Independent benchmarks put Mistral Large 4 at 38, at a steep cost premium
- Source
- x.com
- Date
Mistral has released Mistral Large 4, scoring 38 on the Artificial Analysis Intelligence Index; France is back to having the most intelligent model from outside the US and China @MistralAI has released Mistral Large 4 in Research Public Preview, with plans to release the weights of the 1T parameter (49B active) model at the end of October. It achieves 38 on the Artificial Analysis Intelligence Index, comparable to GPT-6 Luna (max, 38) and DeepSeek V4.1 Flash (max, 39). It also achieves 50% on the Artificial Analysis Cyber Index, level with GLM-5.3-Flash and ahead of models such as Kimi K3 and DeepSeek V4.1 Flash (max). Key benchmarking results for Mistral Large 4 Preview: ➤ Most intelligent model from outside the US and China: Mistral Large 4 Preview scores 38 on the Intelligence Index, comparable to DeepSeek V4.1 Flash (max, 39) and GPT-6 Luna (max, 38). This makes it the most intelligent model from outside the US and China, ahead of countries such as South Korea and the United Arab Emirates ➤ Level with GLM-5.3-Flash on cyber defense capability: Mistral Large 4 Preview scores 50 on the Artificial Analysis Cyber Index, level with GLM-5.3-Flash (50) and behind MiMo-V2.6-Pro…
Independent numbers put Mistral Large 4 level with GPT-6 Luna and DeepSeek V4.1 Flash on intelligence but at over 4x the cost per task of similar open models. That cost gap matters when choosing a model for workloads.
- Artificial Analysis lists Mistral Large 4 Preview at $1.36/$4.18 per 1M input/output , or $1.13 per Intelligence Index task. A two-week 50% launch discount cuts that to $0.57, still above GLM-5.3-Flash ($0.25) and DeepSeek V4.1 Flash ($0.27).
- Its Cyber Index score of 50 ties GLM-5.3-Flash and trails MiMo-V2.6-Pro (56). Artificial Analysis says it would rank among the top three models on that index once the weights are released.
- It scores 19% on GDP.pdf document and image reasoning, 18 points above Mistral Large 3, a gain Artificial Analysis partly credits to the API now accepting 100 images per request instead of 8.
- Per Artificial Analysis, the preview has a 512k-token and accepts text and image input with text output.
- open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…