PageSourceSearch

https://mesmer.tools/benchmarks

html mesmer.tools collected 2026-10-02 01:09:08 UTC 32,730 bytes, 14 lines download raw bytes

1<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/assets/index-B8y9X58P.css" data-rsc-css-href="/assets/index-B8y9X58P.css" data-precedence="vite-rsc/importer-resources"/>
vendor: 66 bytes, line 1
1<script async="" src="https://www.googletagmanager.com/gtag/js?id=
1G-VDTHZ7MG9M
vendor: 11 bytes, line 1
1"></script>
1<link rel="modulepreload" href="/assets/worker-entry-fYcOZbsL.js" crossorigin=""/><link rel="modulepreload" href="/assets/rolldown-runtime-DF2fYuay.js" crossorigin=""/><link rel="modulepreload" href="/assets/index-DUpuAZco.js" crossorigin=""/><link rel="modulepreload" href="/assets/preload-helper-3k_mjWfE.js" crossorigin=""/><link rel="modulepreload" href="/assets/framework-CxYYI_Sd.js" crossorigin=""/><link rel="modulepreload" href="/assets/query-BbOc3VB2.js" crossorigin=""/><title>AI Model Benchmarks | MesmerTools</title><meta name="description" content="Hands-on AI model benchmarks with real, reproducible outputs. Watch what GPT-5.5, Claude, Gemini, DeepSeek, Kimi and more actually produce from identical prompts."/><meta property="og:title" content="AI Model Benchmarks | MesmerTools"/><meta property="og:description" content="Hands-on AI model benchmarks with real, reproducible outputs from identical prompts."/><meta property="og:url" content="/benchmarks"/><meta property="og:type" content="website"/><link rel="icon" href="/favicon.svg"/><link rel="apple-touch-icon" href="/favicon.svg"/>
1<script>
2              
vendor: 169 bytes, lines 2-5
2window.dataLayer = window.dataLayer || [];
3              function gtag(){dataLayer.push(arguments);}
4              gtag('js', new Date());
5              gtag('config', '
5G-VDTHZ7MG9M
vendor: 16 bytes, lines 5-6
5');
6            
6</script>
6<script>
7              (function(c,l,a,r,i,t,y){
8                  c[a]=c[a]||function(){(c[a].q=c[a].q||[]).push(arguments)};
9                  t=l.createElement(r);t.async=1;t.src="https://www.clarity.ms/tag/"+i;
10                  y=l.getElementsByTagName(r)[0];y.parentNode.insertBefore(t,y);
11              })(window, document, "clarity", "script", "w2ucxgxlqe");
12            </script>
12<script>self.__VINEXT_RSC_PARAMS__={}</script>
12<script>self.__VINEXT_RSC_NAV__={"pathname":"/benchmarks","searchParams":[]}</script>
12<link rel="modulepreload" href="/assets/index-DUpuAZco.js" />
13</head><body><div class="min-h-screen flex flex-col"><header class="sticky top-0 z-50 bg-bg border-b border-border px-6 transition-shadow duration-300"><div class="max-w-container mx-auto flex items-center justify-between h-14 gap-4"><a href="/" class="flex items-center gap-2 shrink-0 no-underline"><div class="w-7 h-7 bg-gradient-to-br from-amber to-sienna rounded-[7px] flex items-center justify-center text-sm font-extrabold text-bg">M</div><span class="text-base font-bold text-text-primary tracking-tight whitespace-nowrap">MesmerTools</span></a><nav class="flex items-center gap-1"><div class="relative"><button class="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-sm font-medium transition-colors text-text-secondary hover:text-text-primary"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-wrench w-3.5 h-3.5"><path d="M14.7 6.3a1 1 0 0 0 0 1.4l1.6 1.6a1 1 0 0 0 1.4 0l3.77-3.77a6 6 0 0 1-7.94 7.94l-6.91 6.91a2.12 2.12 0 0 1-3-3l6.91-6.91a6 6 0 0 1 7.94-7.94l-3.76 3.76z"></path></svg><span class="hidden sm:inline">Free Tools</span><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-chevron-down w-3 h-3 transition-transform"><path d="m6 9 6 6 6-6"></path></svg></button></div><a href="/api-tools" class="hidden md:inline-flex px-3 py-1.5 rounded-lg text-sm font-medium text-text-secondary hover:text-text-primary transition-colors no-underline">APIs</a><a href="/benchmarks" class="hidden md:inline-flex px-3 py-1.5 rounded-lg text-sm font-medium text-text-secondary hover:text-text-primary transition-colors no-underline">Benchmarks</a><a href="/blog" class="hidden md:inline-flex px-3 py-1.5 rounded-lg text-sm font-medium text-text-secondary hover:text-text-primary transition-colors no-underline">Blog</a></nav><div class="flex items-center gap-3"><div class="flex items-center gap-3" aria-hidden="true"><div class="h-5 w-14 rounded bg-bg-elevated"></div><div class="h-8 w-[124px] rounded-lg bg-bg-elevated"></div></div></div></div></header><main class="flex-1"><div class="min-h-screen bg-bg"><div class="max-w-container mx-auto px-6 py-10 max-[550px]:px-4"><a href="/" class="inline-flex items-center gap-1.5 text-xs text-text-muted hover:text-amber transition-colors mb-8"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-left w-3.5 h-3.5"><path d="m12 19-7-7 7-7"></path><path d="M19 12H5"></path></svg>Back to home</a><div class="max-w-2xl mb-12"><h1 class="text-4xl sm:text-5xl font-bold text-text-primary tracking-tight mb-4">Model<!-- --> <span class="bg-gradient-to-br from-amber to-sienna bg-clip-text text-transparent">Benchmarks</span></h1><p class="text-base text-text-secondary leading-relaxed mb-2">Real outputs instead of synthetic eval scores. Each benchmark gives every model the same prompts through the same pipeline, then shows you everything that came out, including the failures.</p></div><div class="grid grid-cols-1 md:grid-cols-2 gap-4 mb-16"><a href="/benchmarks/llm-tier-list" class="group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5"><div class="w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-layout-list w-5 h-5 text-amber"><rect width="7" height="7" x="3" y="3" rx="1"></rect><rect width="7" height="7" x="3" y="14" rx="1"></rect><path d="M14 4h7"></path><path d="M14 9h7"></path><path d="M14 15h7"></path><path d="M14 20h7"></path></svg></div><h2 class="text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors">LLM Tier List Maker</h2><p class="text-sm text-text-secondary leading-relaxed mb-4">Rank this week&#x27;s most-used paid models on OpenRouter alongside the Artificial Analysis leaders. Add new releases the day they drop and export a shareable image.</p><span class="inline-flex items-center gap-1 text-xs font-semibold text-amber">Make your tier list<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg></span></a><a href="/benchmarks/qwen-image-2-1" class="group block rounded-xl border border-border bg-bg-card p-6 hover:border-amber/40 hover:bg-bg-card-hover transition-colors"><h2 class="text-lg font-bold text-text-primary mb-2 group-hover:text-amber">Qwen Image 2.1: INT4 + FP4</h2><p class="text-sm text-text-secondary leading-relaxed mb-4">I tested INT4 on a 4070 Ti SUPER and FP4 on a 5090. Compare images, model sizes and measured speed against BF16.</p><span class="inline-flex items-center gap-1 text-xs font-semibold text-amber">Compare the images <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right w-3.5 h-3.5"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg></span></a><a href="/benchmarks/ai-video-generation" class="group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5"><div class="w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clapperboard w-5 h-5 text-amber"><path d="M20.2 6 3 11l-.9-2.4c-.3-1.1.3-2.2 1.3-2.5l13.5-4c1.1-.3 2.2.3 2.5 1.3Z"></path><path d="m6.2 5.3 3.1 3.9"></path><path d="m12.4 3.4 3.1 4"></path><path d="M3 11h18v8a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2Z"></path></svg></div><h2 class="text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors">AI Video Generation</h2><p class="text-sm text-text-secondary leading-relaxed mb-4">24<!-- --> LLMs each generate <!-- -->7<!-- --> Remotion motion-design videos from identical prompts via FrameCall. The lineup includes GPT-5.6, Claude, Gemini 3.1 Pro, DeepSeek V4 and Kimi K2.6.</p><span class="inline-flex items-center gap-1 text-xs font-semibold text-amber">Watch the results<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg></span></a><a href="/benchmarks/openrouter-model-spend" class="group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5"><div class="w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-chart-column w-5 h-5 text-amber"><path d="M3 3v16a2 2 0 0 0 2 2h16"></path><path d="M18 17V9"></path><path d="M13 17V5"></path><path d="M8 17v-3"></path></svg></div><h2 class="text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors">OpenRouter Model Spend</h2><p class="text-sm text-text-secondary leading-relaxed mb-4">Weekly USD spend per model on OpenRouter over the last 52 weeks, priced with time-accurate rates plus cache-adjusted estimates. Refreshes weekly.</p><span class="inline-flex items-center gap-1 text-xs font-semibold text-amber">See who pays the most<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg></span></a><a href="/random/claude-performance" class="group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5"><div class="w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-activity w-5 h-5 text-amber"><path d="M22 12h-2.48a2 2 0 0 0-1.93 1.46l-2.35 8.36a.25.25 0 0 1-.48 0L9.24 2.18a.25.25 0 0 0-.48 0l
13-2.35 8.36A2 2 0 0 1 4.49 12H2"></path></svg></div><h2 class="text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors">Claude Code Performance</h2><p class="text-sm text-text-secondary leading-relaxed mb-4">Daily SWE-Bench-Pro pass rates for Claude Code on Opus 4.6, measured against a fixed baseline so 1-day, 7-day and 30-day regressions show up as they happen. Data from Marginlab, refreshed every 6 hours.</p><span class="inline-flex items-center gap-1 text-xs font-semibold text-amber">Check today&#x27;s pass rate<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg></span></a></div><div class="border-t border-border pt-8 text-center text-xs text-text-muted">More benchmarks coming. Have an idea for a model face-off?<!-- --> <a href="/submit" class="text-amber hover:underline">Tell us</a>.</div></div></div></main><footer class="border-t border-border bg-bg-elevated mt-auto"><div class="max-w-container mx-auto px-6 py-12"><div class="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-4 gap-10"><div><a href="/" class="flex items-center gap-2 no-underline mb-3"><div class="w-7 h-7 bg-gradient-to-br from-amber to-sienna rounded-[7px] flex items-center justify-center text-sm font-extrabold text-bg">M</div><span class="text-base font-bold text-text-primary tracking-tight">MesmerTools</span></a><p class="text-sm text-text-muted leading-relaxed">Discover the best AI tools and utilities</p></div><div><h4 class="text-xs font-semibold uppercase tracking-wider text-text-secondary mb-4">Directory</h4><ul class="space-y-2.5"><li><a href="/" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Browse Tools</a></li><li><a href="/submit" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Submit a Tool</a></li><li><button class="text-sm text-text-muted hover:text-text-primary transition-colors">Sign In</button></li><li><button class="text-sm text-text-muted hover:text-text-primary transition-colors">Register</button></li></ul></div><div><h4 class="text-xs font-semibold uppercase tracking-wider text-text-secondary mb-4">Free Tools</h4><ul class="space-y-2.5"><li><a href="/free-tools/json-formatter" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">JSON Formatter</a></li><li><a href="/free-tools/ai-logo-maker" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">AI Logo Maker</a></li><li><a href="/free-tools/token-price-calculator" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Token Price Calculator</a></li><li><a href="/free-tools/ai-music-maker" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">AI Music Maker</a></li><li><a href="/free-tools/terminal-paste-cleaner" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Terminal Paste Cleaner</a></li><li><a href="/free-tools/claude-code-viewer" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Claude Code Viewer</a></li></ul></div><div><h4 class="text-xs font-semibold uppercase tracking-wider text-text-secondary mb-4">Resources</h4><ul class="space-y-2.5"><li><a href="/blog" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Blog</a></li><li><a href="/benchmarks/ai-video-generation" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">AI Video Benchmark</a></li><li><a href="/api-tools" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Developer APIs</a></li><li><a href="/random/is-it-peak-hours" class="text-sm text-text-muted hover:text-text-primary transition-colors no-underline">Is it Peak Hours for Claude?</a></li><li><a href="/random/claude-performance" class="text-sm text-text-muted hover:text-text-primary transition-colors no-u
13nderline">Claude Code Performance</a></li></ul></div></div><div class="mt-10 pt-6 border-t border-border flex flex-col sm:flex-row items-center justify-between gap-3"><p class="text-xs text-text-muted">© 2026 MesmerTools. All rights reserved.</p><div class="flex items-center gap-4"><a href="/privacy-policy" class="text-xs text-text-muted hover:text-text-primary transition-colors no-underline">Privacy Policy</a><a href="/terms-of-service" class="text-xs text-text-muted hover:text-text-primary transition-colors no-underline">Terms of Service</a></div></div></div></footer></div><section aria-label="Notifications alt+T" tabindex="-1" aria-live="polite" aria-relevant="additions text" aria-atomic="false"></section>
13<script id="_R_">import("/assets/index-DUpuAZco.js")</script>
13<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":"b46beeeba3014903aa97cd1c9d58aae7","r":1,"spa":2}' crossorigin="anonymous"></script>
13
14</body></html>
14<script>self.__VINEXT_RSC_CHUNKS__=self.__VINEXT_RSC_CHUNKS__||[];self.__VINEXT_RSC_CHUNKS__.push("1:I[\"0deffcb8ffd7\",[],\"LayoutSegmentProvider\",1]\n2:I[\"7ebdbd3f6546\",[],\"SentryClientInit\",1]\n3:I[\"bbb6142c7cbf\",[],\"Providers\",1]\n4:I[\"cd32d6ab0418\",[],\"AppShell\",1]\n:HL[\"/assets/index-B8y9X58P.css\",\"style\"]\n")</script>
14<script>self.__VINEXT_RSC_CHUNKS__=self.__VINEXT_RSC_CHUNKS__||[];self.__VINEXT_RSC_CHUNKS__.push("0:[\"$\",\"$L1\",null,{\"childSegments\":[\"benchmarks\"],\"children\":[[[\"$\",\"link\",\"css:/assets/index-B8y9X58P.css\",{\"rel\":\"stylesheet\",\"precedence\":\"vite-rsc/importer-resources\",\"href\":\"/assets/index-B8y9X58P.css\",\"data-rsc-css-href\":\"/assets/index-B8y9X58P.css\"}],\"$undefined\"],[\"$\",\"html\",null,{\"lang\":\"en\",\"suppressHydrationWarning\":true,\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"script\",null,{\"async\":true,\"src\":\"https://www.googletagmanager.com/gtag/js?id=G-VDTHZ7MG9M\"}],[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"\\n              window.dataLayer = window.dataLayer || [];\\n              function gtag(){dataLayer.push(arguments);}\\n              gtag('js', new Date());\\n              gtag('config', 'G-VDTHZ7MG9M');\\n            \"}}],[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"\\n              (function(c,l,a,r,i,t,y){\\n                  c[a]=c[a]||function(){(c[a].q=c[a].q||[]).push(arguments)};\\n                  t=l.createElement(r);t.async=1;t.src=\\\"https://www.clarity.ms/tag/\\\"+i;\\n                  y=l.getElementsByTagName(r)[0];y.parentNode.insertBefore(t,y);\\n              })(window, document, \\\"clarity\\\", \\\"script\\\", \\\"w2ucxgxlqe\\\");\\n            \"}}]]}],[\"$\",\"body\",null,{\"children\":[[\"$\",\"$L2\",null,{}],[\"$\",\"$L3\",null,{\"children\":[\"$\",\"$L4\",null,{\"children\":[[\"$\",\"meta\",null,{\"charSet\":\"utf-8\"}],[[\"$\",\"title\",\"0\",{\"children\":\"AI Model Benchmarks | MesmerTools\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Hands-on AI model benchmarks with real, reproducible outputs. Watch what GPT-5.5, Claude, Gemini, DeepSeek, Kimi and more actually produce from identical prompts.\"}],[\"$\",\"meta\",\"2\",{\"property\":\"og:title\",\"content\":\"AI Model Benchmarks | MesmerTools\"}],[\"$\",\"meta\",\"3\",{\"property\":\"og:description\",\"content\":\"Hands-on AI model benchmarks with real, reproducible outputs from identical prompts.\"}],[\"$\",\"meta\",\"4\",{\"property\":\"og:url\",\"content\":\"/benchmarks\"}],[\"$\",\"meta\",\"5\",{\"property\":\"og:type\",\"content\":\"website\"}],[\"$\",\"link\",\"6\",{\"rel\":\"icon\",\"href\":\"/favicon.svg\"}],[\"$\",\"link\",\"7\",{\"rel\":\"apple-touch-icon\",\"href\":\"/favicon.svg\"}]],[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}]],[\"$\",\"$L1\",null,{\"childSegments\":[],\"children\":[\"$\",\"div\",null,{\"className\":\"min-h-screen bg-bg\",\"children\":[\"$\",\"div\",null,{\"className\":\"max-w-container mx-auto px-6 py-10 max-[550px]:px-4\",\"children\":[[\"$\",\"a\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center gap-1.5 text-xs text-text-muted hover:text-amber transition-colors mb-8\",\"children\":[[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-left w-3.5 h-3.5\",\"children\":[[\"$\",\"path\",\"1l729n\",{\"d\":\"m12 19-7-7 7-7\"}],[\"$\",\"path\",\"x3x0zl\",{\"d\":\"M19 12H5\"}],\"$undefined\"]}],\"Back to home\"]}],[\"$\",\"div\",null,{\"className\":\"max-w-2xl mb-12\",\"children\":[[\"$\",\"h1\",null,{\"className\":\"text-4xl sm:text-5xl font-bold text-text-primary tracking-tight mb-4\",\"children\":[\"Model\",\" \",[\"$\",\"span\",null,{\"className\":\"bg-gradient-to-br from-amber to-sienna bg-clip-text text-transparent\",\"children\":\"Benchmarks\"}]]}],[\"$\",\"p\",null,{\"className\":\"text-base text-text-secondary leading-relaxed mb-2\",\"children\":\"Real outputs instead of synthetic eval scores. Each benchmark gives every model the same prompts through the same pipeline, then shows you everything that came out, including the failures.\"}]]}],[\"$\",\"div\",null,{\"className\":\"grid grid-cols-1 md:grid-cols-2 gap-4 mb-16\",\"children\":[[\"$\",\"a\",null,{\"href\":\"/benchmarks/llm-tier-list\",\"className\":\"group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5\",\"children\":[[\"$\",\"div\",null,{\"className\":\"w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4\",\"children\":\"$L5\"}],\"$L6\",\"$L7\",\"$L8\"]}],\"$L9\",\"$La\",\"$Lb\",\"$Lc\"]}],\"$Ld\"]}]}]}]]}]}]]}]]}]]}]\n5:[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\"
14:24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-layout-list w-5 h-5 text-amber\",\"children\":[[\"$\",\"rect\",\"1g98yp\",{\"width\":\"7\",\"height\":\"7\",\"x\":\"3\",\"y\":\"3\",\"rx\":\"1\"}],[\"$\",\"rect\",\"1bb6yr\",{\"width\":\"7\",\"height\":\"7\",\"x\":\"3\",\"y\":\"14\",\"rx\":\"1\"}],[\"$\",\"path\",\"3xa0d5\",{\"d\":\"M14 4h7\"}],[\"$\",\"path\",\"1icrd9\",{\"d\":\"M14 9h7\"}],[\"$\",\"path\",\"1mj8o2\",{\"d\":\"M14 15h7\"}],[\"$\",\"path\",\"11slyb\",{\"d\":\"M14 20h7\"}],\"$undefined\"]}]\n6:[\"$\",\"h2\",null,{\"className\":\"text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors\",\"children\":\"LLM Tier List Maker\"}]\n7:[\"$\",\"p\",null,{\"className\":\"text-sm text-text-secondary leading-relaxed mb-4\",\"children\":\"Rank this week's most-used paid models on OpenRouter alongside the Artificial Analysis leaders. Add new releases the day they drop and export a shareable image.\"}]\n8:[\"$\",\"span\",null,{\"className\":\"inline-flex items-center gap-1 text-xs font-semibold text-amber\",\"children\":[\"Make your tier list\",[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5\",\"children\":[[\"$\",\"path\",\"1ays0h\",{\"d\":\"M5 12h14\"}],[\"$\",\"path\",\"xquz4c\",{\"d\":\"m12 5 7 7-7 7\"}],\"$undefined\"]}]]}]\n9:[\"$\",\"a\",null,{\"href\":\"/benchmarks/qwen-image-2-1\",\"className\":\"group block rounded-xl border border-border bg-bg-card p-6 hover:border-amber/40 hover:bg-bg-card-hover transition-colors\",\"children\":[[\"$\",\"h2\",null,{\"className\":\"text-lg font-bold text-text-primary mb-2 group-hover:text-amber\",\"children\":\"Qwen Image 2.1: INT4 + FP4\"}],[\"$\",\"p\",null,{\"className\":\"text-sm text-text-secondary leading-relaxed mb-4\",\"children\":\"I tested INT4 on a 4070 Ti SUPER and FP4 on a 5090. Compare images, model sizes and measured speed against BF16.\"}],[\"$\",\"span\",null,{\"className\":\"inline-flex items-center gap-1 text-xs font-semibold text-amber\",\"children\":[\"Compare the images \",[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-right w-3.5 h-3.5\",\"children\":[[\"$\",\"path\",\"1ays0h\",{\"d\":\"M5 12h14\"}],[\"$\",\"path\",\"xquz4c\",{\"d\":\"m12 5 7 7-7 7\"}],\"$undefined\"]}]]}]]}]\n")</script>
14<script>self.__VINEXT_RSC_CHUNKS__=self.__VINEXT_RSC_CHUNKS__||[];self.__VINEXT_RSC_CHUNKS__.push("a:[\"$\",\"a\",null,{\"href\":\"/benchmarks/ai-video-generation\",\"className\":\"group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5\",\"children\":[[\"$\",\"div\",null,{\"className\":\"w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4\",\"children\":[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-clapperboard w-5 h-5 text-amber\",\"children\":[[\"$\",\"path\",\"1tn4o7\",{\"d\":\"M20.2 6 3 11l-.9-2.4c-.3-1.1.3-2.2 1.3-2.5l13.5-4c1.1-.3 2.2.3 2.5 1.3Z\"}],[\"$\",\"path\",\"iuk76l\",{\"d\":\"m6.2 5.3 3.1 3.9\"}],[\"$\",\"path\",\"6hsd6n\",{\"d\":\"m12.4 3.4 3.1 4\"}],[\"$\",\"path\",\"ltgou9\",{\"d\":\"M3 11h18v8a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2Z\"}],\"$undefined\"]}]}],[\"$\",\"h2\",null,{\"className\":\"text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors\",\"children\":\"AI Video Generation\"}],[\"$\",\"p\",null,{\"className\":\"text-sm text-text-secondary leading-relaxed mb-4\",\"children\":[24,\" LLMs each generate \",7,\" Remotion motion-design videos from identical prompts via FrameCall. The lineup includes GPT-5.6, Claude, Gemini 3.1 Pro, DeepSeek V4 and Kimi K2.6.\"]}],[\"$\",\"span\",null,{\"className\":\"inline-flex items-center gap-1 text-xs font-semibold text-amber\",\"children\":[\"Watch the results\",[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5\",\"children\":[[\"$\",\"path\",\"1ays0h\",{\"d\":\"M5 12h14\"}],[\"$\",\"path\",\"xquz4c\",{\"d\":\"m12 5 7 7-7 7\"}],\"$undefined\"]}]]}]]}]\nb:[\"$\",\"a\",null,{\"href\":\"/benchmarks/openrouter-model-spend\",\"className\":\"group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5\",\"children\":[[\"$\",\"div\",null,{\"className\":\"w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4\",\"children\":[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-chart-column w-5 h-5 text-amber\",\"children\":[[\"$\",\"path\",\"c24i48\",{\"d\":\"M3 3v16a2 2 0 0 0 2 2h16\"}],[\"$\",\"path\",\"2bz60n\",{\"d\":\"M18 17V9\"}],[\"$\",\"path\",\"1frdt8\",{\"d\":\"M13 17V5\"}],[\"$\",\"path\",\"17ska0\",{\"d\":\"M8 17v-3\"}],\"$undefined\"]}]}],[\"$\",\"h2\",null,{\"className\":\"text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors\",\"children\":\"OpenRouter Model Spend\"}],[\"$\",\"p\",null,{\"className\":\"text-sm text-text-secondary leading-relaxed mb-4\",\"children\":\"Weekly USD spend per model on OpenRouter over the last 52 weeks, priced with time-accurate rates plus cache-adjusted estimates. Refreshes weekly.\"}],[\"$\",\"span\",null,{\"className\":\"inline-flex items-center gap-1 text-xs font-semibold text-amber\",\"children\":[\"See who pays the most\",[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5\",\"children\":[[\"$\",\"path\",\"1ays0h\",{\"d\":\"M5 12h14\"}],[\"$\",\"path\",\"xquz4c\",{\"d\":\"m12 5 7 7-7 7\"}],\"$undefined\"]}]]}]]}]\n")</script>
14<script>self.__VINEXT_RSC_CHUNKS__=self.__VINEXT_RSC_CHUNKS__||[];self.__VINEXT_RSC_CHUNKS__.push("c:[\"$\",\"a\",null,{\"href\":\"/random/claude-performance\",\"className\":\"group block no-underline rounded-xl border border-border bg-bg-card p-6 transition-all duration-[250ms] ease-[cubic-bezier(0.22,1,0.36,1)] hover:border-amber/40 hover:bg-bg-card-hover hover:shadow-[0_0_24px_rgba(245,158,11,0.08)] hover:-translate-y-0.5\",\"children\":[[\"$\",\"div\",null,{\"className\":\"w-10 h-10 rounded-lg bg-amber/10 border border-amber/25 flex items-center justify-center mb-4\",\"children\":[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-activity w-5 h-5 text-amber\",\"children\":[[\"$\",\"path\",\"169zse\",{\"d\":\"M22 12h-2.48a2 2 0 0 0-1.93 1.46l-2.35 8.36a.25.25 0 0 1-.48 0L9.24 2.18a.25.25 0 0 0-.48 0l-2.35 8.36A2 2 0 0 1 4.49 12H2\"}],\"$undefined\"]}]}],[\"$\",\"h2\",null,{\"className\":\"text-lg font-bold text-text-primary mb-2 group-hover:text-amber transition-colors\",\"children\":\"Claude Code Performance\"}],[\"$\",\"p\",null,{\"className\":\"text-sm text-text-secondary leading-relaxed mb-4\",\"children\":\"Daily SWE-Bench-Pro pass rates for Claude Code on Opus 4.6, measured against a fixed baseline so 1-day, 7-day and 30-day regressions show up as they happen. Data from Marginlab, refreshed every 6 hours.\"}],[\"$\",\"span\",null,{\"className\":\"inline-flex items-center gap-1 text-xs font-semibold text-amber\",\"children\":[\"Check today's pass rate\",[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-arrow-right w-3.5 h-3.5 transition-transform group-hover:translate-x-0.5\",\"children\":[[\"$\",\"path\",\"1ays0h\",{\"d\":\"M5 12h14\"}],[\"$\",\"path\",\"xquz4c\",{\"d\":\"m12 5 7 7-7 7\"}],\"$undefined\"]}]]}]]}]\nd:[\"$\",\"div\",null,{\"className\":\"border-t border-border pt-8 text-center text-xs text-text-muted\",\"children\":[\"More benchmarks coming. Have an idea for a model face-off?\",\" \",[\"$\",\"a\",null,{\"href\":\"/submit\",\"className\":\"text-amber hover:underline\",\"children\":\"Tell us\"}],\".\"]}]\n")</script>
14<script>self.__VINEXT_RSC_DONE__=true</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.