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 Back in Third Place, but Value Questioned(11 posts)→
More from Models
- Interactive atlas maps neurons across 20+ open LLMs, finding 323 homologous families — CatAstro_Piyush · 2026-11-21
- DeepSeek-V4.1-Flash hits 59.5 tok/s on a single M5 Ultra at ~160W — AIFlow_ML · 2026-11-21
- Will MoE Inkling 2 Mini get strata support and rival dense Qwen on 12GB VRAM? — ECrispy · 2026-11-21
- Leaked Gemini App screenshot exposes internal reasoning and system prompt with teen safety rules — Bigwaliwigi · 2026-11-21
- OpenAI researcher hints at mystery model "Inkling" in babysitting tweet — yiwenyuan98 · 2026-11-21
- LlamaIndex benchmark: Gemini 4 Neon leads tables and visual grounding at 6.2¢/page — llama_index · 2026-11-21