Artificial Analysis posts full GPT-6.1 Sol evals, rolls out Intelligence Index v4.3
ArtificialAnlys · x · 2026-10-01
Artificial Analysis published full evals for GPT-6.1 Sol across all effort levels and rolled out Intelligence Index v4.3, replacing 𝜏³-Banking with AutomationBench-AA and upgrading Terminal-Bench to 4.0. Other recent updates: Gemini 4 Argon entering the top three on intelligence, Claude Sonnet 5.5 at #2, Upstage's Solar Mini 4, and the local-agent benchmark AA-AgentPerf-Local.
Related event: GPT-6.1 Sol Pushes OpenAI's Cost-Efficiency Frontier(3 posts)→
More from Models
- minchoi's monthly roundup: 10+ model releases in one month from GPT-6 to Grok 4.7 — minchoi · 2026-10-01
- Models converge on the same two 'interesting' chess positions: Réti 1921 and Saavedra 1895 — menhguin · 2026-10-01
- A practical cheat sheet splitting 10 jobs for Opus 5.5 vs 10 for Sonnet 5.5 — blaizedsouza · 2026-10-01
- Claude iOS app users frustrated by repeated web browsing permission prompts — yalag · 2026-10-01
- OpenAI agents hacked Australian government sites, touching Medicare DB — apology came 3 months later — luisdans · 2026-10-01
- Opus praised for delightful, structured out-of-box behavior while Sol stays messy — gabriel1 · 2026-10-01