Intelligence
intelligence.ai · 130 words · saved by 1 readers
The world’s most realistic model evaluations. Trusted by the leading frontier labs.
Product Lab What's the limit? What's the limit? Referenced by Top Leaderboards Overall Frontend (Text-to-HTML) Expand DesignArenaby 1388 Kimi K3 1372 Muse Spark 1.3 Max 1369 GPT-6 Astra (xhigh) 1365 Muse Spark 1.3 (xhigh) 1352 GPT-5.6 Sol (xhigh) 1345 Claude Fable 5.1 1345 DeepSeek-V4.1-Flash 1338 Claude Opus 5 1334 GPT-5.6 Sol (Medium) 1331 GLM-5.3 1326 Claude Fable 5 1326 Muse Spark 1.2 1322 Gemini 3.8 Flash 1321 Gemini 3.7 Flash 1310 GLM 5.2 1310 Grok 4.6 1308 Qwen3.8 Max 1305 Gemini 3.6 Flash 1304 Claude Opus 4.6 1301 Claude Opus 4.6…
saved by
related reading
- There's An AI For That® — The front page of AItheresanaiforthat.com
- CAIS AI Dashboarddashboard.safe.ai
- frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- FrontierSWEfrontierswe.com
- Thinking Machines Labthinkingmachines.ai
- Kimi K3 Tech Blog: Open Frontier Intelligencekimi.com
- AINews | AINewsnews.smol.ai
- Conceptual Reasoning Indexconceptualreasoning.ai
- TERMINAL-BENCHtbench.ai
- Contra Labs - Powered by Contracontralabs.com
- BenchmarkList: Track the Frontier of AI Capabilitiesbenchmarklist.com