PageSourceSearch

https://zerx.dev/benchmarks/

html zerx.dev collected 2026-09-24 11:58:57 UTC 183,040 bytes, 47 lines download raw bytes

1<!DOCTYPE html><html lang="zh-CN" data-astro-cid-iv7lwsuo> <head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover"><meta name="color-scheme" content="light dark"><meta name="theme-color" content="#fafaf9" media="(prefers-color-scheme: light)"><meta name="theme-color" content="#0a0a0a" media="(prefers-color-scheme: dark)"><meta name="generator" content="Astro v6.1.7"><title>AI 模型能力榜 — ZerxLab</title><meta name="description" content="多维度比较 AI 模型的推理、编程与语言能力,结合分类筛选和模型对比,为技术选型提供参考。"><meta name="robots" content="index, follow, max-image-preview:large, max-snippet:-1"><link rel="canonical" href="https://zerx.dev/benchmarks/"><link rel="alternate" hreflang="zh-CN" href="https://zerx.dev/benchmarks/"><link rel="alternate" hreflang="en-US" href="https://zerx.dev/en/benchmarks/"><link rel="alternate" hreflang="x-default" href="https://zerx.dev/benchmarks/"><meta property="og:site_name" content="ZerxLab"><meta property="og:type" content="website"><meta property="og:title" content="AI 模型能力榜 — ZerxLab"><meta property="og:description" content="多维度比较 AI 模型的推理、编程与语言能力,结合分类筛选和模型对比,ä¸
1ºæŠ€æœ¯é€‰åž‹æä¾›å‚考。"><meta property="og:url" content="https://zerx.dev/benchmarks/"><meta property="og:locale" content="zh_CN"><meta property="og:locale:alternate" content="en_US"><meta name="twitter:card" content="summary"><meta name="twitter:title" content="AI 模型能力榜 — ZerxLab"><meta name="twitter:description" content="多维度比较 AI 模型的推理、编程与语言能力,结合分类筛选和模型对比,为技术选型提供参考。"><link rel="icon" type="image/svg+xml" href="/favicon.svg"><link rel="alternate icon" type="image/png" href="/favicon.png"><link rel="apple-touch-icon" href="/apple-touch-icon.png"><link rel="manifest" href="/site.webmanifest"><link rel="sitemap" type="application/xml" href="/sitemap-index.xml"><link rel="alternate" type="application/rss+xml" title="ZerxLab — 博客 RSS (中文)" href="/rss.xml"><link rel="alternate" type="application/rss+xml" title="ZerxLab — Blog RSS (English)" href="/en/rss.xml" hreflang="en"><link rel="preload" href="/fonts/geist-sans-regular.woff2" as="font" type="font/woff2" crossorigin="anonymous"><link rel="preload" href="/fonts/geist-sans-medium.woff2" as="font" type="font/woff2" crossorigin="anonymous"><link rel="preload" href="/fonts/geist-mono-regular.woff2" as="font" type="font/woff2" crossorigin="anonymous">
1<script type="application/ld+json">{"@context":"https://schema.org","@type":"WebSite","name":"ZerxLab","description":"聚焦高性能应用、现代技术架构与开源工具,探索代码与工程的边界。","url":"https://zerx.dev","inLanguage":["zh-CN","en-US"],"publisher":{"@type":"Organization","name":"ZerxLab","url":"https://zerx.dev"}}</script>
1<script>
2	(function () {
3		try {
4			var KEY = "zerx-theme";
5			var stored = null;
6			try {
7				stored = localStorage.getItem(KEY);
8			} catch (_) {
9				/* localStorage 不可用(隐私模式),降级 */
10			}
11
12			var prefersDark =
13				window.matchMedia &&
14				window.matchMedia("(prefers-color-scheme: dark)").matches;
15
16			var resolved;
17			if (stored === "light" || stored === "dark") {
18				resolved = stored;
19			} else {
20				// "system" 或 null
21				resolved = prefersDark ? "dark" : "light";
22			}
23
24			var root = document.documentElement;
25			if (resolved === "dark") {
26				root.classList.add("dark");
27			} else {
28				root.classList.remove("dark");
29			}
30			root.style.colorScheme = resolved;
31		} catch (_) {
32			/* 兜底:任何异常都不应阻塞渲染 */
33		}
34	})();
35</script>
35<link rel="stylesheet" href="/_astro/MetaRow.ees2hAdf.css">
36<link rel="stylesheet" href="/_astro/global.CRKj8kEJ.css">
37<style>button[data-astro-cid-7k4hvajv][data-cat]{transition:background-color .12s,color .12s,border-color .12s}button[data-astro-cid-7k4hvajv][data-cat][aria-pressed=true]{background-color:var(--color-ink-primary);color:var(--color-paper);border-color:var(--color-ink-primary);font-weight:600}@media(prefers-reduced-motion:reduce){button[data-astro-cid-7k4hvajv][data-cat]{transition:none}}
38</style>
38<script type="module" src="/_astro/page.C0k1DY2K.js"></script>
38</head> <body class="app-shell-body min-h-screen bg-[color:var(--color-paper)] text-[color:var(--color-ink-primary)] antialiased" data-astro-cid-iv7lwsuo>  <div class="app-shell" data-astro-cid-iv7lwsuo>  <aside class="app-shell__left" aria-label="侧边信息栏" data-astro-cid-iv7lwsuo> <aside class="left-pane relative flex flex-col bg-[color:var(--color-paper)] lg:border-r lg:border-dashed lg:border-[color:var(--color-hairline)] px-5 sm:px-8 lg:px-10 xl:px-14 pt-5 sm:pt-6 lg:pt-8 pb-6 sm:pb-8 lg:pb-10" data-astro-cid-xnqmve7t>  <div class="flex items-center" data-astro-cid-xnqmve7t> <a href="/" aria-label="ZERX-LAB" class="inline-flex items-center font-semibold tracking-tight gap-2 text-[15px] text-[color:var(--color-ink-primary)] transition-opacity duration-[var(--duration-fast)] hover:opacity-70"><span aria-hidden="true" class="relative inline-block shrink-0 h-[14px] w-[14px]"> <svg viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg" class="h-full w-full">  <rect x="0" y="0" width="10" height="10" fill="currentColor"></rect>  <rect x="6" y="6" width="10" height="10" fill="currentColor" fill-opacity="0.35"></rect> </svg> </span> <span class="whitespace-nowrap leading-none"> ZERX-LAB<span aria-hidden="true" class="text-[color:var(--color-ink-tertiary)]">.</span> </span> </a> </div> <hr class="hairline mt-5 sm:mt-6 lg:mt-8" aria-hidden="true" data-astro-cid-xnqmve7t>    <div class="mt-6 md:mt-10 lg:mt-12 xl:mt-14 flex-1 min-h-0 flex flex-col" data-astro-cid-xnqmve7t>  <div class="flex items-center gap-1.5 mb-3 md:mb-4" data-astro-cid-xnqmve7t>  <span class="mono-label" data-astro-cid-xnqmve7t>AI / MODEL BENCHMARKS</span> </div>  <h1 class="font-medium text-[color:var(--color-ink-primary)] tracking-[-0.02em] leading-[1.15] text-[26px] sm:text-[32px] md:text-[36px] lg:text-[40px] xl:text-[44px] mb-3 md:mb-4 lg:mb-5" data-astro-cid-xnqmve7t> AI 模型能力榜 </h1>  <p class="text-[color:var(--color-ink-secondary)] text-[14px] md:text-[15px] leading-[1.6] max-w-[38ch] mb-5 md:mb-6 lg:mb-7" data-astro-cid-xnqmve7t> 多维度比较 AI 模型的推理、编程与语言能力,结合分类筛选和模型对比,ä¸
38ºæŠ€æœ¯é€‰åž‹æä¾›å‚考。 </p>  <div class="flex flex-wrap items-center gap-2 mb-6 md:mb-8" data-astro-cid-xnqmve7t>  </div>  <div class="flex items-center gap-4 text-[color:var(--color-ink-tertiary)] mb-6 md:mb-8" data-astro-cid-xnqmve7t>  </div>  <div class="flex-1" aria-hidden="true" data-astro-cid-xnqmve7t></div> </div>  <details class="left-pane__meta-collapsible lg:hidden mt-6 pt-4 border-t border-dashed border-[color:var(--color-hairline)]" data-astro-cid-xnqmve7t> <summary class="flex items-center justify-between gap-2 cursor-pointer select-none list-none py-1" data-astro-cid-xnqmve7t> <span class="mono-label text-[11px] text-[color:var(--color-ink-tertiary)]" data-astro-cid-xnqmve7t>
39META
40</span> <span aria-hidden="true" class="left-pane__meta-chevron inline-flex items-center justify-center h-5 w-5 text-[color:var(--color-ink-muted)] transition-transform duration-[var(--duration-fast)] ease-[var(--ease-standard)]" data-astro-cid-xnqmve7t> <svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-xnqmve7t> <path d="m6 9 6 6 6-6" data-astro-cid-xnqmve7t></path> </svg> </span> </summary> <dl class="flex flex-col mt-2" data-astro-cid-xnqmve7t>  <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 数据版本 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>2026-06-25</span>     </span> </div> <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 同步时间 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>2026年9月23日 05:12 UTC</span>     </span> </div> <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 模型数 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>57</span>     </span> </div>  </dl> </details> <div class="hidden lg:block mt-8 lg:mt-10 pt-4 border-t border-dashed border-[color:var(--color-hairline)]" data-astro-cid-xnqmve7t> <dl class="flex flex-col" data-astro-cid-xnqmve7t>  <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 数据版本 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>2026-06-25</span>     </span> </div> <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 同步时间 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>2026年9月23日 05:12 UTC</span>     </span> </div> <div data-astro-cid-cus352i6="true" class="meta-row-component flex items-baseline justify-between gap-3 py-2 font-[var(--font-mono)] text-[11px] leading-[1.4] tracking-[var(--tracking-wide)] border-b border-dashed border-[color:var(--color-hairline)]"><span class="shrink-0 uppercase text-[color:var(--color-ink-tertiary)] tracking-[var(--tracking-wider)] font-medium" data-astro-cid-cus352i6> 模型数 </span> <span class="min-w-0 truncate text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-primary)]" data-astro-cid-cus352i6> <span class="truncate" data-astro-cid-cus352i6>57</span>     </span> </div>  </dl> </div>  </aside> </aside>  <main class="app-shell__right" id="main-content" data-astro-cid-iv7lwsuo>
40  <div class="app-shell__nav" data-astro-cid-iv7lwsuo> <nav aria-label="主导航" class="top-nav flex items-stretch w-full h-[var(--layout-top-nav-height)] border-b border-[color:var(--color-hairline)] bg-[color:var(--color-paper)]/80 backdrop-blur-sm supports-[backdrop-filter]:bg-[color:var(--color-paper)]/60" data-astro-cid-5i26sbjv>  <div class="md:hidden flex items-stretch w-full" data-astro-cid-5i26sbjv>  <a href="/" aria-label="ZERX-LAB" class="flex items-center px-4 font-[var(--font-mono)] text-[12px] font-semibold tracking-[var(--tracking-wider)] text-[color:var(--color-ink-primary)] select-none" data-astro-cid-5i26sbjv> ZERX-LAB </a>  <div class="ml-auto flex items-stretch" data-astro-cid-5i26sbjv>  <a href="https://github.com/zerx-lab" target="_blank" rel="noopener noreferrer" aria-label="GitHub" class="inline-flex items-center justify-center h-full w-12 border-l border-[color:var(--color-hairline)] text-[color:var(--color-ink-muted)] hover:text-[color:var(--color-ink-primary)] hover:bg-[color:var(--color-paper-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] select-none" data-astro-cid-5i26sbjv> <svg aria-hidden="true" width="16" height="16" viewBox="0 0 24 24" fill="currentColor" class="shrink-0" data-astro-cid-5i26sbjv> <path d="M12 .3a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2c-3.3.7-4-1.6-4-1.6-.6-1.4-1.4-1.8-1.4-1.8-1-.7.1-.7.1-.7 1.2 0 1.9 1.2 1.9 1.2 1 1.8 2.8 1.3 3.5 1 0-.8.4-1.3.7-1.6-2.7-.3-5.5-1.3-5.5-6 0-1.2.5-2.3 1.3-3.1-.1-.4-.6-1.6.1-3.2 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0C17.3 4.7 18.3 5 18.3 5c.7 1.6.2 2.8.1 3.2.8.8 1.3 1.9 1.3 3.1 0 4.6-2.8 5.6-5.5 5.9.5.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .3" data-astro-cid-5i26sbjv></path> </svg> </a>  <button type="button" data-mobile-menu-open aria-label="打开菜单" aria-controls="mobile-menu-drawer" aria-expanded="false" class="inline-flex items-center justify-center h-full w-14 border-l border-[color:var(--color-hairline)] text-[color:var(--color-ink-primary)] hover:bg-[color:var(--color-paper-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] cursor-pointer" data-astro-cid-5i26sbjv> <svg aria-hidden="true" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-5i26sbjv> <path d="M3 6h18" data-astro-cid-5i26sbjv></path> <path d="M3 12h18" data-astro-cid-5i26sbjv></path> <path d="M3 18h18" data-astro-cid-5i26sbjv></path> </svg> </button> </div> </div>   <ul role="menubar" class="hidden md:flex items-stretch flex-1 min-w-0 list-none m-0 p-0" data-astro-cid-5i26sbjv> <li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-tertiary)] hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>首页</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-transparent group-hover:bg-[color:var(--color-hairline-strong)]" data-astro-cid-5i26sbjv></span> </a> </li><li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/projects" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-tertiary)] hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>项目</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-transparent group-hover:bg-[color:var(--color-hairline-strong)]" data-astro-cid-5i26sbjv></span> </a> </li><li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/benchmarks" aria-current="page" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>榜单</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv></span> </a> </li><li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/aur" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-tertiary)] hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>AUR</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-transparent group-hover:bg-[color:var(--color-hairline-strong)]" data-astro-cid-5i26sbjv></span> </a> </li><li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/blog" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-tertiary)] hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>博客</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-transparent group-hover:bg-[color:var(--color-hairline-strong)]" data-astro-cid-5i26sbjv></span> </a> </li><li role="none" class="flex-1 flex items-stretch min-w-0 border-r border-[color:var(--color-hairline)] first:border-l-0" data-astro-cid-5i26sbjv> <a role="menuitem" href="/about" class="group relative flex-1 flex items-center justify-center px-3 mono-label text-[11px] sm:text-xs select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-tertiary)] hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="truncate leading-none" data-astro-cid-5i26sbjv>关于</span>  <span aria-hidden="true" class="pointer-events-none absolute left-0 right-0 bottom-0 h-[2px] bg-transparent group-hover:bg-[color:var(--color-hairline-strong)]" data-astro-cid-5i26sbjv></span> </a> </li> </ul>  <div class="hidden md:flex items-stretch shrink-0 border-l border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv>
40  <div class="flex items-center border-r border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <div role="group" aria-label="语言切换" class="lang-toggle flex items-center h-full px-3 sm:px-4 gap-1.5 select-none" data-astro-cid-got23tqz> <a href="/benchmarks/" hreflang="zh-CN" aria-current="true" aria-label="切换到 中文" data-lang="zh" class="mono-label text-[11px] leading-none tracking-[var(--tracking-wider)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] text-[color:var(--color-ink-primary)] font-semibold" data-astro-cid-got23tqz> ZH </a> <span aria-hidden="true" class="text-[color:var(--color-ink-faint)] text-[10px] leading-none" data-astro-cid-got23tqz>
41·
42</span><a href="/en/benchmarks/" hreflang="en-US" aria-label="切换到 English" data-lang="en" class="mono-label text-[11px] leading-none tracking-[var(--tracking-wider)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] text-[color:var(--color-ink-muted)]" data-astro-cid-got23tqz> EN </a>  </div> </div>  <div class="flex items-center border-r border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <div role="group" aria-label="切换主题" class="theme-toggle flex items-center h-full px-2 sm:px-3 gap-0.5 select-none" data-astro-cid-lfoluaxz> <button type="button" data-theme-btn="light" aria-label="浅色" title="浅色" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz> <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <circle cx="12" cy="12" r="4" data-astro-cid-lfoluaxz></circle> <path d="M12 2v2" data-astro-cid-lfoluaxz></path> <path d="M12 20v2" data-astro-cid-lfoluaxz></path> <path d="m4.93 4.93 1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="m17.66 17.66 1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="M2 12h2" data-astro-cid-lfoluaxz></path> <path d="M20 12h2" data-astro-cid-lfoluaxz></path> <path d="m6.34 17.66-1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="m19.07 4.93-1.41 1.41" data-astro-cid-lfoluaxz></path> </svg>   </button><button type="button" data-theme-btn="system" aria-label="跟随系统" title="跟随系统" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz>  <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <rect x="2" y="4" width="20" height="14" rx="2" data-astro-cid-lfoluaxz></rect> <path d="M8 20h8" data-astro-cid-lfoluaxz></path> <path d="M12 18v2" data-astro-cid-lfoluaxz></path> </svg>  </button><button type="button" data-theme-btn="dark" aria-label="深色" title="深色" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz>   <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <path d="M21 12.79A9 9 0 1 1 11.21 3 7 7 0 0 0 21 12.79Z" data-astro-cid-lfoluaxz></path> </svg> </button> </div>  
42<script type="module">const i="zerx-theme";function d(){try{const t=localStorage.getItem(i);if(t==="light"||t==="dark"||t==="system")return t}catch{}return"system"}function u(){return window.matchMedia("(prefers-color-scheme: dark)").matches}function c(t){const a=document.documentElement,e=t==="dark"||t==="system"&&u();a.classList.toggle("dark",e),a.style.colorScheme=e?"dark":"light"}function o(t){document.querySelectorAll("[data-theme-btn]").forEach(e=>{const r=e.getAttribute("data-theme-btn")===t;e.setAttribute("data-active",String(r)),e.setAttribute("aria-pressed",String(r))})}function l(t){try{localStorage.setItem(i,t)}catch{}c(t),o(t)}function m(){const t=d();c(t),o(t),document.querySelectorAll("[data-theme-btn]").forEach(s=>{s.addEventListener("click",()=>{const n=s.getAttribute("data-theme-btn");(n==="light"||n==="dark"||n==="system")&&l(n)})});const e=window.matchMedia("(prefers-color-scheme: dark)"),r=()=>{d()==="system"&&c("system")};e.addEventListener?e.addEventListener("change",r):e.addListener&&e.addListener(r),window.addEventListener("storage",s=>{if(s.key===i&&s.newValue){const n=s.newValue;(n==="light"||n==="dark"||n==="system")&&(c(n),o(n))}})}m();document.addEventListener("astro:after-swap",m);</script>
42 </div>  <a href="https://github.com/zerx-lab" target="_blank" rel="noopener noreferrer" aria-label="GitHub" class="group flex items-center gap-2 px-4 sm:px-5 font-[var(--font-mono)] text-[11px] sm:text-xs uppercase tracking-[var(--tracking-wider)] font-medium text-[color:var(--color-ink-muted)] hover:text-[color:var(--color-ink-primary)] hover:bg-[color:var(--color-paper-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] select-none whitespace-nowrap" data-astro-cid-5i26sbjv> <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="currentColor" class="shrink-0" data-astro-cid-5i26sbjv> <path d="M12 .3a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2c-3.3.7-4-1.6-4-1.6-.6-1.4-1.4-1.8-1.4-1.8-1-.7.1-.7.1-.7 1.2 0 1.9 1.2 1.9 1.2 1 1.8 2.8 1.3 3.5 1 0-.8.4-1.3.7-1.6-2.7-.3-5.5-1.3-5.5-6 0-1.2.5-2.3 1.3-3.1-.1-.4-.6-1.6.1-3.2 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0C17.3 4.7 18.3 5 18.3 5c.7 1.6.2 2.8.1 3.2.8.8 1.3 1.9 1.3 3.1 0 4.6-2.8 5.6-5.5 5.9.5.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .3" data-astro-cid-5i26sbjv></path> </svg> <span class="leading-none" data-astro-cid-5i26sbjv>GitHub</span> <svg aria-hidden="true" width="10" height="10" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" class="shrink-0 transition-transform duration-[var(--duration-fast)] ease-[var(--ease-standard)] group-hover:translate-x-[1px] group-hover:-translate-y-[1px]" data-astro-cid-5i26sbjv> <path d="M7 17L17 7" data-astro-cid-5i26sbjv></path> <path d="M8 7h9v9" data-astro-cid-5i26sbjv></path> </svg> </a> </div> </nav>  <div id="mobile-menu-drawer" data-mobile-menu data-open="false" aria-hidden="true" role="dialog" aria-modal="true" aria-label="菜单" class="mobile-menu md:hidden" data-astro-cid-5i26sbjv>  <div data-mobile-menu-backdrop class="mobile-menu__backdrop" aria-hidden="true" data-astro-cid-5i26sbjv></div>  <div class="mobile-menu__panel" role="document" data-astro-cid-5i26sbjv>  <div class="mobile-menu__header" data-astro-cid-5i26sbjv> <span class="font-[var(--font-mono)] text-[12px] font-semibold tracking-[var(--tracking-wider)] text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> ZERX-LAB </span> <button type="button" data-mobile-menu-close aria-label="关闭菜单" class="inline-flex items-center justify-center h-10 w-10 text-[color:var(--color-ink-primary)] hover:bg-[color:var(--color-paper-muted)] rounded-[var(--radius-sm)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] cursor-pointer" data-astro-cid-5i26sbjv> <svg aria-hidden="true" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-5i26sbjv> <path d="M18 6 6 18" data-astro-cid-5i26sbjv></path> <path d="m6 6 12 12" data-astro-cid-5i26sbjv></path> </svg> </button> </div>  <ul role="menu" class="list-none m-0 p-0 border-t border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-secondary)] hover:bg-[color:var(--color-paper-muted)]/40 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 01 </span> <span data-astro-cid-5i26sbjv>首页</span> </span>  </a> </li><li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/projects" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-secondary)] hover:bg-[color:var(--color-paper-muted)]/40 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 02 </span> <span data-astro-cid-5i26sbjv>项目</span> </span>  </a> </li><li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/benchmarks" aria-current="page" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-primary)] bg-[color:var(--color-paper-muted)]/40" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 03 </span> <span data-astro-cid-5i26sbjv>榜单</span> </span> <span aria-hidden="true" class="mono-label text-[10px] text-[color:var(--color-ink-muted)]" data-astro-cid-5i26sbjv>
43●
44</span> </a> </li><li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/aur" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-secondary)] hover:bg-[color:var(--color-paper-muted)]/40 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 04 </span> <span data-astro-cid-5i26sbjv>AUR</span> </span>  </a> </li><li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/blog" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-secondary)] hover:bg-[color:var(--color-paper-muted)]/40 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 05 </span> <span data-astro-cid-5i26sbjv>博客</span> </span>  </a> </li><li role="none" class="border-b border-dashed border-[color:var(--color-hairline)]" data-astro-cid-5i26sbjv> <a role="menuitem" href="/about" data-mobile-menu-link class="flex items-center justify-between gap-4 h-14 px-6 mono-label text-[13px] select-none transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] text-[color:var(--color-ink-secondary)] hover:bg-[color:var(--color-paper-muted)]/40 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-5i26sbjv> <span class="flex items-center gap-3" data-astro-cid-5i26sbjv> <span aria-hidden="true" class="mono-num text-[10px] text-[color:var(--color-ink-muted)] tabular-nums" data-astro-cid-5i26sbjv> 06 </span> <span data-astro-cid-5i26sbjv>关于</span> </span>  </a> </li> </ul>  <div class="mt-6 px-6 flex flex-col gap-4" data-astro-cid-5i26sbjv> <div class="flex items-center justify-between gap-4" data-astro-cid-5i26sbjv> <span class="mono-label text-[11px] text-[color:var(--color-ink-tertiary)]" data-astro-cid-5i26sbjv> 切换语言 </span> <div role="group" aria-label="语言切换" class="lang-toggle flex items-center h-full px-3 sm:px-4 gap-1.5 select-none !px-0" data-astro-cid-got23tqz> <a href="/benchmarks/" hreflang="zh-CN" aria-current="true" aria-label="切换到 中文" data-lang="zh" class="mono-label text-[11px] leading-none tracking-[var(--tracking-wider)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] text-[color:var(--color-ink-primary)] font-semibold" data-astro-cid-got23tqz>
44 ZH </a> <span aria-hidden="true" class="text-[color:var(--color-ink-faint)] text-[10px] leading-none" data-astro-cid-got23tqz>
45·
46</span><a href="/en/benchmarks/" hreflang="en-US" aria-label="切换到 English" data-lang="en" class="mono-label text-[11px] leading-none tracking-[var(--tracking-wider)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] text-[color:var(--color-ink-muted)]" data-astro-cid-got23tqz> EN </a>  </div> </div> <div class="flex items-center justify-between gap-4" data-astro-cid-5i26sbjv> <span class="mono-label text-[11px] text-[color:var(--color-ink-tertiary)]" data-astro-cid-5i26sbjv> 切换主题 </span> <div role="group" aria-label="切换主题" class="theme-toggle flex items-center h-full px-2 sm:px-3 gap-0.5 select-none !px-0" data-astro-cid-lfoluaxz> <button type="button" data-theme-btn="light" aria-label="浅色" title="浅色" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz> <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <circle cx="12" cy="12" r="4" data-astro-cid-lfoluaxz></circle> <path d="M12 2v2" data-astro-cid-lfoluaxz></path> <path d="M12 20v2" data-astro-cid-lfoluaxz></path> <path d="m4.93 4.93 1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="m17.66 17.66 1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="M2 12h2" data-astro-cid-lfoluaxz></path> <path d="M20 12h2" data-astro-cid-lfoluaxz></path> <path d="m6.34 17.66-1.41 1.41" data-astro-cid-lfoluaxz></path> <path d="m19.07 4.93-1.41 1.41" data-astro-cid-lfoluaxz></path> </svg>   </button><button type="button" data-theme-btn="system" aria-label="跟随系统" title="跟随系统" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz>  <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <rect x="2" y="4" width="20" height="14" rx="2" data-astro-cid-lfoluaxz></rect> <path d="M8 20h8" data-astro-cid-lfoluaxz></path> <path d="M12 18v2" data-astro-cid-lfoluaxz></path> </svg>  </button><button type="button" data-theme-btn="dark" aria-label="深色" title="深色" class="theme-btn inline-flex items-center justify-center h-6 w-6 rounded-[var(--radius-sm)] text-[color:var(--color-ink-muted)] transition-colors duration-[var(--duration-fast)] ease-[var(--ease-standard)] hover:text-[color:var(--color-ink-primary)] focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-[color:var(--color-ink-primary)] cursor-pointer" data-astro-cid-lfoluaxz>   <svg aria-hidden="true" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" data-astro-cid-lfoluaxz> <path d="M21 12.79A9 9 0 1 1 11.21 3 7 7 0 0 0 21 12.79Z" data-astro-cid-lfoluaxz></path> </svg> </button> </div>   </div> </div>  <div class="mt-auto px-6 pb-6 pt-6" data-astro-cid-5i26sbjv> <a href="https://github.com/zerx-lab" target="_blank" rel="noopener noreferrer" class="flex items-center justify-center gap-2 h-12 px-5 mono-label text-[12px] bg-[color:var(--color-ink-primary)] text-[color:var(--color-paper)] rounded-[var(--radius-sm)] select-none" data-astro-cid-5i26sbjv> <svg aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="currentColor" data-astro-cid-5i26sbjv> <path d="M12 .3a12 12 0 0 0-3.8 23.4c.6.1.8-.3.8-.6v-2c-3.3.7-4-1.6-4-1.6-.6-1.4-1.4-1.8-1.4-1.8-1-.7.1-.7.1-.7 1.2 0 1.9 1.2 1.9 1.2 1 1.8 2.8 1.3 3.5 1 0-.8.4-1.3.7-1.6-2.7-.3-5.5-1.3-5.5-6 0-1.2.5-2.3 1.3-3.1-.1-.4-.6-1.6.1-3.2 0 0 1-.3 3.3 1.2a11.5 11.5 0 0 1 6 0C17.3 4.7 18.3 5 18.3 5c.7 1.6.2 2.8.1 3.2.8.8 1.3 1.9 1.3 3.1 0 4.6-2.8 5.6-5.5 5.9.5.4.8 1.1.8 2.2v3.3c0 .3.2.7.8.6A12 12 0 0 0 12 .3" data-astro-cid-5i26sbjv></path> </svg> <span data-astro-cid-5i26sbjv>GitHub</span>
46 <svg aria-hidden="true" width="11" height="11" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" class="shrink-0" data-astro-cid-5i26sbjv> <path d="M7 17L17 7" data-astro-cid-5i26sbjv></path> <path d="M8 7h9v9" data-astro-cid-5i26sbjv></path> </svg> </a> </div> </div> </div>  
46<script type="module">function i(){const t=document.querySelector("[data-mobile-menu]");if(!t)return;const o=document.querySelectorAll("[data-mobile-menu-open]"),c=document.querySelectorAll("[data-mobile-menu-close]"),s=t.querySelector("[data-mobile-menu-backdrop]"),u=t.querySelectorAll("[data-mobile-menu-link]"),l=()=>{t.setAttribute("data-open","true"),t.setAttribute("aria-hidden","false"),document.body.classList.add("mobile-menu-open"),o.forEach(e=>e.setAttribute("aria-expanded","true"))},n=()=>{t.setAttribute("data-open","false"),t.setAttribute("aria-hidden","true"),document.body.classList.remove("mobile-menu-open"),o.forEach(e=>e.setAttribute("aria-expanded","false"))};o.forEach(e=>{e.addEventListener("click",d=>{d.preventDefault(),l()})}),c.forEach(e=>{e.addEventListener("click",d=>{d.preventDefault(),n()})}),s?.addEventListener("click",n),u.forEach(e=>{e.addEventListener("click",()=>{n()})}),document.addEventListener("keydown",e=>{e.key==="Escape"&&t.getAttribute("data-open")==="true"&&n()});const a=window.matchMedia("(min-width: 768px)"),r=()=>{a.matches&&t.getAttribute("data-open")==="true"&&n()};a.addEventListener?a.addEventListener("change",r):a.addListener&&a.addListener(r)}i();document.addEventListener("astro:after-swap",i);</script>
46 </div>  <div class="app-shell__content px-5 sm:px-8 md:px-10 lg:px-12 xl:px-16 py-6 sm:py-8 lg:py-10" style="--content-max: none;" data-astro-cid-iv7lwsuo>   <section id="benchmark-panel" data-lang="zh" aria-labelledby="benchmarks-heading" class="py-8 sm:py-12" data-astro-cid-7k4hvajv> <header id="benchmarks-heading" class="section-header w-full pt-6 lg:pt-8">  <div class="flex items-baseline justify-between gap-4 mb-3"> <span class="mono-label text-[11px] sm:text-xs leading-none tracking-[var(--tracking-wider)] text-[color:var(--color-ink-secondary)] font-medium"> MODEL BENCHMARKS </span>  <span class="mono-num text-[11px] tabular-nums text-[color:var(--color-ink-tertiary)]"> 57 </span> </div>  <hr aria-hidden="true" class="border-0 border-t border-dashed border-[color:var(--color-hairline)] m-0">  <div class="mt-6 lg:mt-8"> <h2 class="font-medium text-[color:var(--color-ink-primary)] tracking-[-0.02em] leading-[1.2] text-[22px] sm:text-[24px] lg:text-[28px]">模型榜单</h2>  </div>   </header> <p class="mt-5 text-sm leading-relaxed text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>从综合表现到细分任务,按能力、机构与开放权重筛选模型,直观对比不同模型的优势。</p> <div class="mt-8 flex flex-wrap items-end gap-3" data-astro-cid-7k4hvajv> <label class="flex min-w-56 flex-1 flex-col gap-2 sm:max-w-sm" for="benchmark-search" data-astro-cid-7k4hvajv> <span class="font-[var(--font-mono)] text-xs uppercase tracking-wider text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>搜索模型或机构</span> <input id="benchmark-search" type="search" name="q" autocomplete="off" placeholder="搜索模型 / 机构…" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2 w-full" data-astro-cid-7k4hvajv> </label> <label class="flex items-center gap-2 py-2 text-sm" data-astro-cid-7k4hvajv><input id="benchmark-open" type="checkbox" data-astro-cid-7k4hvajv>开放权重</label> <label class="flex flex-col gap-2 text-sm" for="benchmark-ft" data-astro-cid-7k4hvajv> <span class="font-[var(--font-mono)] text-xs uppercase tracking-wider text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>微调模型</span> <select id="benchmark-ft" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv> <option value="hide" data-astro-cid-7k4hvajv>隐藏</option> <option value="all" data-astro-cid-7k4hvajv>全部</option> <option value="only" data-astro-cid-7k4hvajv>仅微调及基座</option> </select> </label> <label class="flex items-center gap-2 py-2 text-sm" data-astro-cid-7k4hvajv><input id="benchmark-showorg" type="checkbox" checked data-astro-cid-7k4hvajv>显示机构</label> <label class="flex flex-col gap-2 text-sm" for="benchmark-org" data-astro-cid-7k4hvajv> <span class="font-[var(--font-mono)] text-xs uppercase tracking-wider text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>机构</span> <select id="benchmark-org" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv> <option value="" data-astro-cid-7k4hvajv>所有机构</option> <option value="Abacus.AI" data-astro-cid-7k4hvajv>Abacus.AI</option><option value="Alibaba" data-astro-cid-7k4hvajv>Alibaba</option><option value="Anthropic" data-astro-cid-7k4hvajv>Anthropic</option><option value="DeepSeek" data-astro-cid-7k4hvajv>DeepSeek</option><option value="Google" data-astro-cid-7k4hvajv>Google</option><option value="Meta" data-astro-cid-7k4hvajv>Meta</option><option value="Minimax" data-astro-cid-7k4hvajv>Minimax</option><option value="Moonshot AI" data-astro-cid-7k4hvajv>Moonshot AI</option><option value="NVIDIA" data-astro-cid-7k4hvajv>NVIDIA</option><option value="OpenAI" data-astro-cid-7k4hvajv>OpenAI</option><option value="Stealth" data-astro-cid-7k4hvajv>Stealth</option><option value="Thinking Machines" data-astro-cid-7k4hvajv>Thinking Machines</option><option value="xAI" data-astro-cid-7k4hvajv>xAI</option><option value="Z.AI" data-astro-cid-7k4hvajv>Z.AI</option> </select> </label> </div> <div class="mt-5 flex flex-wrap items-start gap-3" data-astro-cid-7k4hvajv> <details id="benchmark-compare" class="relative" data-astro-cid-7k4hvajv> <summary class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2 cursor-pointer list-none" data-astro-cid-7k4hvajv>对比模型 <span id="benchmark-compare-count" data-astro-cid-7k4hvajv></span></summary> <div class="absolute left-0 z-20 mt-1 w-[min(22rem,calc(100vw-3rem))] border border-[color:var(--color-hairline)] bg-[color:var(--color-paper)] p-3 shadow-lg" data-astro-cid-7k4hvajv> <p class="mb-2 text-xs text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>已选模型</p> <div class="max-h-64 space-y-1 overflow-y-auto" role="group" aria-label="对比模型" data-astro-cid-7k4hvajv> <label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-4-5-20251101-thinking-64k-high-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 4.5 Opus Thinking High Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-4-6-thinking-auto-high-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 4.6 Opus Thinking High Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-sonnet-4-6-thinking-auto-medium-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 4.6 Sonnet Thinking Medium Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-4-7-xhigh-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 4.7 Opus Thinking xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-4-8-max-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 4.8 Opus Thinking Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-5-max-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 5 Opus Thinking Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-5-5-max-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 5.5 Opus Thinking Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-opus-5-5-xhigh-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude 5.5 Opus Thinking xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-fable-5-max-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude Fable 5 Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-fable-5-1-max-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude Fable 5.1 Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="claude-sonnet-5-xhigh-effort" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Claude Sonnet 5 xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Anthropic)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="deepseek-v4-flash-0731" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>DeepSeek V4 Flash 0731 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(DeepSeek)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="deepseek-v4-flash-vision-exp" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>DeepSeek V4 Flash Vision Exp <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(DeepSeek)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="deepseek-v4-pro-0813" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>DeepSeek V4 Pro 0813 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(DeepSeek)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="deepseek-v4.1-flash-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>DeepSeek V4.1 Flash Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(DeepSeek)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.1-pro-preview-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.1 Pro Preview High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.5-flash-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.5 Flash High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.5-flash-lite-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.5 Flash-Lite High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.6-flash-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.6 Flash High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.7-flash-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.7 Flash High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gemini-3.8-flash-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Gemini 3.8 Flash High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Google)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="glm-5.2" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GLM-5.2 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Z.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="glm-5.3" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GLM-5.3 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Z.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="glm-5.3-flash" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GLM-5.3 Flash <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Z.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.2-codex" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.2 Codex <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.2-2025-12-11-high" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.2 High <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.4-mini-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.4 Mini xHigh <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.4-nano-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.4 Nano xHigh <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.4-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.4 Thinking xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.5-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.5 Thinking xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.6-luna-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.6 Luna Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.6-sol-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.6 Sol Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-5.6-terra-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-5.6 Terra Max Effort <
46small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-6-astra-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-6 Astra Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-6-luna-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-6 Luna Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="gpt-6-sol-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>GPT-6 Sol Max Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(OpenAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="grok-4.3" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Grok 4.3 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(xAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="grok-4.5" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Grok 4.5 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(xAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="grok-4.6" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Grok 4.6 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(xAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="grok-4.7-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Grok 4.7 xHigh <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(xAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="grok-build-0.1" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Grok Build 0.1 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(xAI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="inkling-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Inkling xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Thinking Machines)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="kimi-k2.6-thinking" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Kimi K2.6 Thinking <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Moonshot AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="kimi-k2.7-code" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Kimi K2.7 Code <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Moonshot AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="kimi-k3" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Kimi K3 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Moonshot AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="minimax-m3" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Minimax M3 <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Minimax)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="muse-spark-1.1-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Muse Spark 1.1 xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Meta)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="muse-spark-1.2-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Muse Spark 1.2 xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Meta)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="muse-spark-1.3-xhigh" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Muse Spark 1.3 xHigh Effort <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Meta)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="nemotron-3-ultra-550b-a55b" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Nemotron 3 Ultra 550B A55B <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(NVIDIA)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="ox-alpha-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>ox-alpha-max <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Stealth)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.6-27b" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen 3.6 27B <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.6-plus" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen 3.6 Plus <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.7-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen 3.7 Max <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.8-flash-next" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen 3.8 Flash Next <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.8-max" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen 3.8 Max <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="qwen3.8-27b" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Qwen3.8 27B <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Alibaba)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="smaug-agentic" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Smaug Agentic <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Abacus.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="smaug-flash" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>
46Smaug Flash <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Abacus.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="smaug-mini" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Smaug Mini <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Abacus.AI)</small></span></label><label class="flex items-start gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-compare="union-alpha" class="mt-1" data-astro-cid-7k4hvajv><span data-astro-cid-7k4hvajv>Union Alpha <small class="text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>(Stealth)</small></span></label> </div> <div class="mt-3 flex flex-wrap gap-2" data-astro-cid-7k4hvajv> <button id="benchmark-compare-apply" type="button" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>应用对比</button> <button id="benchmark-compare-clear" type="button" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>清空对比</button> </div> </div> </details> <details id="benchmark-columns" class="relative" data-astro-cid-7k4hvajv> <summary class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2 cursor-pointer list-none" data-astro-cid-7k4hvajv>选择列</summary> <div class="absolute left-0 z-20 mt-1 max-h-[60vh] w-[min(23rem,calc(100vw-3rem))] overflow-y-auto border border-[color:var(--color-hairline)] bg-[color:var(--color-paper)] p-3 shadow-lg" data-astro-cid-7k4hvajv> <p class="mb-2 text-xs text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>选择列</p> <label class="flex gap-2 py-1 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="overall" checked data-astro-cid-7k4hvajv>总分</label> <div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Reasoning" checked data-astro-cid-7k4hvajv>推理</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Reasoning" checked data-astro-cid-7k4hvajv>推理</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="theory_of_mind" checked data-astro-cid-7k4hvajv>心智理论</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="zebra_puzzle" checked data-astro-cid-7k4hvajv>斑马谜题</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="spatial" checked data-astro-cid-7k4hvajv>空间推理</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="logic_with_navigation" checked data-astro-cid-7k4hvajv>导航逻辑</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Coding" checked data-astro-cid-7k4hvajv>编程</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Coding" checked data-astro-cid-7k4hvajv>编程</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="code_generation" checked data-astro-cid-7k4hvajv>代码生成</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="code_completion" checked data-astro-cid-7k4hvajv>代码补全</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Agentic Coding" checked data-astro-cid-7k4hvajv>智能体编程</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Agentic Coding" checked data-astro-cid-7k4hvajv>智能体编程</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="javascript" checked data-astro-cid-7k4hvajv>JavaScript</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="typescript" checked data-astro-cid-7k4hvajv>TypeScript</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="python" checked data-astro-cid-7k4hvajv>Python</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Mathematics" checked data-astro-cid-7k4hvajv>数学</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Mathematics" checked data-astro-cid-7k4hvajv>数学</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="AMPS_Hard" checked data-astro-cid-7k4hvajv>AMPS 高难度</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="integrals_with_game" checked data-astro-cid-7k4hvajv>游戏中的积分</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="math_comp" checked data-astro-cid-7k4hvajv>数学竞赛</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="olympiad" checked data-astro-cid-7k4hvajv>奥林匹克数学</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Data Analysis" checked data-astro-cid-7k4hvajv>数据分析</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Data Analysis" checked data-astro-cid-7k4hvajv>数据分析</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="consecutive_events" checked data-astro-cid-7k4hvajv>连续事件</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="tablejoin" checked data-astro-cid-7k4hvajv>表格连接</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="tablereformat" checked data-astro-cid-7k4hvajv>表格重排</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="Language" checked data-astro-cid-7k4hvajv>语言</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="Language" checked data-astro-cid-7k4hvajv>语言</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="connections" checked data-astro-cid-7k4hvajv>词语关联</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="plot_unscrambling" checked data-astro-cid-7k4hvajv>情节重组</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="typos" checked data-astro-cid-7k4hvajv>拼写纠错</label> </div> </div><div class="border-t border-[color:var(--color-hairline)] py-2" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm font-medium" data-astro-cid-7k4hvajv><input type="checkbox" data-group="IF" checked data-astro-cid-7k4hvajv>指令遵循</label> <div class="mt-1 grid grid-cols-1 gap-1 pl-5" data-astro-cid-7k4hvajv> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="IF" checked data-astro-cid-7k4hvajv>指令遵循</label> <label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="paraphrase" checked data-astro-cid-7k4hvajv>改写</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="simplify" checked data-astro-cid-7k4hvajv>简化</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="story_generation" checked data-astro-cid-7k4hvajv>故事生成</label><label class="flex gap-2 text-sm" data-astro-cid-7k4hvajv><input type="checkbox" data-column="summarize" checked data-astro-cid-7k4hvajv>摘要</label> </div> </div> <button id="benchmark-columns-reset" type="button" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>重置列</button> </div> </details> <p class="ml-auto self-center font-[var(--font-mono)] text-xs text-[color:var(--color-ink-secondary)]" role="status" aria-l
46ive="polite" data-astro-cid-7k4hvajv> 匹配模型: <span id="benchmark-count" data-astro-cid-7k4hvajv>57</span> </p> </div> <div class="mt-5 flex flex-wrap items-center gap-2" role="group" aria-label="类别" data-astro-cid-7k4hvajv> <button type="button" data-cat="all" aria-pressed="true" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>全部</button> <button type="button" data-cat="Reasoning" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>推理</button><button type="button" data-cat="Coding" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>编程</button><button type="button" data-cat="Agentic Coding" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>智能体编程</button><button type="button" data-cat="Mathematics" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>数学</button><button type="button" data-cat="Data Analysis" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>数据分析</button><button type="button" data-cat="Language" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>语言</button><button type="button" data-cat="IF" aria-pressed="false" class="border border-[color:var(--color-hairline)] bg-transparent px-3 py-2 text-sm text-[color:var(--color-ink-primary)] focus-visible:outline-2 focus-visible:outline-offset-2" data-astro-cid-7k4hvajv>指令遵循</button> </div> <div class="mt-5 max-w-full overflow-x-auto border-y border-[color:var(--color-hairline)]" tabindex="0" role="region" aria-label="模型榜单" data-astro-cid-7k4hvajv> <table id="benchmark-table" class="w-full min-w-[760px] border-collapse text-left text-sm" data-astro-cid-7k4hvajv> <caption class="sr-only" data-astro-cid-7k4hvajv>模型榜单 — 2026-06-25</caption> <thead data-astro-cid-7k4hvajv><tr class="border-b border-[color:var(--color-hairline)] bg-[color:var(--color-paper-muted)]/40 font-[var(--font-mono)] text-xs text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv> <th scope="col" class="px-3 py-3 font-normal" data-astro-cid-7k4hvajv>排名</th> <th scope="col" class="min-w-52 px-3 py-3 font-normal" data-astro-cid-7k4hvajv>模型</th> <th scope="col" class="px-3 py-3 font-normal" data-astro-cid-7k4hvajv>机构</th> <th scope="col" aria-sort="descending" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="overall" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>总分 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Reasoning" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>推理 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Coding" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>编程 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Agentic Coding" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>智能体编程 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Mathematics" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>数学 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Data Analysis" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>数据分析 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="Language" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>语言 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th><th scope="col" aria-sort="none" class="px-3 py-3 text-right font-normal" data-astro-cid-7k4hvajv><button type="button" data-sort="IF" class="whitespace-nowrap underline-offset-4 hover:underline focus-visible:underline" data-astro-cid-7k4hvajv>指令遵循 <span aria-hidden="true" data-astro-cid-7k4hvajv>↕</span></button></th> </tr></thead> <tbody data-astro-cid-7k4hvajv><tr data-model-id="claude-fable-5-1-max-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>1</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude Fable 5.1 Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>83.4</td> <td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.7</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.4</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>66.1</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>97.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.3</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.0</td> </tr><tr data-model-id="claude-opus-5-5-max-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>2</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 5.5 Opus Thinking Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>83.2</td> <td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>92.2</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.3</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.7</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>97.1</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.7</td> </tr><tr data-model-id="claude-fable-5-max-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>3</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude Fable 5 Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>83.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.7</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>96.0</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.5</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.8</td> </tr><tr data-model-id="gpt-6-astra-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>4</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-6 Astra Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>82.2</td> <td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>92.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>57.3</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>96.8</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.0</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.6</td> </tr><tr data-model-id="muse-spark-1.3-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>5</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Muse Spark 1.3 xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Meta</td> <td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>81.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>64.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.8</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.0</td> </tr><tr data-model-id="deepseek-v4.1-flash-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>6</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>DeepSeek V4.1 Flash Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>DeepSeek</td>
46 <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>81.1</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.0</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>93.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.0</td> </tr><tr data-model-id="gpt-5.6-sol-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>7</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.6 Sol Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>81.0</td> <td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.7</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>56.2</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>96.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.8</td> </tr><tr data-model-id="gpt-5.5-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>8</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.5 Thinking xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>80.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.9</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.7</td> </tr><tr data-model-id="claude-opus-5-max-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>9</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 5 Opus Thinking Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>80.1</td> <td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.4</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.6</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.8</td> </tr><tr data-model-id="gpt-6-sol-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>10</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-6 Sol Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>79.3</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>52.9</td><td style="background-color:rgba(47, 84, 235, 0.07)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>96.4</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>68.6</td> </tr><tr data-model-id="kimi-k3" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>11</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Kimi K3</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Moonshot AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>79.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.4</td> </tr><tr data-model-id="gemini-3.7-flash-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>12</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.7 Flash High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>78.8</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>58.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>93.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>68.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.5</td><td style="background-color:rgba(47, 84, 235, 0.17)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.9</td> </tr><tr data-model-id="qwen3.8-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>13</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen 3.8 Max</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>78.5</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>64.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.1</td> </tr><tr data-model-id="grok-4.6" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>14</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Grok 4.6</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>xAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>78.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>57.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>92.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.9</td> </tr><tr data-model-id="gpt-5.4-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>15</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.4 Thinking xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>78.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--
46color-ink-secondary)]" data-astro-cid-7k4hvajv>88.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>53.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>94.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.2</td> </tr><tr data-model-id="muse-spark-1.2-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>16</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Muse Spark 1.2 xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Meta</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>78.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>57.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.3</td> </tr><tr data-model-id="gpt-5.6-terra-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>17</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.6 Terra Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>77.9</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>94.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>64.6</td> </tr><tr data-model-id="deepseek-v4-pro-0813" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>18</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>DeepSeek V4 Pro 0813</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>DeepSeek</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>77.4</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>67.7</td> </tr><tr data-model-id="grok-4.7-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>19</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Grok 4.7 xHigh</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>xAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>77.4</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.3</td> </tr><tr data-model-id="gemini-3.1-pro-preview-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>20</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.1 Pro Preview High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>77.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>44.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.4</td><td style="background-color:rgba(47, 84, 235, 0.115)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.1</td> </tr><tr data-model-id="deepseek-v4-flash-vision-exp" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>21</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>DeepSeek V4 Flash Vision Exp</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>DeepSeek</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.8</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>68.2</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.0</td> </tr><tr data-model-id="claude-opus-4-7-xhigh-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>22</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 4.7 Opus Thinking xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.5</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>50.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>92.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>66.7</td> </tr><tr data-model-id="claude-opus-4-8-max-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>23</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 4.8 Opus Thinking Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>50.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>
4694.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>66.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.0</td> </tr><tr data-model-id="qwen3.8-flash-next" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>24</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen 3.8 Flash Next</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>61.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.6</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.1</td> </tr><tr data-model-id="glm-5.3" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>25</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GLM-5.3</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Z.AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.1</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>60.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>69.3</td> </tr><tr data-model-id="union-alpha" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>26</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Union Alpha</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Stealth</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.1</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>95.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>59.5</td> </tr><tr data-model-id="claude-sonnet-5-xhigh-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>27</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude Sonnet 5 xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>76.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>59.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>92.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.9</td> </tr><tr data-model-id="gemini-3.8-flash-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>28</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.8 Flash High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>75.8</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.0</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.8</td><td style="background-color:rgba(47, 84, 235, 0.24)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.4</td> </tr><tr data-model-id="grok-4.5" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>29</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Grok 4.5</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>xAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>75.8</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>68.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>56.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.5</td> </tr><tr data-model-id="muse-spark-1.1-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>30</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Muse Spark 1.1 xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Meta</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>75.3</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>58.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>69.6</td> </tr><tr data-model-id="qwen3.8-27b" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>31</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen3.8 27B</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>75.3</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>61.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.7</td> </tr><tr data-model-id="gemini-3.5-flash-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>32</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.5 Flash High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>74.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>49.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>64.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.6</td> </tr><tr data-model-id="gpt-5.2-2025-12-11-high" class="border-b border-dashed border-[colo
46r:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>33</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.2 High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>74.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>50.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>93.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>61.8</td> </tr><tr data-model-id="claude-opus-4-6-thinking-auto-high-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>34</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 4.6 Opus Thinking High Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>74.5</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>49.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>69.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.3</td> </tr><tr data-model-id="deepseek-v4-flash-0731" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>35</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>DeepSeek V4 Flash 0731</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>DeepSeek</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>74.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>46.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.5</td> </tr><tr data-model-id="gpt-5.2-codex" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>36</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.2 Codex</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>74.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.7</td><td style="background-color:rgba(47, 84, 235, 0.035)" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>49.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>66.4</td> </tr><tr data-model-id="gemini-3.6-flash-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>37</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.6 Flash High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>73.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>43.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>86.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.4</td> </tr><tr data-model-id="gpt-5.6-luna-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>38</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.6 Luna Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>73.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>48.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>60.1</td> </tr><tr data-model-id="glm-5.2" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>39</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GLM-5.2</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Z.AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>73.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>51.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.3</td> </tr><tr data-model-id="qwen3.7-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>40</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen 3.7 Max</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>73.1</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>43.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>85.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.0</td> </tr><tr data-model-id="claude-sonnet-4-6-thinking-auto-medium-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>41</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 4.6 Sonnet Thinking Medium Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>73.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>42.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>87.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.2</td> </tr><tr data-model-id="claude-opus-4-5-20251101-thinking-64k-high-effort" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>42</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Claude 4.5 Opus Thinking High Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Anthropic</td> <td style="" class="px-3 p
46y-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>72.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>80.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>39.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>90.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.5</td> </tr><tr data-model-id="gpt-6-luna-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>43</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-6 Luna Max Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>72.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>51.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>89.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>55.9</td> </tr><tr data-model-id="inkling-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>44</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Inkling xHigh Effort</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Thinking Machines</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>71.9</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>49.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.1</td> </tr><tr data-model-id="glm-5.3-flash" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>45</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GLM-5.3 Flash</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Z.AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>71.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>56.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>52.8</td> </tr><tr data-model-id="kimi-k2.6-thinking" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>46</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Kimi K2.6 Thinking</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Moonshot AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>70.5</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>46.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>64.4</td> </tr><tr data-model-id="gpt-5.4-nano-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>47</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.4 Nano xHigh</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>69.6</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>81.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>46.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>91.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>67.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>67.2</td> </tr><tr data-model-id="ox-alpha-max" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>48</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>ox-alpha-max</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Stealth</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>69.2</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>52.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>66.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>60.3</td> </tr><tr data-model-id="qwen3.6-plus" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>49</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen 3.6 Plus</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>68.9</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>41.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>83.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>69.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>75.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>58.3</td> </tr><tr data-model-id="kimi-k2.7-code" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>50</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Kimi K2.7 Code</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Moonshot AI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>68.4</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>82.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>45.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>77.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>56.3</td> </tr><tr data-model-id="grok-build-0.1" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>51</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Grok Build 0.1</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>xAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>67.8</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>45.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-
46cid-7k4hvajv>78.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>72.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>65.2</td> </tr><tr data-model-id="nemotron-3-ultra-550b-a55b" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>52</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Nemotron 3 Ultra 550B A55B</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>NVIDIA</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>67.4</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>38.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>88.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>54.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.4</td> </tr><tr data-model-id="minimax-m3" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>53</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Minimax M3</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Minimax</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>67.3</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>74.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>68.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>40.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>57.5</td> </tr><tr data-model-id="gpt-5.4-mini-xhigh" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>54</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>GPT-5.4 Mini xHigh</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>OpenAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>66.4</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>41.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>78.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.0</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>59.8</td> </tr><tr data-model-id="qwen3.6-27b" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>55</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Qwen 3.6 27B</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Alibaba</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>64.0</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>39.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>79.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.4</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>63.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>53.2</td> </tr><tr data-model-id="gemini-3.5-flash-lite-high" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>56</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Gemini 3.5 Flash-Lite High</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>Google</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>63.9</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>60.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>76.1</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>45.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.7</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>53.2</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>71.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>67.2</td> </tr><tr data-model-id="grok-4.3" class="border-b border-dashed border-[color:var(--color-hairline)] last:border-0 hover:bg-[color:var(--color-paper-muted)]/40" data-astro-cid-7k4hvajv> <td class="px-3 py-3 font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>57</td> <th scope="row" class="px-3 py-3 font-medium text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>Grok 4.3</th> <td class="px-3 py-3 text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>xAI</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] font-semibold tabular-nums" data-astro-cid-7k4hvajv>62.3</td> <td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>70.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>69.9</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>18.5</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>84.3</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>55.8</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>73.6</td><td style="" class="px-3 py-3 text-right font-[var(--font-mono)] tabular-nums text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>62.8</td> </tr></tbody> </table> </div> <p id="benchmark-empty" hidden class="py-8 text-center text-sm text-[color:var(--color-ink-secondary)]" role="status" data-astro-cid-7k4hvajv>没有符合条件的模型。</p> <p class="mt-6 border-l-2 border-[color:var(--color-hairline)] pl-4 text-sm leading-relaxed text-[color:var(--color-ink-secondary)]" data-astro-cid-7k4hvajv>选择单个类别查看子任务,多选类别比较综合表现;点击表头切换降序、升序与默认排序。蓝色深浅突出每列前五名,破折号表示暂无分数。</p> <p class="mt-3 text-xs text-[color:var(--color-ink-tertiary)]" data-astro-cid-7k4hvajv>数据来源: <a href="https://github.com/LiveBench/new-livebench/commit/050d326a7378fd5c70018e85700f32a910c304df" target="_blank" rel="noopener noreferrer" class="underline underline-offset-4 hover:text-[color:var(--color-ink-primary)]" data-astro-cid-7k4hvajv>LiveBench/new-livebench @ 050d326a</a></p> </section>  </div>   </main> </div>
46  <a href="#main-content" class="skip-link" data-astro-cid-iv7lwsuo> 跳转到主内容 </a>
46<script type="module" src="https://static.cloudflareinsights.com/beacon.min.js/v31edd6df95cf4e85bb4c19e7a9bdbcba1788362987495" integrity="sha512-iIg7k2xntmwu6/uSb5tpc/hySgZc4eoL31yB29W6tJFo2akwjPWcEqnCEdJvGexCL0KEQwVYv5BlowfhVz26hg==" data-cf-beacon='{"version":"2024.11.0","token":"e7d29dc627fc4377b26015a603a75906","r":1,"spa":2}' crossorigin="anonymous"></script>
46
47</body></html>  
47<script type="module" src="/_astro/BenchmarksPage.astro_astro_type_script_index_0_lang.B0nTmenN.js"></script>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.