Open weights fall 12 points behind in AA v5, gap triples from v4.3
ArtificialAnlys · x · 2026-10-28
Open weights models lost ground in v5: the open leader Kimi K3.1 Pro (weights not yet released) scores 46, 12 points behind the overall leader versus a 3-point gap in v4.3. Among released-weights models, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) top out at 32 — below Claude Haiku 5.5 (max). The gap is widest on HLE-Diamond (Kimi 37% vs Opus 5.5's 68%) and Terminal-Bench-Science (34% vs 63% for GPT-6 Astra).
More from Models
- Debate: Claude isn't 'lobotomized' — inference stack updates may shift old-model outputs — JasonBotterill · 2026-10-28
- AI labs near IPO, yet LLMs still produce 'astonishingly terrible prose' by default — GabGarrett · 2026-10-28
- Rebuttal: Kimi 3.1 Nears Fable on Frontier Code 2, Contradicting 'China Models Crushed' Claim — bookwormengr · 2026-10-28
- Open model Flint hits #2 trending on Hugging Face, team outlines next steps — josh_tobin_ · 2026-10-28
- Artificial Analysis Intelligence Index v5 widens open-weight gap from 3 to 12 points — ResearchCrafty1804 · 2026-10-28
- YacineMTB rails: even the best LLMs are 'complete dogshit' and he's tired of it — yacineMTB · 2026-10-28