Vibeleaderboard
← All Intel
Intel / post

Mistral Large 4 benchmarks at 38, with a steep cost premium

Source
x.com
Date
ArtificialAnlys@ArtificialAnlys

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…

Read the full post on X

Context

Artificial Analysis, an independent model-benchmarking group, found on October 6 that Mistral Large 4 Preview matches its rivals on capability but not on price. The model scores 38 on the group's Intelligence Index, comparable to GPT-6 Luna (38) and DeepSeek V4.1 Flash (39), both tested at their 'max' setting. That is enough, by Artificial Analysis's count, to make it the most capable model built outside the US and China.

The gap shows up in cost per task, Artificial Analysis's figure for running one task from the index at the model's standard prices. Mistral Large 4 Preview came to $1.13, against $0.25 for GLM-5.3-Flash and $0.27 for DeepSeek V4.1 Flash, more than four times as much for a similar score. Its list price is $1.36 per million input and $4.18 per million output tokens. A 50% launch discount for the first two weeks brings the cost per task to $0.57, which is still about double the two cheaper models.

The same report puts the model at 50 on Artificial Analysis's Cyber Index, which measures cyber defense capability, level with GLM-5.3-Flash and behind MiMo-V2.6-Pro (56). Its best single result was 82% on CyberGym-E2E-AA. When the report came out, Mistral had released Large 4 only as a research preview on its API, with downloadable weights for the 1-trillion-parameter model planned for the end of October, so the group's ranking of it among open-weights models assumed that release would happen. Mistral's own launch claims are in Intel's item on the announcement.

Terms in this piece · Glossary
  • 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.
  • 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.
  • context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
More from ArtificialAnlys
Recommended reads
Comments

Checking sign-in…

Loading comments…