l,{value:void 0}),r=D({},r,{value:void 0}),u=[];break;case"textarea":l=Hl(e,l),r=Hl(e,r),u=[];break;default:typeof l.onClick!="function"&&typeof r.onClick=="function"&&(e.onclick=Jr)}Ql(n,r);var i;n=null;for(y in l)if(!r.hasOwnProperty(y)&&l.hasOwnProperty(y)&&l[y]!=null)if(y==="style"){var s=l[y];for(i in s)s.hasOwnProperty(i)&&(n||(n={}),n[i]="")}else y!=="dangerouslySetInnerHTML"&&y!=="children"&&y!=="suppressContentEditableWarning"&&y!=="suppressHydrationWarning"&&y!=="autoFocus"&&(g.hasOwnProperty(y)?u||(u=[]):(u=u||[]).push(y,null));for(y in r){var f=r[y];if(s=l!=null?l[y]:void 0,r.hasOwnProperty(y)&&f!==s&&(f!=null||s!=null))if(y==="style")if(s){for(i in s)!s.hasOwnProperty(i)||f&&f.hasOwnProperty(i)||(n||(n={}),n[i]="");for(i in f)f.hasOwnProperty(i)&&s[i]!==f[i]&&(n||(n={}),n[i]=f[i])}else n||(u||(u=[]),u.push(y,n)),n=f;else y==="dangerouslySetInnerHTML"?(f=f?f.__html:void 0,s=s?s.__html:void 0,f!=null&&s!==f&&(u=u||[]).push(y,f)):y==="children"?typeof f!="string"&&typeof f!="number"||(u=u||[]).push(y,""+f):y!=="suppressContentEditableWarning"&&y!=="suppressHydrationWarning"&&(g.hasOwnProperty(y)?(f!=null&&y==="onScroll"&&se("scroll",e),u||s===f||(u=[])):(u=u||[]).push(y,f))}n&&(u=u||[]).push("style",n);var y=u;(t.updateQueue=y)&&(t.flags|=4)}},ds=function(e,t,n,r){n!==r&&(t.flags|=4)};function yr(e,t){if(!de)switch(e.tailMode){case"hidden":t=e.tail;for(var n=null;t!==null;)t.alternate!==null&&(n=t),t=t.sibling;n===null?e.tail=null:n.sibling=null;break;case"collapsed":n=e.tail;for(var r=null;n!==null;)n.alternate!==null&&(r=n),n=n.sibling;r===null?t||e.tail===null?e.tail=null:e.tail.sibling=null:r.sibling=null}}function Te(e){var t=e.alternate!==null&&e.alternate.child===e.child,n=0,r=0;if(t)for(var l=e.child;l!==null;)n|=l.lanes|l.childLanes,r|=l.subtreeFlags&14680064,r|=l.flags&14680064,l.return=e,l=l.sibling;else for(l=e.child;l!==null;)n|=l.lanes|l.childLanes,r|=l.subtreeFlags,r|=l.flags,l.return=e,l=l.sibling;return e.subtreeFlags|=r,e.childLanes=n,t}function Hf(e,t,n){var r=t.pendingProps;switch(Mu(t),t.tag){case 2:case 16:case 15:case 0:case 11:case 7:case 8:case 12:case 9:case 14:return Te(t),null;case 1:return Be(t.type)&&br(),Te(t),null;case 3:return r=t.stateNode,On(),ce(je),ce(ze),Ku(),r.pendingContext&&(r.context=r.pendingContext,r.pendingContext=null),(e===null||e.child===null)&&(ll(t)?t.flags|=4:e===null||e.memoizedState.isDehydrated&&(t.flags&256)===0||(t.flags|=1024,it!==null&&(Ei(it),it=null))),fi(e,t),Te(t),null;case 5:$u(t);var l=rn(dr.current);if(n=t.type,e!==null&&t.stateNode!=null)fs(e,t,n,r,l),e.ref!==t.ref&&(t.flags|=512,t.flags|=2097152);else{if(!r){if(t.stateNode===null)throw Error(a(166));return Te(t),null}if(e=rn(mt.current),ll(t)){r=t.stateNode,n=t.type;var u=t.memoizedProps;switch(r[ht]=t,r[or]=u,e=(t.mode&1)!==0,n){case"dialog":se("cancel",r),se("close",r);break;case"iframe":case"object":case"embed":se("load",r);break;case"video":case"audio":for(l=0;l<\/script>",e=e.removeChild(e.firstChild)):typeof r.is=="string"?e=i.createElement(n,{is:r.is}):(e=i.createElement(n),n==="select"&&(i=e,r.multiple?i.multiple=!0:r.size&&(i.size=r.size))):e=i.createElementNS(e,n),e[ht]=t,e[or]=r,cs(e,t,!1,!1),t.stateNode=e;e:{switch(i=Kl(n,r),n){case"dialog":se("cancel",e),se("close",e),l=r;break;case"iframe":case"object":case"embed":se("load",e),l=r;break;case"video":case"audio":for(l=0;lFn&&(t.flags|=128,r=!0,yr(u,!1),t.lanes=4194304)}else{if(!r)if(e=cl(i),e!==null){if(t.flags|=128,r=!0,n=e.updateQueue,n!==null&&(t.updateQueue=n,t.flags|=4),yr(u,!0),u.tail===null&&u.tailMode==="hidden"&&!i.alternate&&!de)return Te(t),null}else 2*ye()-u.renderingStartTime>Fn&&n!==1073741824&&(t.flags|=128,r=!0,yr(u,!1),t.lanes=4194304);u.isBackwards?(i.sibling=t.child,t.child=i):(n=u.last,n!==null?n.sibling=i:t.child=i,u.last=i)}return u.tail!==null?(t=u.tail,u.rendering=t,u.tail=t.sibling,u.renderingStartTime=ye(),t.sibling=null,n=pe.current,ae(pe,r?n&1|2:n&1),t):(Te(t),null);case 22:case 23:return xi(),r=t.memoizedState!==null,e!==null&&e.memoizedState!==null!==r&&(t.flags|=8192),r&&(t.mode&1)!==0?(Ge&1073741824)!==0&&(Te(t),t.subtreeFlags&6&&(t.flags|=8192)):Te(t),null;case 24:return null;case 25:return null}throw Error(a(156,t.tag))}function $f(e,t){switch(Mu(t),t.tag){case 1:return Be(t.type)&&br(),e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 3:return On(),ce(je),ce(ze),Ku(),e=t.flags,(e&65536)!==0&&(e&128)===0?(t.flags=e&-65537|128,t):null;case 5:return $u(t),null;case 13:if(ce(pe),e=t.memoizedState,e!==null&&e.dehydrated!==null){if(t.alternate===null)throw Error(a(340));Rn()}return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 19:return ce(pe),null;case 4:return On(),null;case 10:return Bu(t.type._context),null;case 22:case 23:return xi(),null;case 24:return null;default:return null}}var wl=!1,Oe=!1,Qf=typeof WeakSet=="function"?WeakSet:Set,I=null;function In(e,t){var n=e.ref;if(n!==null)if(typeof n=="function")try{n(null)}catch(r){ve(e,t,r)}else n.current=null}function di(e,t,n){try{n()}catch(r){ve(e,t,r)}}var ps=!1;function Kf(e,t){if(xu=Br,e=Qo(),vu(e)){if("selectionStart"in e)var n={start:e.selectionStart,end:e.selectionEnd};else e:{n=(n=e.ownerDocument)&&n.defaultView||window;var r=n.getSelection&&n.getSelection();if(r&&r.rangeCount!==0){n=r.anchorNode;var l=r.anchorOffset,u=r.focusNode;r=r.focusOffset;try{n.nodeType,u.nodeType}catch{n=null;break e}var i=0,s=-1,f=-1,y=0,C=0,x=e,k=null;t:for(;;){for(var O;x!==n||l!==0&&x.nodeType!==3||(s=i+l),x!==u||r!==0&&x.nodeType!==3||(f=i+r),x.nodeType===3&&(i+=x.nodeValue.length),(O=x.firstChild)!==null;)k=x,x=O;for(;;){if(x===e)break t;if(k===n&&++y===l&&(s=i),k===u&&++C===r&&(f=i),(O=x.nextSibling)!==null)break;x=k,k=x.parentNode}x=O}n=s===-1||f===-1?null:{start:s,end:f}}else n=null}n=n||{start:0,end:0}}else n=null;for(_u={focusedElem:e,selectionRange:n},Br=!1,I=t;I!==null;)if(t=I,e=t.child,(t.subtreeFlags&1028)!==0&&e!==null)e.return=t,I=e;else for(;I!==null;){t=I;try{var F=t.alternate;if((t.flags&1024)!==0)switch(t.tag){case 0:case 11:case 15:break;case 1:if(F!==null){var U=F.memoizedProps,ge=F.memoizedState,m=t.stateNode,d=m.getSnapshotBeforeUpdate(t.elementType===t.type?U:ot(t.type,U),ge);m.__reactInternalSnapshotBeforeUpdate=d}break;case 3:var v=t.stateNode.containerInfo;v.nodeType===1?v.textContent="":v.nodeType===9&&v.documentElement&&v.removeChild(v.documentElement);break;case 5:case 6:case 4:case 17:break;default:throw Error(a(163))}}catch(P){ve(t,t.return,P)}if(e=t.sibling,e!==null){e.return=t.return,I=e;break}I=t.return}return F=ps,ps=!1,F}function gr(e,t,n){var r=t.updateQueue;if(r=r!==null?r.lastEffect:null,r!==null){var l=r=r.next;do{if((l.tag&e)===e){var u=l.destroy;l.destroy=void 0,u!==void 0&&di(t,n,u)}l=l.next}while(l!==r)}}function Sl(e,t){if(t=t.updateQueue,t=t!==null?t.lastEffect:null,t!==null){var n=t=t.next;do{if((n.tag&e)===e){var r=n.create;n.destroy=r()}n=n.next}while(n!==t)}}function pi(e){var t=e.ref;if(t!==null){var n=e.stateNode;switch(e.tag){case 5:e=n;break;default:e=n}typeof t=="function"?t(e):t.current=e}}function hs(e){var t=e.alternate;t!==null&&(e.alternate=null,hs(t)),e.child=null,e.deletions=null,e.sibling=null,e.tag===5&&(t=e.stateNode,t!==null&&(delete t[ht],delete t[or],delete t[zu],delete t[Rf],delete t[zf])),e.stateNode=null,e.return=null,e.dependencies=null,e.memoizedProps=null,e.memoizedState=null,e.pendingProps=null,e.stateNode=null,e.updateQueue=null}function ms(e){return e.tag===5||e.tag===3||e.tag===4}function vs(e){e:for(;;){for(;e.sibling===null;){if(e.return===null||ms(e.return))return null;e=e.return}for(e.sibling.return=e.return,e=e.sibling;e.tag!==5&&e.tag!==6&&e.tag!==18;){if(e.flags&2||e.child===null||e.tag===4)continue e;e.child.return=e,e=e.child}if(!(e.flags&2))return e.stateNode}}function hi(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.nodeType===8?n.parentNode.insertBefore(e,t):n.insertBefore(e,t):(n.nodeType===8?(t=n.parentNode,t.insertBefore(e,n)):(t=n,t.appendChild(e)),n=n._reactRootContainer,n!=null||t.onclick!==null||(t.onclick=Jr));else if(r!==4&&(e=e.child,e!==null))for(hi(e,t,n),e=e.sibling;e!==null;)hi(e,t,n),e=e.sibling}function mi(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.insertBefore(e,t):n.appendChild(e);else if(r!==4&&(e=e.child,e!==null))for(mi(e,t,n),e=e.sibling;e!==null;)mi(e,t,n),e=e.sibling}var Ne=null,at=!1;function Vt(e,t,n){for(n=n.child;n!==null;)ys(e,t,n),n=n.sibling}function ys(e,t,n){if(pt&&typeof pt.onCommitFiberUnmount=="function")try{pt.onCommitFiberUnmount(Mr,n)}catch{}switch(n.tag){case 5:Oe||In(n,t);case 6:var r=Ne,l=at;Ne=null,Vt(e,t,n),Ne=r,at=l,Ne!==null&&(at?(e=Ne,n=n.stateNode,e.nodeType===8?e.parentNode.removeChild(n):e.removeChild(n)):Ne.removeChild(n.stateNode));break;case 18:Ne!==null&&(at?(e=Ne,n=n.stateNode,e.nodeType===8?Ru(e.parentNode,n):e.nodeType===1&&Ru(e,n),Zn(e)):Ru(Ne,n.stateNode));break;case 4:r=Ne,l=at,Ne=n.stateNode.containerInfo,at=!0,Vt(e,t,n),Ne=r,at=l;break;case 0:case 11:case 14:case 15:if(!Oe&&(r=n.updateQueue,r!==null&&(r=r.lastEffect,r!==null))){l=r=r.next;do{var u=l,i=u.destroy;u=u.tag,i!==void 0&&((u&2)!==0||(u&4)!==0)&&di(n,t,i),l=l.next}while(l!==r)}Vt(e,t,n);break;case 1:if(!Oe&&(In(n,t),r=n.stateNode,typeof r.componentWillUnmount=="function"))try{r.props=n.memoizedProps,r.state=n.memoizedState,r.componentWillUnmount()}catch(s){ve(n,t,s)}Vt(e,t,n);break;case 21:Vt(e,t,n);break;case 22:n.mode&1?(Oe=(r=Oe)||n.memoizedState!==null,Vt(e,t,n),Oe=r):Vt(e,t,n);break;default:Vt(e,t,n)}}function gs(e){var t=e.updateQueue;if(t!==null){e.updateQueue=null;var n=e.stateNode;n===null&&(n=e.stateNode=new Qf),t.forEach(function(r){var l=td.bind(null,e,r);n.has(r)||(n.add(r),r.then(l,l))})}}function st(e,t){var n=t.deletions;if(n!==null)for(var r=0;rl&&(l=i),r&=~u}if(r=l,r=ye()-r,r=(120>r?120:480>r?480:1080>r?1080:1920>r?1920:3e3>r?3e3:4320>r?4320:1960*Xf(r/1960))-r,10e?16:e,Ht===null)var r=!1;else{if(e=Ht,Ht=null,_l=0,(Z&6)!==0)throw Error(a(331));var l=Z;for(Z|=4,I=e.current;I!==null;){var u=I,i=u.child;if((I.flags&16)!==0){var s=u.deletions;if(s!==null){for(var f=0;fye()-gi?an(e,0):yi|=n),We(e,t)}function Ts(e,t){t===0&&((e.mode&1)===0?t=1:(t=Dr,Dr<<=1,(Dr&130023424)===0&&(Dr=4194304)));var n=De();e=Ct(e,t),e!==null&&(Qn(e,t,n),We(e,n))}function ed(e){var t=e.memoizedState,n=0;t!==null&&(n=t.retryLane),Ts(e,n)}function td(e,t){var n=0;switch(e.tag){case 13:var r=e.stateNode,l=e.memoizedState;l!==null&&(n=l.retryLane);break;case 19:r=e.stateNode;break;default:throw Error(a(314))}r!==null&&r.delete(t),Ts(e,n)}var Os;Os=function(e,t,n){if(e!==null)if(e.memoizedProps!==t.pendingProps||je.current)Ae=!0;else{if((e.lanes&n)===0&&(t.flags&128)===0)return Ae=!1,Wf(e,t,n);Ae=(e.flags&131072)!==0}else Ae=!1,de&&(t.flags&1048576)!==0&&fa(t,rl,t.index);switch(t.lanes=0,t.tag){case 2:var r=t.type;gl(e,t),e=t.pendingProps;var l=_n(t,ze.current);Tn(t,n),l=Gu(null,t,r,e,l,n);var u=Zu();return t.flags|=1,typeof l=="object"&&l!==null&&typeof l.render=="function"&&l.$$typeof===void 0?(t.tag=1,t.memoizedState=null,t.updateQueue=null,Be(r)?(u=!0,el(t)):u=!1,t.memoizedState=l.state!==null&&l.state!==void 0?l.state:null,Wu(t),l.updater=vl,t.stateNode=l,l._reactInternals=t,ni(t,r,e,n),t=ii(null,t,r,!0,u,n)):(t.tag=0,de&&u&&Ou(t),Ie(null,t,l,n),t=t.child),t;case 16:r=t.elementType;e:{switch(gl(e,t),e=t.pendingProps,l=r._init,r=l(r._payload),t.type=r,l=t.tag=rd(r),e=ot(r,e),l){case 0:t=ui(null,t,r,e,n);break e;case 1:t=ls(null,t,r,e,n);break e;case 11:t=ba(null,t,r,e,n);break e;case 14:t=es(null,t,r,ot(r.type,e),n);break e}throw Error(a(306,r,""))}return t;case 0:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ui(e,t,r,l,n);case 1:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ls(e,t,r,l,n);case 3:e:{if(us(t),e===null)throw Error(a(387));r=t.pendingProps,u=t.memoizedState,l=u.element,Sa(e,t),sl(t,r,null,n);var i=t.memoizedState;if(r=i.element,u.isDehydrated)if(u={element:r,isDehydrated:!1,cache:i.cache,pendingSuspenseBoundaries:i.pendingSuspenseBoundaries,transitions:i.transitions},t.updateQueue.baseState=u,t.memoizedState=u,t.flags&256){l=Mn(Error(a(423)),t),t=is(e,t,r,n,l);break e}else if(r!==l){l=Mn(Error(a(424)),t),t=is(e,t,r,n,l);break e}else for(Xe=Dt(t.stateNode.containerInfo.firstChild),Ye=t,de=!0,it=null,n=ga(t,null,r,n),t.child=n;n;)n.flags=n.flags&-3|4096,n=n.sibling;else{if(Rn(),r===l){t=_t(e,t,n);break e}Ie(e,t,r,n)}t=t.child}return t;case 5:return Ca(t),e===null&&Du(t),r=t.type,l=t.pendingProps,u=e!==null?e.memoizedProps:null,i=l.children,Pu(r,l)?i=null:u!==null&&Pu(r,u)&&(t.flags|=32),rs(e,t),Ie(e,t,i,n),t.child;case 6:return e===null&&Du(t),null;case 13:return os(e,t,n);case 4:return Hu(t,t.stateNode.containerInfo),r=t.pendingProps,e===null?t.child=zn(t,null,r,n):Ie(e,t,r,n),t.child;case 11:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),ba(e,t,r,l,n);case 7:return Ie(e,t,t.pendingProps,n),t.child;case 8:return Ie(e,t,t.pendingProps.children,n),t.child;case 12:return Ie(e,t,t.pendingProps.children,n),t.child;case 10:e:{if(r=t.type._context,l=t.pendingProps,u=t.memoizedProps,i=l.value,ae(il,r._currentValue),r._currentValue=i,u!==null)if(ut(u.value,i)){if(u.children===l.children&&!je.current){t=_t(e,t,n);break e}}else for(u=t.child,u!==null&&(u.return=t);u!==null;){var s=u.dependencies;if(s!==null){i=u.child;for(var f=s.firstContext;f!==null;){if(f.context===r){if(u.tag===1){f=xt(-1,n&-n),f.tag=2;var y=u.updateQueue;if(y!==null){y=y.shared;var C=y.pending;C===null?f.next=f:(f.next=C.next,C.next=f),y.pending=f}}u.lanes|=n,f=u.alternate,f!==null&&(f.lanes|=n),Au(u.return,n,t),s.lanes|=n;break}f=f.next}}else if(u.tag===10)i=u.type===t.type?null:u.child;else if(u.tag===18){if(i=u.return,i===null)throw Error(a(341));i.lanes|=n,s=i.alternate,s!==null&&(s.lanes|=n),Au(i,n,t),i=u.sibling}else i=u.child;if(i!==null)i.return=u;else for(i=u;i!==null;){if(i===t){i=null;break}if(u=i.sibling,u!==null){u.return=i.return,i=u;break}i=i.return}u=i}Ie(e,t,l.children,n),t=t.child}return t;case 9:return l=t.type,r=t.pendingProps.children,Tn(t,n),l=be(l),r=r(l),t.flags|=1,Ie(e,t,r,n),t.child;case 14:return r=t.type,l=ot(r,t.pendingProps),l=ot(r.type,l),es(e,t,r,l,n);case 15:return ts(e,t,t.type,t.pendingProps,n);case 17:return r=t.type,l=t.pendingProps,l=t.elementType===r?l:ot(r,l),gl(e,t),t.tag=1,Be(r)?(e=!0,el(t)):e=!1,Tn(t,n),Ka(t,r,l),ni(t,r,l,n),ii(null,t,r,!0,e,n);case 19:return ss(e,t,n);case 22:return ns(e,t,n)}throw Error(a(156,t.tag))};function Ms(e,t){return fo(e,t)}function nd(e,t,n,r){this.tag=e,this.key=n,this.sibling=this.child=this.return=this.stateNode=this.type=this.elementType=null,this.index=0,this.ref=null,this.pendingProps=t,this.dependencies=this.memoizedState=this.updateQueue=this.memoizedProps=null,this.mode=r,this.subtreeFlags=this.flags=0,this.deletions=null,this.childLanes=this.lanes=0,this.alternate=null}function nt(e,t,n,r){return new nd(e,t,n,r)}function Pi(e){return e=e.prototype,!(!e||!e.isReactComponent)}function rd(e){if(typeof e=="function")return Pi(e)?1:0;if(e!=null){if(e=e.$$typeof,e===ft)return 11;if(e===dt)return 14}return 2}function Kt(e,t){var n=e.alternate;return n===null?(n=nt(e.tag,t,e.key,e.mode),n.elementType=e.elementType,n.type=e.type,n.stateNode=e.stateNode,n.alternate=e,e.alternate=n):(n.pendingProps=t,n.type=e.type,n.flags=0,n.subtreeFlags=0,n.deletions=null),n.flags=e.flags&14680064,n.childLanes=e.childLanes,n.lanes=e.lanes,n.child=e.child,n.memoizedProps=e.memoizedProps,n.memoizedState=e.memoizedState,n.updateQueue=e.updateQueue,t=e.dependencies,n.dependencies=t===null?null:{lanes:t.lanes,firstContext:t.firstContext},n.sibling=e.sibling,n.index=e.index,n.ref=e.ref,n}function zl(e,t,n,r,l,u){var i=2;if(r=e,typeof e=="function")Pi(e)&&(i=1);else if(typeof e=="string")i=5;else e:switch(e){case Fe:return cn(n.children,l,u,t);case Ze:i=8,l|=8;break;case Rt:return e=nt(12,n,t,l|2),e.elementType=Rt,e.lanes=u,e;case $e:return e=nt(13,n,t,l),e.elementType=$e,e.lanes=u,e;case rt:return e=nt(19,n,t,l),e.elementType=rt,e.lanes=u,e;case me:return Ll(n,l,u,t);default:if(typeof e=="object"&&e!==null)switch(e.$$typeof){case gt:i=10;break e;case Zt:i=9;break e;case ft:i=11;break e;case dt:i=14;break e;case Ue:i=16,r=null;break e}throw Error(a(130,e==null?e:typeof e,""))}return t=nt(i,n,t,l),t.elementType=e,t.type=r,t.lanes=u,t}function cn(e,t,n,r){return e=nt(7,e,r,t),e.lanes=n,e}function Ll(e,t,n,r){return e=nt(22,e,r,t),e.elementType=me,e.lanes=n,e.stateNode={isHidden:!1},e}function Ni(e,t,n){return e=nt(6,e,null,t),e.lanes=n,e}function Ri(e,t,n){return t=nt(4,e.children!==null?e.children:[],e.key,t),t.lanes=n,t.stateNode={containerInfo:e.containerInfo,pendingChildren:null,implementation:e.implementation},t}function ld(e,t,n,r,l){this.tag=t,this.containerInfo=e,this.finishedWork=this.pingCache=this.current=this.pendingChildren=null,this.timeoutHandle=-1,this.callbackNode=this.pendingContext=this.context=null,this.callbackPriority=0,this.eventTimes=tu(0),this.expirationTimes=tu(-1),this.entangledLanes=this.finishedLanes=this.mutableReadLanes=this.expiredLanes=this.pingedLanes=this.suspendedLanes=this.pendingLanes=0,this.entanglements=tu(0),this.identifierPrefix=r,this.onRecoverableError=l,this.mutableSourceEagerHydrationData=null}function zi(e,t,n,r,l,u,i,s,f){return e=new ld(e,t,n,s,f),t===1?(t=1,u===!0&&(t|=8)):t=0,u=nt(3,null,null,t),e.current=u,u.stateNode=e,u.memoizedState={element:r,isDehydrated:n,cache:null,transitions:null,pendingSuspenseBoundaries:null},Wu(u),e}function ud(e,t,n){var r=3"u"||typeof __REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE!="function"))try{__REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE(o)}catch(c){console.error(c)}}return o(),Ii.exports=gd(),Ii.exports}var _p=wd();/** + * @remix-run/router v1.23.3 * * Copyright (c) Remix Software Inc. * @@ -38,8 +38,8 @@ Error generating stack: `+u.message+` * LICENSE.md file in the root directory of this source tree. * * @license MIT - */function Cr(){return Cr=Object.assign?Object.assign.bind():function(o){for(var c=1;c"u")throw new Error(c)}function jl(o,c){if(!o){typeof console<"u"&&console.warn(c);try{throw new Error(c)}catch{}}}function Sd(){return Math.random().toString(36).substr(2,8)}function Ks(o,c){return{usr:o.state,key:o.key,idx:c}}function ji(o,c,a,p){return a===void 0&&(a=null),Cr({pathname:typeof o=="string"?o:o.pathname,search:"",hash:""},typeof c=="string"?fn(c):c,{state:a,key:c&&c.key||p||Sd()})}function Ul(o){let{pathname:c="/",search:a="",hash:p=""}=o;return a&&a!=="?"&&(c+=a.charAt(0)==="?"?a:"?"+a),p&&p!=="#"&&(c+=p.charAt(0)==="#"?p:"#"+p),c}function fn(o){let c={};if(o){let a=o.indexOf("#");a>=0&&(c.hash=o.substr(a),o=o.substr(0,a));let p=o.indexOf("?");p>=0&&(c.search=o.substr(p),o=o.substr(0,p)),o&&(c.pathname=o)}return c}function kd(o,c,a,p){p===void 0&&(p={});let{window:g=document.defaultView,v5Compat:w=!1}=p,S=g.history,N=Xt.Pop,x=null,z=B();z==null&&(z=0,S.replaceState(Cr({},S.state,{idx:z}),""));function B(){return(S.state||{idx:null}).idx}function R(){N=Xt.Pop;let L=B(),le=L==null?null:L-z;z=L,x&&x({action:N,location:H.location,delta:le})}function W(L,le){N=Xt.Push;let ue=ji(H.location,L,le);a&&a(ue,L),z=B()+1;let ee=Ks(ue,z),ie=H.createHref(ue);try{S.pushState(ee,"",ie)}catch(Ce){if(Ce instanceof DOMException&&Ce.name==="DataCloneError")throw Ce;g.location.assign(ie)}w&&x&&x({action:N,location:H.location,delta:1})}function re(L,le){N=Xt.Replace;let ue=ji(H.location,L,le);a&&a(ue,L),z=B();let ee=Ks(ue,z),ie=H.createHref(ue);S.replaceState(ee,"",ie),w&&x&&x({action:N,location:H.location,delta:0})}function G(L){let le=g.location.origin!=="null"?g.location.origin:g.location.href,ue=typeof L=="string"?L:Ul(L);return ue=ue.replace(/ $/,"%20"),Se(le,"No window.location.(origin|href) available to create URL for href: "+ue),new URL(ue,le)}let H={get action(){return N},get location(){return o(g,S)},listen(L){if(x)throw new Error("A history only accepts one active listener");return g.addEventListener(Qs,R),x=L,()=>{g.removeEventListener(Qs,R),x=null}},createHref(L){return c(g,L)},createURL:G,encodeLocation(L){let le=G(L);return{pathname:le.pathname,search:le.search,hash:le.hash}},push:W,replace:re,go(L){return S.go(L)}};return H}var Ys;(function(o){o.data="data",o.deferred="deferred",o.redirect="redirect",o.error="error"})(Ys||(Ys={}));function Ed(o,c,a){return a===void 0&&(a="/"),Cd(o,c,a)}function Cd(o,c,a,p){let g=typeof c=="string"?fn(c):c,w=Wi(g.pathname||"/",a);if(w==null)return null;let S=tc(o);xd(S);let N=null;for(let x=0;N==null&&x{let x={relativePath:N===void 0?w.path||"":N,caseSensitive:w.caseSensitive===!0,childrenIndex:S,route:w};x.relativePath.startsWith("/")&&(Se(x.relativePath.startsWith(p),'Absolute route path "'+x.relativePath+'" nested under path '+('"'+p+'" is not valid. An absolute child route path ')+"must start with the combined path of all its parent routes."),x.relativePath=x.relativePath.slice(p.length));let z=Gt([p,x.relativePath]),B=a.concat(x);w.children&&w.children.length>0&&(Se(w.index!==!0,"Index routes must not have child routes. Please remove "+('all child routes from route path "'+z+'".')),tc(w.children,c,B,z)),!(w.path==null&&!w.index)&&c.push({path:z,score:Td(z,w.index),routesMeta:B})};return o.forEach((w,S)=>{var N;if(w.path===""||!((N=w.path)!=null&&N.includes("?")))g(w,S);else for(let x of nc(w.path))g(w,S,x)}),c}function nc(o){let c=o.split("/");if(c.length===0)return[];let[a,...p]=c,g=a.endsWith("?"),w=a.replace(/\?$/,"");if(p.length===0)return g?[w,""]:[w];let S=nc(p.join("/")),N=[];return N.push(...S.map(x=>x===""?w:[w,x].join("/"))),g&&N.push(...S),N.map(x=>o.startsWith("/")&&x===""?"/":x)}function xd(o){o.sort((c,a)=>c.score!==a.score?a.score-c.score:Od(c.routesMeta.map(p=>p.childrenIndex),a.routesMeta.map(p=>p.childrenIndex)))}const _d=/^:[\w-]+$/,Pd=3,Nd=2,Rd=1,zd=10,Ld=-2,Xs=o=>o==="*";function Td(o,c){let a=o.split("/"),p=a.length;return a.some(Xs)&&(p+=Ld),c&&(p+=Nd),a.filter(g=>!Xs(g)).reduce((g,w)=>g+(_d.test(w)?Pd:w===""?Rd:zd),p)}function Od(o,c){return o.length===c.length&&o.slice(0,-1).every((p,g)=>p===c[g])?o[o.length-1]-c[c.length-1]:0}function Md(o,c,a){let{routesMeta:p}=o,g={},w="/",S=[];for(let N=0;N{let{paramName:W,isOptional:re}=B;if(W==="*"){let H=N[R]||"";S=w.slice(0,w.length-H.length).replace(/(.)\/+$/,"$1")}const G=N[R];return re&&!G?z[W]=void 0:z[W]=(G||"").replace(/%2F/g,"/"),z},{}),pathname:w,pathnameBase:S,pattern:o}}function Dd(o,c,a){c===void 0&&(c=!1),a===void 0&&(a=!0),jl(o==="*"||!o.endsWith("*")||o.endsWith("/*"),'Route path "'+o+'" will be treated as if it were '+('"'+o.replace(/\*$/,"/*")+'" because the `*` character must ')+"always follow a `/` in the pattern. To get rid of this warning, "+('please change the route path to "'+o.replace(/\*$/,"/*")+'".'));let p=[],g="^"+o.replace(/\/*\*?$/,"").replace(/^\/*/,"/").replace(/[\\.*+^${}|()[\]]/g,"\\$&").replace(/\/:([\w-]+)(\?)?/g,(S,N,x)=>(p.push({paramName:N,isOptional:x!=null}),x?"/?([^\\/]+)?":"/([^\\/]+)"));return o.endsWith("*")?(p.push({paramName:"*"}),g+=o==="*"||o==="/*"?"(.*)$":"(?:\\/(.+)|\\/*)$"):a?g+="\\/*$":o!==""&&o!=="/"&&(g+="(?:(?=\\/|$))"),[new RegExp(g,c?void 0:"i"),p]}function Fd(o){try{return o.split("/").map(c=>decodeURIComponent(c).replace(/\//g,"%2F")).join("/")}catch(c){return jl(!1,'The URL path "'+o+'" could not be decoded because it is is a malformed URL segment. This is probably due to a bad percent '+("encoding ("+c+").")),o}}function Wi(o,c){if(c==="/")return o;if(!o.toLowerCase().startsWith(c.toLowerCase()))return null;let a=c.endsWith("/")?c.length-1:c.length,p=o.charAt(a);return p&&p!=="/"?null:o.slice(a)||"/"}const Ud=/^(?:[a-z][a-z0-9+.-]*:|\/\/)/i,jd=o=>Ud.test(o);function Bd(o,c){c===void 0&&(c="/");let{pathname:a,search:p="",hash:g=""}=typeof o=="string"?fn(o):o,w;if(a)if(jd(a))w=a;else{if(a.includes("//")){let S=a;a=a.replace(/\/\/+/g,"/"),jl(!1,"Pathnames cannot have embedded double slashes - normalizing "+(S+" -> "+a))}a.startsWith("/")?w=Gs(a.substring(1),"/"):w=Gs(a,c)}else w=c;return{pathname:w,search:Wd(p),hash:Hd(g)}}function Gs(o,c){let a=c.replace(/\/+$/,"").split("/");return o.split("/").forEach(g=>{g===".."?a.length>1&&a.pop():g!=="."&&a.push(g)}),a.length>1?a.join("/"):"/"}function Ui(o,c,a,p){return"Cannot include a '"+o+"' character in a manually specified "+("`to."+c+"` field ["+JSON.stringify(p)+"]. Please separate it out to the ")+("`to."+a+"` field. Alternatively you may provide the full path as ")+'a string in and the router will parse it for you.'}function Ad(o){return o.filter((c,a)=>a===0||c.route.path&&c.route.path.length>0)}function rc(o,c){let a=Ad(o);return c?a.map((p,g)=>g===a.length-1?p.pathname:p.pathnameBase):a.map(p=>p.pathnameBase)}function lc(o,c,a,p){p===void 0&&(p=!1);let g;typeof o=="string"?g=fn(o):(g=Cr({},o),Se(!g.pathname||!g.pathname.includes("?"),Ui("?","pathname","search",g)),Se(!g.pathname||!g.pathname.includes("#"),Ui("#","pathname","hash",g)),Se(!g.search||!g.search.includes("#"),Ui("#","search","hash",g)));let w=o===""||g.pathname==="",S=w?"/":g.pathname,N;if(S==null)N=a;else{let R=c.length-1;if(!p&&S.startsWith("..")){let W=S.split("/");for(;W[0]==="..";)W.shift(),R-=1;g.pathname=W.join("/")}N=R>=0?c[R]:"/"}let x=Bd(g,N),z=S&&S!=="/"&&S.endsWith("/"),B=(w||S===".")&&a.endsWith("/");return!x.pathname.endsWith("/")&&(z||B)&&(x.pathname+="/"),x}const Gt=o=>o.join("/").replace(/\/\/+/g,"/"),Vd=o=>o.replace(/\/+$/,"").replace(/^\/*/,"/"),Wd=o=>!o||o==="?"?"":o.startsWith("?")?o:"?"+o,Hd=o=>!o||o==="#"?"":o.startsWith("#")?o:"#"+o;function $d(o){return o!=null&&typeof o.status=="number"&&typeof o.statusText=="string"&&typeof o.internal=="boolean"&&"data"in o}const uc=["post","put","patch","delete"];new Set(uc);const Qd=["get",...uc];new Set(Qd);/** - * React Router v6.30.3 + */function Cr(){return Cr=Object.assign?Object.assign.bind():function(o){for(var c=1;c"u")throw new Error(c)}function jl(o,c){if(!o){typeof console<"u"&&console.warn(c);try{throw new Error(c)}catch{}}}function kd(){return Math.random().toString(36).substr(2,8)}function Ks(o,c){return{usr:o.state,key:o.key,idx:c}}function ji(o,c,a,p){return a===void 0&&(a=null),Cr({pathname:typeof o=="string"?o:o.pathname,search:"",hash:""},typeof c=="string"?fn(c):c,{state:a,key:c&&c.key||p||kd()})}function Ul(o){let{pathname:c="/",search:a="",hash:p=""}=o;return a&&a!=="?"&&(c+=a.charAt(0)==="?"?a:"?"+a),p&&p!=="#"&&(c+=p.charAt(0)==="#"?p:"#"+p),c}function fn(o){let c={};if(o){let a=o.indexOf("#");a>=0&&(c.hash=o.substr(a),o=o.substr(0,a));let p=o.indexOf("?");p>=0&&(c.search=o.substr(p),o=o.substr(0,p)),o&&(c.pathname=o)}return c}function Ed(o,c,a,p){p===void 0&&(p={});let{window:g=document.defaultView,v5Compat:w=!1}=p,S=g.history,N=Xt.Pop,_=null,z=B();z==null&&(z=0,S.replaceState(Cr({},S.state,{idx:z}),""));function B(){return(S.state||{idx:null}).idx}function R(){N=Xt.Pop;let L=B(),le=L==null?null:L-z;z=L,_&&_({action:N,location:H.location,delta:le})}function W(L,le){N=Xt.Push;let ue=ji(H.location,L,le);a&&a(ue,L),z=B()+1;let ee=Ks(ue,z),ie=H.createHref(ue);try{S.pushState(ee,"",ie)}catch(Ce){if(Ce instanceof DOMException&&Ce.name==="DataCloneError")throw Ce;g.location.assign(ie)}w&&_&&_({action:N,location:H.location,delta:1})}function re(L,le){N=Xt.Replace;let ue=ji(H.location,L,le);a&&a(ue,L),z=B();let ee=Ks(ue,z),ie=H.createHref(ue);S.replaceState(ee,"",ie),w&&_&&_({action:N,location:H.location,delta:0})}function G(L){let le=g.location.origin!=="null"?g.location.origin:g.location.href,ue=typeof L=="string"?L:Ul(L);return ue=ue.replace(/ $/,"%20"),Se(le,"No window.location.(origin|href) available to create URL for href: "+ue),new URL(ue,le)}let H={get action(){return N},get location(){return o(g,S)},listen(L){if(_)throw new Error("A history only accepts one active listener");return g.addEventListener(Qs,R),_=L,()=>{g.removeEventListener(Qs,R),_=null}},createHref(L){return c(g,L)},createURL:G,encodeLocation(L){let le=G(L);return{pathname:le.pathname,search:le.search,hash:le.hash}},push:W,replace:re,go(L){return S.go(L)}};return H}var Ys;(function(o){o.data="data",o.deferred="deferred",o.redirect="redirect",o.error="error"})(Ys||(Ys={}));function Cd(o,c,a){return a===void 0&&(a="/"),xd(o,c,a)}function xd(o,c,a,p){let g=typeof c=="string"?fn(c):c,w=Wi(g.pathname||"/",a);if(w==null)return null;let S=tc(o);_d(S);let N=null,_=Ud(w);for(let z=0;N==null&&z{let _={relativePath:N===void 0?w.path||"":N,caseSensitive:w.caseSensitive===!0,childrenIndex:S,route:w};_.relativePath.startsWith("/")&&(Se(_.relativePath.startsWith(p),'Absolute route path "'+_.relativePath+'" nested under path '+('"'+p+'" is not valid. An absolute child route path ')+"must start with the combined path of all its parent routes."),_.relativePath=_.relativePath.slice(p.length));let z=Gt([p,_.relativePath]),B=a.concat(_);w.children&&w.children.length>0&&(Se(w.index!==!0,"Index routes must not have child routes. Please remove "+('all child routes from route path "'+z+'".')),tc(w.children,c,B,z)),!(w.path==null&&!w.index)&&c.push({path:z,score:Od(z,w.index),routesMeta:B})};return o.forEach((w,S)=>{var N;if(w.path===""||!((N=w.path)!=null&&N.includes("?")))g(w,S);else for(let _ of nc(w.path))g(w,S,_)}),c}function nc(o){let c=o.split("/");if(c.length===0)return[];let[a,...p]=c,g=a.endsWith("?"),w=a.replace(/\?$/,"");if(p.length===0)return g?[w,""]:[w];let S=nc(p.join("/")),N=[];return N.push(...S.map(_=>_===""?w:[w,_].join("/"))),g&&N.push(...S),N.map(_=>o.startsWith("/")&&_===""?"/":_)}function _d(o){o.sort((c,a)=>c.score!==a.score?a.score-c.score:Md(c.routesMeta.map(p=>p.childrenIndex),a.routesMeta.map(p=>p.childrenIndex)))}const Pd=/^:[\w-]+$/,Nd=3,Rd=2,zd=1,Ld=10,Td=-2,Xs=o=>o==="*";function Od(o,c){let a=o.split("/"),p=a.length;return a.some(Xs)&&(p+=Td),c&&(p+=Rd),a.filter(g=>!Xs(g)).reduce((g,w)=>g+(Pd.test(w)?Nd:w===""?zd:Ld),p)}function Md(o,c){return o.length===c.length&&o.slice(0,-1).every((p,g)=>p===c[g])?o[o.length-1]-c[c.length-1]:0}function Id(o,c,a){let{routesMeta:p}=o,g={},w="/",S=[];for(let N=0;N{let{paramName:W,isOptional:re}=B;if(W==="*"){let H=N[R]||"";S=w.slice(0,w.length-H.length).replace(/(.)\/+$/,"$1")}const G=N[R];return re&&!G?z[W]=void 0:z[W]=(G||"").replace(/%2F/g,"/"),z},{}),pathname:w,pathnameBase:S,pattern:o}}function Fd(o,c,a){c===void 0&&(c=!1),a===void 0&&(a=!0),jl(o==="*"||!o.endsWith("*")||o.endsWith("/*"),'Route path "'+o+'" will be treated as if it were '+('"'+o.replace(/\*$/,"/*")+'" because the `*` character must ')+"always follow a `/` in the pattern. To get rid of this warning, "+('please change the route path to "'+o.replace(/\*$/,"/*")+'".'));let p=[],g="^"+o.replace(/\/*\*?$/,"").replace(/^\/*/,"/").replace(/[\\.*+^${}|()[\]]/g,"\\$&").replace(/\/:([\w-]+)(\?)?/g,(S,N,_)=>(p.push({paramName:N,isOptional:_!=null}),_?"/?([^\\/]+)?":"/([^\\/]+)"));return o.endsWith("*")?(p.push({paramName:"*"}),g+=o==="*"||o==="/*"?"(.*)$":"(?:\\/(.+)|\\/*)$"):a?g+="\\/*$":o!==""&&o!=="/"&&(g+="(?:(?=\\/|$))"),[new RegExp(g,c?void 0:"i"),p]}function Ud(o){try{return o.split("/").map(c=>decodeURIComponent(c).replace(/\//g,"%2F")).join("/")}catch(c){return jl(!1,'The URL path "'+o+'" could not be decoded because it is is a malformed URL segment. This is probably due to a bad percent '+("encoding ("+c+").")),o}}function Wi(o,c){if(c==="/")return o;if(!o.toLowerCase().startsWith(c.toLowerCase()))return null;let a=c.endsWith("/")?c.length-1:c.length,p=o.charAt(a);return p&&p!=="/"?null:o.slice(a)||"/"}const jd=/^(?:[a-z][a-z0-9+.-]*:|\/\/)/i,Bd=o=>jd.test(o);function Ad(o,c){c===void 0&&(c="/");let{pathname:a,search:p="",hash:g=""}=typeof o=="string"?fn(o):o,w;if(a)if(Bd(a))w=a;else{if(a.includes("//")){let S=a;a=uc(a),jl(!1,"Pathnames cannot have embedded double slashes - normalizing "+(S+" -> "+a))}a.startsWith("/")?w=Gs(a.substring(1),"/"):w=Gs(a,c)}else w=c;return{pathname:w,search:Hd(p),hash:$d(g)}}function Gs(o,c){let a=c.replace(/\/+$/,"").split("/");return o.split("/").forEach(g=>{g===".."?a.length>1&&a.pop():g!=="."&&a.push(g)}),a.length>1?a.join("/"):"/"}function Ui(o,c,a,p){return"Cannot include a '"+o+"' character in a manually specified "+("`to."+c+"` field ["+JSON.stringify(p)+"]. Please separate it out to the ")+("`to."+a+"` field. Alternatively you may provide the full path as ")+'a string in and the router will parse it for you.'}function Vd(o){return o.filter((c,a)=>a===0||c.route.path&&c.route.path.length>0)}function rc(o,c){let a=Vd(o);return c?a.map((p,g)=>g===a.length-1?p.pathname:p.pathnameBase):a.map(p=>p.pathnameBase)}function lc(o,c,a,p){p===void 0&&(p=!1);let g;typeof o=="string"?g=fn(o):(g=Cr({},o),Se(!g.pathname||!g.pathname.includes("?"),Ui("?","pathname","search",g)),Se(!g.pathname||!g.pathname.includes("#"),Ui("#","pathname","hash",g)),Se(!g.search||!g.search.includes("#"),Ui("#","search","hash",g)));let w=o===""||g.pathname==="",S=w?"/":g.pathname,N;if(S==null)N=a;else{let R=c.length-1;if(!p&&S.startsWith("..")){let W=S.split("/");for(;W[0]==="..";)W.shift(),R-=1;g.pathname=W.join("/")}N=R>=0?c[R]:"/"}let _=Ad(g,N),z=S&&S!=="/"&&S.endsWith("/"),B=(w||S===".")&&a.endsWith("/");return!_.pathname.endsWith("/")&&(z||B)&&(_.pathname+="/"),_}const uc=o=>o.replace(/\/\/+/g,"/"),Gt=o=>uc(o.join("/")),Wd=o=>o.replace(/\/+$/,"").replace(/^\/*/,"/"),Hd=o=>!o||o==="?"?"":o.startsWith("?")?o:"?"+o,$d=o=>!o||o==="#"?"":o.startsWith("#")?o:"#"+o;function Qd(o){return o!=null&&typeof o.status=="number"&&typeof o.statusText=="string"&&typeof o.internal=="boolean"&&"data"in o}const ic=["post","put","patch","delete"];new Set(ic);const Kd=["get",...ic];new Set(Kd);/** + * React Router v6.30.4 * * Copyright (c) Remix Software Inc. * @@ -47,8 +47,8 @@ Error generating stack: `+u.message+` * LICENSE.md file in the root directory of this source tree. * * @license MIT - */function xr(){return xr=Object.assign?Object.assign.bind():function(o){for(var c=1;c{N.current=!0}),M.useCallback(function(z,B){if(B===void 0&&(B={}),!N.current)return;if(typeof z=="number"){p.go(z);return}let R=lc(z,JSON.parse(S),w,B.relative==="path");o==null&&c!=="/"&&(R.pathname=R.pathname==="/"?c:Gt([c,R.pathname])),(B.replace?p.replace:p.push)(R,B.state,B)},[c,p,S,w,o])}const Gd=M.createContext(null);function Zd(o){let c=M.useContext(Nt).outlet;return c&&M.createElement(Gd.Provider,{value:o},c)}function _p(){let{matches:o}=M.useContext(Nt),c=o[o.length-1];return c?c.params:{}}function sc(o,c){let{relative:a}=c===void 0?{}:c,{future:p}=M.useContext(dn),{matches:g}=M.useContext(Nt),{pathname:w}=Pr(),S=JSON.stringify(rc(g,p.v7_relativeSplatPath));return M.useMemo(()=>lc(o,JSON.parse(S),w,a==="path"),[o,S,w,a])}function Jd(o,c){return qd(o,c)}function qd(o,c,a,p){_r()||Se(!1);let{navigator:g}=M.useContext(dn),{matches:w}=M.useContext(Nt),S=w[w.length-1],N=S?S.params:{};S&&S.pathname;let x=S?S.pathnameBase:"/";S&&S.route;let z=Pr(),B;if(c){var R;let L=typeof c=="string"?fn(c):c;x==="/"||(R=L.pathname)!=null&&R.startsWith(x)||Se(!1),B=L}else B=z;let W=B.pathname||"/",re=W;if(x!=="/"){let L=x.replace(/^\//,"").split("/");re="/"+W.replace(/^\//,"").split("/").slice(L.length).join("/")}let G=Ed(o,{pathname:re}),H=rp(G&&G.map(L=>Object.assign({},L,{params:Object.assign({},N,L.params),pathname:Gt([x,g.encodeLocation?g.encodeLocation(L.pathname).pathname:L.pathname]),pathnameBase:L.pathnameBase==="/"?x:Gt([x,g.encodeLocation?g.encodeLocation(L.pathnameBase).pathname:L.pathnameBase])})),w,a,p);return c&&H?M.createElement(Bl.Provider,{value:{location:xr({pathname:"/",search:"",hash:"",state:null,key:"default"},B),navigationType:Xt.Pop}},H):H}function bd(){let o=op(),c=$d(o)?o.status+" "+o.statusText:o instanceof Error?o.message:JSON.stringify(o),a=o instanceof Error?o.stack:null,g={padding:"0.5rem",backgroundColor:"rgba(200,200,200, 0.5)"};return M.createElement(M.Fragment,null,M.createElement("h2",null,"Unexpected Application Error!"),M.createElement("h3",{style:{fontStyle:"italic"}},c),a?M.createElement("pre",{style:g},a):null,null)}const ep=M.createElement(bd,null);class tp extends M.Component{constructor(c){super(c),this.state={location:c.location,revalidation:c.revalidation,error:c.error}}static getDerivedStateFromError(c){return{error:c}}static getDerivedStateFromProps(c,a){return a.location!==c.location||a.revalidation!=="idle"&&c.revalidation==="idle"?{error:c.error,location:c.location,revalidation:c.revalidation}:{error:c.error!==void 0?c.error:a.error,location:a.location,revalidation:c.revalidation||a.revalidation}}componentDidCatch(c,a){console.error("React Router caught the following error during render",c,a)}render(){return this.state.error!==void 0?M.createElement(Nt.Provider,{value:this.props.routeContext},M.createElement(ic.Provider,{value:this.state.error,children:this.props.component})):this.props.children}}function np(o){let{routeContext:c,match:a,children:p}=o,g=M.useContext(Hi);return g&&g.static&&g.staticContext&&(a.route.errorElement||a.route.ErrorBoundary)&&(g.staticContext._deepestRenderedBoundaryId=a.route.id),M.createElement(Nt.Provider,{value:c},p)}function rp(o,c,a,p){var g;if(c===void 0&&(c=[]),a===void 0&&(a=null),p===void 0&&(p=null),o==null){var w;if(!a)return null;if(a.errors)o=a.matches;else if((w=p)!=null&&w.v7_partialHydration&&c.length===0&&!a.initialized&&a.matches.length>0)o=a.matches;else return null}let S=o,N=(g=a)==null?void 0:g.errors;if(N!=null){let B=S.findIndex(R=>R.route.id&&(N==null?void 0:N[R.route.id])!==void 0);B>=0||Se(!1),S=S.slice(0,Math.min(S.length,B+1))}let x=!1,z=-1;if(a&&p&&p.v7_partialHydration)for(let B=0;B=0?S=S.slice(0,z+1):S=[S[0]];break}}}return S.reduceRight((B,R,W)=>{let re,G=!1,H=null,L=null;a&&(re=N&&R.route.id?N[R.route.id]:void 0,H=R.route.errorElement||ep,x&&(z<0&&W===0?(sp("route-fallback"),G=!0,L=null):z===W&&(G=!0,L=R.route.hydrateFallbackElement||null)));let le=c.concat(S.slice(0,W+1)),ue=()=>{let ee;return re?ee=H:G?ee=L:R.route.Component?ee=M.createElement(R.route.Component,null):R.route.element?ee=R.route.element:ee=B,M.createElement(np,{match:R,routeContext:{outlet:B,matches:le,isDataRoute:a!=null},children:ee})};return a&&(R.route.ErrorBoundary||R.route.errorElement||W===0)?M.createElement(tp,{location:a.location,revalidation:a.revalidation,component:H,error:re,children:ue(),routeContext:{outlet:null,matches:le,isDataRoute:!0}}):ue()},null)}var cc=(function(o){return o.UseBlocker="useBlocker",o.UseRevalidator="useRevalidator",o.UseNavigateStable="useNavigate",o})(cc||{}),fc=(function(o){return o.UseBlocker="useBlocker",o.UseLoaderData="useLoaderData",o.UseActionData="useActionData",o.UseRouteError="useRouteError",o.UseNavigation="useNavigation",o.UseRouteLoaderData="useRouteLoaderData",o.UseMatches="useMatches",o.UseRevalidator="useRevalidator",o.UseNavigateStable="useNavigate",o.UseRouteId="useRouteId",o})(fc||{});function lp(o){let c=M.useContext(Hi);return c||Se(!1),c}function up(o){let c=M.useContext(Kd);return c||Se(!1),c}function ip(o){let c=M.useContext(Nt);return c||Se(!1),c}function dc(o){let c=ip(),a=c.matches[c.matches.length-1];return a.route.id||Se(!1),a.route.id}function op(){var o;let c=M.useContext(ic),a=up(),p=dc();return c!==void 0?c:(o=a.errors)==null?void 0:o[p]}function ap(){let{router:o}=lp(cc.UseNavigateStable),c=dc(fc.UseNavigateStable),a=M.useRef(!1);return oc(()=>{a.current=!0}),M.useCallback(function(g,w){w===void 0&&(w={}),a.current&&(typeof g=="number"?o.navigate(g):o.navigate(g,xr({fromRouteId:c},w)))},[o,c])}const Zs={};function sp(o,c,a){Zs[o]||(Zs[o]=!0)}function cp(o,c){o==null||o.v7_startTransition,o==null||o.v7_relativeSplatPath}function Pp(o){return Zd(o.context)}function fp(o){Se(!1)}function dp(o){let{basename:c="/",children:a=null,location:p,navigationType:g=Xt.Pop,navigator:w,static:S=!1,future:N}=o;_r()&&Se(!1);let x=c.replace(/^\/*/,"/"),z=M.useMemo(()=>({basename:x,navigator:w,static:S,future:xr({v7_relativeSplatPath:!1},N)}),[x,N,w,S]);typeof p=="string"&&(p=fn(p));let{pathname:B="/",search:R="",hash:W="",state:re=null,key:G="default"}=p,H=M.useMemo(()=>{let L=Wi(B,x);return L==null?null:{location:{pathname:L,search:R,hash:W,state:re,key:G},navigationType:g}},[x,B,R,W,re,G,g]);return H==null?null:M.createElement(dn.Provider,{value:z},M.createElement(Bl.Provider,{children:a,value:H}))}function Np(o){let{children:c,location:a}=o;return Jd(Bi(c),a)}new Promise(()=>{});function Bi(o,c){c===void 0&&(c=[]);let a=[];return M.Children.forEach(o,(p,g)=>{if(!M.isValidElement(p))return;let w=[...c,g];if(p.type===M.Fragment){a.push.apply(a,Bi(p.props.children,w));return}p.type!==fp&&Se(!1),!p.props.index||!p.props.children||Se(!1);let S={id:p.props.id||w.join("-"),caseSensitive:p.props.caseSensitive,element:p.props.element,Component:p.props.Component,index:p.props.index,path:p.props.path,loader:p.props.loader,action:p.props.action,errorElement:p.props.errorElement,ErrorBoundary:p.props.ErrorBoundary,hasErrorBoundary:p.props.ErrorBoundary!=null||p.props.errorElement!=null,shouldRevalidate:p.props.shouldRevalidate,handle:p.props.handle,lazy:p.props.lazy};p.props.children&&(S.children=Bi(p.props.children,w)),a.push(S)}),a}/** - * React Router DOM v6.30.3 + */function xr(){return xr=Object.assign?Object.assign.bind():function(o){for(var c=1;c{N.current=!0}),M.useCallback(function(z,B){if(B===void 0&&(B={}),!N.current)return;if(typeof z=="number"){p.go(z);return}let R=lc(z,JSON.parse(S),w,B.relative==="path");o==null&&c!=="/"&&(R.pathname=R.pathname==="/"?c:Gt([c,R.pathname])),(B.replace?p.replace:p.push)(R,B.state,B)},[c,p,S,w,o])}const Zd=M.createContext(null);function Jd(o){let c=M.useContext(Nt).outlet;return c&&M.createElement(Zd.Provider,{value:o},c)}function Pp(){let{matches:o}=M.useContext(Nt),c=o[o.length-1];return c?c.params:{}}function cc(o,c){let{relative:a}=c===void 0?{}:c,{future:p}=M.useContext(dn),{matches:g}=M.useContext(Nt),{pathname:w}=Pr(),S=JSON.stringify(rc(g,p.v7_relativeSplatPath));return M.useMemo(()=>lc(o,JSON.parse(S),w,a==="path"),[o,S,w,a])}function qd(o,c){return bd(o,c)}function bd(o,c,a,p){_r()||Se(!1);let{navigator:g}=M.useContext(dn),{matches:w}=M.useContext(Nt),S=w[w.length-1],N=S?S.params:{};S&&S.pathname;let _=S?S.pathnameBase:"/";S&&S.route;let z=Pr(),B;if(c){var R;let L=typeof c=="string"?fn(c):c;_==="/"||(R=L.pathname)!=null&&R.startsWith(_)||Se(!1),B=L}else B=z;let W=B.pathname||"/",re=W;if(_!=="/"){let L=_.replace(/^\//,"").split("/");re="/"+W.replace(/^\//,"").split("/").slice(L.length).join("/")}let G=Cd(o,{pathname:re}),H=lp(G&&G.map(L=>Object.assign({},L,{params:Object.assign({},N,L.params),pathname:Gt([_,g.encodeLocation?g.encodeLocation(L.pathname).pathname:L.pathname]),pathnameBase:L.pathnameBase==="/"?_:Gt([_,g.encodeLocation?g.encodeLocation(L.pathnameBase).pathname:L.pathnameBase])})),w,a,p);return c&&H?M.createElement(Bl.Provider,{value:{location:xr({pathname:"/",search:"",hash:"",state:null,key:"default"},B),navigationType:Xt.Pop}},H):H}function ep(){let o=ap(),c=Qd(o)?o.status+" "+o.statusText:o instanceof Error?o.message:JSON.stringify(o),a=o instanceof Error?o.stack:null,g={padding:"0.5rem",backgroundColor:"rgba(200,200,200, 0.5)"};return M.createElement(M.Fragment,null,M.createElement("h2",null,"Unexpected Application Error!"),M.createElement("h3",{style:{fontStyle:"italic"}},c),a?M.createElement("pre",{style:g},a):null,null)}const tp=M.createElement(ep,null);class np extends M.Component{constructor(c){super(c),this.state={location:c.location,revalidation:c.revalidation,error:c.error}}static getDerivedStateFromError(c){return{error:c}}static getDerivedStateFromProps(c,a){return a.location!==c.location||a.revalidation!=="idle"&&c.revalidation==="idle"?{error:c.error,location:c.location,revalidation:c.revalidation}:{error:c.error!==void 0?c.error:a.error,location:a.location,revalidation:c.revalidation||a.revalidation}}componentDidCatch(c,a){console.error("React Router caught the following error during render",c,a)}render(){return this.state.error!==void 0?M.createElement(Nt.Provider,{value:this.props.routeContext},M.createElement(oc.Provider,{value:this.state.error,children:this.props.component})):this.props.children}}function rp(o){let{routeContext:c,match:a,children:p}=o,g=M.useContext(Hi);return g&&g.static&&g.staticContext&&(a.route.errorElement||a.route.ErrorBoundary)&&(g.staticContext._deepestRenderedBoundaryId=a.route.id),M.createElement(Nt.Provider,{value:c},p)}function lp(o,c,a,p){var g;if(c===void 0&&(c=[]),a===void 0&&(a=null),p===void 0&&(p=null),o==null){var w;if(!a)return null;if(a.errors)o=a.matches;else if((w=p)!=null&&w.v7_partialHydration&&c.length===0&&!a.initialized&&a.matches.length>0)o=a.matches;else return null}let S=o,N=(g=a)==null?void 0:g.errors;if(N!=null){let B=S.findIndex(R=>R.route.id&&(N==null?void 0:N[R.route.id])!==void 0);B>=0||Se(!1),S=S.slice(0,Math.min(S.length,B+1))}let _=!1,z=-1;if(a&&p&&p.v7_partialHydration)for(let B=0;B=0?S=S.slice(0,z+1):S=[S[0]];break}}}return S.reduceRight((B,R,W)=>{let re,G=!1,H=null,L=null;a&&(re=N&&R.route.id?N[R.route.id]:void 0,H=R.route.errorElement||tp,_&&(z<0&&W===0?(cp("route-fallback"),G=!0,L=null):z===W&&(G=!0,L=R.route.hydrateFallbackElement||null)));let le=c.concat(S.slice(0,W+1)),ue=()=>{let ee;return re?ee=H:G?ee=L:R.route.Component?ee=M.createElement(R.route.Component,null):R.route.element?ee=R.route.element:ee=B,M.createElement(rp,{match:R,routeContext:{outlet:B,matches:le,isDataRoute:a!=null},children:ee})};return a&&(R.route.ErrorBoundary||R.route.errorElement||W===0)?M.createElement(np,{location:a.location,revalidation:a.revalidation,component:H,error:re,children:ue(),routeContext:{outlet:null,matches:le,isDataRoute:!0}}):ue()},null)}var fc=(function(o){return o.UseBlocker="useBlocker",o.UseRevalidator="useRevalidator",o.UseNavigateStable="useNavigate",o})(fc||{}),dc=(function(o){return o.UseBlocker="useBlocker",o.UseLoaderData="useLoaderData",o.UseActionData="useActionData",o.UseRouteError="useRouteError",o.UseNavigation="useNavigation",o.UseRouteLoaderData="useRouteLoaderData",o.UseMatches="useMatches",o.UseRevalidator="useRevalidator",o.UseNavigateStable="useNavigate",o.UseRouteId="useRouteId",o})(dc||{});function up(o){let c=M.useContext(Hi);return c||Se(!1),c}function ip(o){let c=M.useContext(Yd);return c||Se(!1),c}function op(o){let c=M.useContext(Nt);return c||Se(!1),c}function pc(o){let c=op(),a=c.matches[c.matches.length-1];return a.route.id||Se(!1),a.route.id}function ap(){var o;let c=M.useContext(oc),a=ip(),p=pc();return c!==void 0?c:(o=a.errors)==null?void 0:o[p]}function sp(){let{router:o}=up(fc.UseNavigateStable),c=pc(dc.UseNavigateStable),a=M.useRef(!1);return ac(()=>{a.current=!0}),M.useCallback(function(g,w){w===void 0&&(w={}),a.current&&(typeof g=="number"?o.navigate(g):o.navigate(g,xr({fromRouteId:c},w)))},[o,c])}const Zs={};function cp(o,c,a){Zs[o]||(Zs[o]=!0)}function fp(o,c){o==null||o.v7_startTransition,o==null||o.v7_relativeSplatPath}function Np(o){return Jd(o.context)}function dp(o){Se(!1)}function pp(o){let{basename:c="/",children:a=null,location:p,navigationType:g=Xt.Pop,navigator:w,static:S=!1,future:N}=o;_r()&&Se(!1);let _=c.replace(/^\/*/,"/"),z=M.useMemo(()=>({basename:_,navigator:w,static:S,future:xr({v7_relativeSplatPath:!1},N)}),[_,N,w,S]);typeof p=="string"&&(p=fn(p));let{pathname:B="/",search:R="",hash:W="",state:re=null,key:G="default"}=p,H=M.useMemo(()=>{let L=Wi(B,_);return L==null?null:{location:{pathname:L,search:R,hash:W,state:re,key:G},navigationType:g}},[_,B,R,W,re,G,g]);return H==null?null:M.createElement(dn.Provider,{value:z},M.createElement(Bl.Provider,{children:a,value:H}))}function Rp(o){let{children:c,location:a}=o;return qd(Bi(c),a)}new Promise(()=>{});function Bi(o,c){c===void 0&&(c=[]);let a=[];return M.Children.forEach(o,(p,g)=>{if(!M.isValidElement(p))return;let w=[...c,g];if(p.type===M.Fragment){a.push.apply(a,Bi(p.props.children,w));return}p.type!==dp&&Se(!1),!p.props.index||!p.props.children||Se(!1);let S={id:p.props.id||w.join("-"),caseSensitive:p.props.caseSensitive,element:p.props.element,Component:p.props.Component,index:p.props.index,path:p.props.path,loader:p.props.loader,action:p.props.action,errorElement:p.props.errorElement,ErrorBoundary:p.props.ErrorBoundary,hasErrorBoundary:p.props.ErrorBoundary!=null||p.props.errorElement!=null,shouldRevalidate:p.props.shouldRevalidate,handle:p.props.handle,lazy:p.props.lazy};p.props.children&&(S.children=Bi(p.props.children,w)),a.push(S)}),a}/** + * React Router DOM v6.30.4 * * Copyright (c) Remix Software Inc. * @@ -56,4 +56,4 @@ Error generating stack: `+u.message+` * LICENSE.md file in the root directory of this source tree. * * @license MIT - */function Ai(){return Ai=Object.assign?Object.assign.bind():function(o){for(var c=1;c=0)&&(a[g]=o[g]);return a}function hp(o){return!!(o.metaKey||o.altKey||o.ctrlKey||o.shiftKey)}function mp(o,c){return o.button===0&&(!c||c==="_self")&&!hp(o)}function Vi(o){return o===void 0&&(o=""),new URLSearchParams(typeof o=="string"||Array.isArray(o)||o instanceof URLSearchParams?o:Object.keys(o).reduce((c,a)=>{let p=o[a];return c.concat(Array.isArray(p)?p.map(g=>[a,g]):[[a,p]])},[]))}function vp(o,c){let a=Vi(o);return c&&c.forEach((p,g)=>{a.has(g)||c.getAll(g).forEach(w=>{a.append(g,w)})}),a}const yp=["onClick","relative","reloadDocument","replace","state","target","to","preventScrollReset","viewTransition"],gp="6";try{window.__reactRouterVersion=gp}catch{}const wp="startTransition",Js=hd[wp];function Rp(o){let{basename:c,children:a,future:p,window:g}=o,w=M.useRef();w.current==null&&(w.current=wd({window:g,v5Compat:!0}));let S=w.current,[N,x]=M.useState({action:S.action,location:S.location}),{v7_startTransition:z}=p||{},B=M.useCallback(R=>{z&&Js?Js(()=>x(R)):x(R)},[x,z]);return M.useLayoutEffect(()=>S.listen(B),[S,B]),M.useEffect(()=>cp(p),[p]),M.createElement(dp,{basename:c,children:a,location:N.location,navigationType:N.action,navigator:S,future:p})}const Sp=typeof window<"u"&&typeof window.document<"u"&&typeof window.document.createElement<"u",kp=/^(?:[a-z][a-z0-9+.-]*:|\/\/)/i,zp=M.forwardRef(function(c,a){let{onClick:p,relative:g,reloadDocument:w,replace:S,state:N,target:x,to:z,preventScrollReset:B,viewTransition:R}=c,W=pp(c,yp),{basename:re}=M.useContext(dn),G,H=!1;if(typeof z=="string"&&kp.test(z)&&(G=z,Sp))try{let ee=new URL(window.location.href),ie=z.startsWith("//")?new URL(ee.protocol+z):new URL(z),Ce=Wi(ie.pathname,re);ie.origin===ee.origin&&Ce!=null?z=Ce+ie.search+ie.hash:H=!0}catch{}let L=Yd(z,{relative:g}),le=Ep(z,{replace:S,state:N,target:x,preventScrollReset:B,relative:g,viewTransition:R});function ue(ee){p&&p(ee),ee.defaultPrevented||le(ee)}return M.createElement("a",Ai({},W,{href:G||L,onClick:H||w?p:ue,ref:a,target:x}))});var qs;(function(o){o.UseScrollRestoration="useScrollRestoration",o.UseSubmit="useSubmit",o.UseSubmitFetcher="useSubmitFetcher",o.UseFetcher="useFetcher",o.useViewTransitionState="useViewTransitionState"})(qs||(qs={}));var bs;(function(o){o.UseFetcher="useFetcher",o.UseFetchers="useFetchers",o.UseScrollRestoration="useScrollRestoration"})(bs||(bs={}));function Ep(o,c){let{target:a,replace:p,state:g,preventScrollReset:w,relative:S,viewTransition:N}=c===void 0?{}:c,x=ac(),z=Pr(),B=sc(o,{relative:S});return M.useCallback(R=>{if(mp(R,a)){R.preventDefault();let W=p!==void 0?p:Ul(z)===Ul(B);x(o,{replace:W,state:g,preventScrollReset:w,relative:S,viewTransition:N})}},[z,x,B,p,g,a,o,w,S,N])}function Lp(o){let c=M.useRef(Vi(o)),a=M.useRef(!1),p=Pr(),g=M.useMemo(()=>vp(p.search,a.current?null:c.current),[p.search]),w=ac(),S=M.useCallback((N,x)=>{const z=Vi(typeof N=="function"?N(g):N);a.current=!0,w("?"+z,x)},[w,g]);return[g,S]}export{Rp as H,zp as L,Pp as O,pd as R,ec as a,xp as b,Cp as c,gd as d,_p as e,ac as f,fd as g,Np as h,fp as i,M as r,hd as t,Lp as u}; + */function Ai(){return Ai=Object.assign?Object.assign.bind():function(o){for(var c=1;c{let p=o[a];return c.concat(Array.isArray(p)?p.map(g=>[a,g]):[[a,p]])},[]))}function yp(o,c){let a=Vi(o);return c&&c.forEach((p,g)=>{a.has(g)||c.getAll(g).forEach(w=>{a.append(g,w)})}),a}const gp=["onClick","relative","reloadDocument","replace","state","target","to","preventScrollReset","viewTransition"],wp="6";try{window.__reactRouterVersion=wp}catch{}const Sp="startTransition",Js=md[Sp];function zp(o){let{basename:c,children:a,future:p,window:g}=o,w=M.useRef();w.current==null&&(w.current=Sd({window:g,v5Compat:!0}));let S=w.current,[N,_]=M.useState({action:S.action,location:S.location}),{v7_startTransition:z}=p||{},B=M.useCallback(R=>{z&&Js?Js(()=>_(R)):_(R)},[_,z]);return M.useLayoutEffect(()=>S.listen(B),[S,B]),M.useEffect(()=>fp(p),[p]),M.createElement(pp,{basename:c,children:a,location:N.location,navigationType:N.action,navigator:S,future:p})}const kp=typeof window<"u"&&typeof window.document<"u"&&typeof window.document.createElement<"u",Ep=/^(?:[a-z][a-z0-9+.-]*:|\/\/)/i,Lp=M.forwardRef(function(c,a){let{onClick:p,relative:g,reloadDocument:w,replace:S,state:N,target:_,to:z,preventScrollReset:B,viewTransition:R}=c,W=hp(c,gp),{basename:re}=M.useContext(dn),G,H=!1;if(typeof z=="string"&&Ep.test(z)&&(G=z,kp))try{let ee=new URL(window.location.href),ie=z.startsWith("//")?new URL(ee.protocol+z):new URL(z),Ce=Wi(ie.pathname,re);ie.origin===ee.origin&&Ce!=null?z=Ce+ie.search+ie.hash:H=!0}catch{}let L=Xd(z,{relative:g}),le=Cp(z,{replace:S,state:N,target:_,preventScrollReset:B,relative:g,viewTransition:R});function ue(ee){p&&p(ee),ee.defaultPrevented||le(ee)}return M.createElement("a",Ai({},W,{href:G||L,onClick:H||w?p:ue,ref:a,target:_}))});var qs;(function(o){o.UseScrollRestoration="useScrollRestoration",o.UseSubmit="useSubmit",o.UseSubmitFetcher="useSubmitFetcher",o.UseFetcher="useFetcher",o.useViewTransitionState="useViewTransitionState"})(qs||(qs={}));var bs;(function(o){o.UseFetcher="useFetcher",o.UseFetchers="useFetchers",o.UseScrollRestoration="useScrollRestoration"})(bs||(bs={}));function Cp(o,c){let{target:a,replace:p,state:g,preventScrollReset:w,relative:S,viewTransition:N}=c===void 0?{}:c,_=sc(),z=Pr(),B=cc(o,{relative:S});return M.useCallback(R=>{if(vp(R,a)){R.preventDefault();let W=p!==void 0?p:Ul(z)===Ul(B);_(o,{replace:W,state:g,preventScrollReset:w,relative:S,viewTransition:N})}},[z,_,B,p,g,a,o,w,S,N])}function Tp(o){let c=M.useRef(Vi(o)),a=M.useRef(!1),p=Pr(),g=M.useMemo(()=>yp(p.search,a.current?null:c.current),[p.search]),w=sc(),S=M.useCallback((N,_)=>{const z=Vi(typeof N=="function"?N(g):N);a.current=!0,w("?"+z,_)},[w,g]);return[g,S]}export{zp as H,Lp as L,Np as O,hd as R,ec as a,_p as b,xp as c,wd as d,Pp as e,sc as f,dd as g,Rp as h,dp as i,M as r,md as t,Tp as u}; diff --git a/src/helm/benchmark/static_build/assets/react-markdown-kIsf0iIR.js b/src/helm/benchmark/static_build/assets/react-markdown-DTLembof.js similarity index 99% rename from src/helm/benchmark/static_build/assets/react-markdown-kIsf0iIR.js rename to src/helm/benchmark/static_build/assets/react-markdown-DTLembof.js index 2138db42adf..18bc5b3a007 100644 --- a/src/helm/benchmark/static_build/assets/react-markdown-kIsf0iIR.js +++ b/src/helm/benchmark/static_build/assets/react-markdown-DTLembof.js @@ -1,4 +1,4 @@ -import{g as qn,R as Fn}from"./react-BhnNyHuP.js";import{i as v}from"./recharts-Bmm96ixf.js";const Le=["http","https","mailto","tel"];function tr(n){const e=(n||"").trim(),t=e.charAt(0);if(t==="#"||t==="/")return e;const r=e.indexOf(":");if(r===-1)return e;let i=-1;for(;++ii||(i=e.indexOf("#"),i!==-1&&r>i)?e:"javascript:void(0)"}/*! +import{g as qn,R as Fn}from"./react-D3IQTVQZ.js";import{i as v}from"./recharts-DhnSad7c.js";const Le=["http","https","mailto","tel"];function tr(n){const e=(n||"").trim(),t=e.charAt(0);if(t==="#"||t==="/")return e;const r=e.indexOf(":");if(r===-1)return e;let i=-1;for(;++ii||(i=e.indexOf("#"),i!==-1&&r>i)?e:"javascript:void(0)"}/*! * Determine if an object is a Buffer * * @author Feross Aboukhadijeh diff --git a/src/helm/benchmark/static_build/assets/recharts-Bmm96ixf.js b/src/helm/benchmark/static_build/assets/recharts-DhnSad7c.js similarity index 99% rename from src/helm/benchmark/static_build/assets/recharts-Bmm96ixf.js rename to src/helm/benchmark/static_build/assets/recharts-DhnSad7c.js index f78c026c53a..639c4e155c6 100644 --- a/src/helm/benchmark/static_build/assets/recharts-Bmm96ixf.js +++ b/src/helm/benchmark/static_build/assets/recharts-DhnSad7c.js @@ -1,4 +1,4 @@ -import{c as Ci,g as oe,r as D,R as A}from"./react-BhnNyHuP.js";function h0(e){var t,r,n="";if(typeof e=="string"||typeof e=="number")n+=e;else if(typeof e=="object")if(Array.isArray(e)){var i=e.length;for(t=0;t-1}return du=t,du}var vu,Hh;function i_(){if(Hh)return vu;Hh=1;var e=Za();function t(r,n){var i=this.__data__,a=e(i,r);return a<0?(++this.size,i.push([r,n])):i[a][1]=n,this}return vu=t,vu}var yu,Gh;function Ja(){if(Gh)return yu;Gh=1;var e=e_(),t=t_(),r=r_(),n=n_(),i=i_();function a(o){var u=-1,c=o==null?0:o.length;for(this.clear();++u-1}return du=t,du}var vu,Hh;function i_(){if(Hh)return vu;Hh=1;var e=Za();function t(r,n){var i=this.__data__,a=e(i,r);return a<0?(++this.size,i.push([r,n])):i[a][1]=n,this}return vu=t,vu}var yu,Gh;function Ja(){if(Gh)return yu;Gh=1;var e=e_(),t=t_(),r=r_(),n=n_(),i=i_();function a(o){var u=-1,c=o==null?0:o.length;for(this.clear();++uHolistic Evaluation of Language Models (HELM) - - - - - + + + + +