Mistral Large 4 scores 38 on AA Intelligence Index, 1T open weights due end of October
ArtificialAnlys · x · 2026-10-06
Artificial Analysis benchmarks Mistral Large 4 Research Public Preview:
- Intelligence: 1T params (49B active), scores 38 on the Intelligence Index, comparable to GPT-6 Luna (38 max) and DeepSeek V4.1 Flash (39 max) — the most intelligent model from outside the US and China.
- Cyber: 50 on the Cyber Index, level with GLM-5.3-Flash; top-three open weights once released; 82% on CyberGym-E2E-AA, ahead of MiMo-V2.6-Pro (79%).
- Pricing: $1.36/$4.18 per 1M input/output tokens, 50% off for two weeks; $1.13 cost per task (vs $0.25 for GLM-5.3-Flash), notably pricier than peers.
- Docs/images: 19% on GDP.pdf (+18 pts over Large 3); API now takes 100 images per request (up from 8).
- 512k context, text+image input; open weights planned end of October.
Related event: Mistral Large 4 Review: France Rises to Third in Frontier AI Rankings(5 posts)→
More from Models
- GLM 5.3 full NVFP4 deployable on 4x B200 or H200 with Marlin kernels — TheZachMueller · 2026-10-06
- User complains OpenAI dot silently burned through usage and started consuming credits — badhiyahai · 2026-10-06
- Mistral Large 4 tops a benchmark about regulation, dubbed the most EU-pilled model — japie06 · 2026-10-06
- ML4 lands with strong agentic skills and 'past the threshold' for recursive self-improvement — Fluke_Ellington · 2026-10-06
- Brief reply suggests GLM 5.3 is the model being tested, not a Flash variant — TheZachMueller · 2026-10-06
- Prepending ".\n\n Okay" lifts Olmo-3-7B's MATH-500 accuracy from 42% to 78%, hinting base models already reason — arankomatsuzaki · 2026-10-06