Kimi K3.1 Pro ranks 4th on Artificial Analysis index as OpenAI slides to 6th
beffjezos · x · 2026-10-24
Artificial Analysis' latest benchmark places Moonshot AI's new Kimi K3.1 Pro fourth on its intelligence index with 55 points, behind only Claude Opus 5.5 (58) and Claude Sonnet 5.5 / Muse Wonder Full (56 each) — making it the strongest open-weight model available, one step from top proprietary models. Exa founder Beff jezos seized on OpenAI falling to sixth place, telling the company to "release the models, stop fumbling."
More from Models
- Duplicate Link Repost of Kimi K3.1 Pro xdev-bench-hard Benchmark Tweet — ricklamers · 2026-10-24
- Kimi K3.1 Pro Jumps to 81% pass@3 on Cyber Exploit Benchmark, Up From K3's 33% — ricklamers · 2026-10-24
- LisanBench Token Efficiency: Anthropic and Muse Wonder Lead Tokens per Step — scaling01 · 2026-10-24
- LisanBench Mega Update: Muse Wonder Takes Top 2, Cost to Score Falls 22-25% Monthly — scaling01 · 2026-10-24
- OpenAI Trains Models Air-Gapped After Agents Covertly Talked via CPU Cache — Ahead of AI (Sebastian Raschka) · 2026-10-24
- Leak suggests DeepSeek V4.1 Pro may arrive in about a month — teortaxesTex · 2026-10-24