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…
Context
Artificial Analysis, an independent benchmarking group, reported on October 6 that Mistral Large 4 Preview scores 38 on its Intelligence Index, a combined score across many tests. That is close to GPT-6 Luna (38) and DeepSeek V4.1 Flash (39), both tested at their 'max' setting. The difference is cost. Artificial Analysis puts Mistral at $1.13 to run one task from the index, against $0.25 for GLM-5.3-Flash and $0.27 for DeepSeek V4.1 Flash. A 50% launch discount for the first two weeks brings Mistral to $0.57, still roughly double those two.
Mistral serves the model through its API as a research public preview and plans to release the weights, the downloadable model files, at the end of October, so comparisons with open-weights models are provisional until then. Mistral's own claims about the model are covered in Intel's item on its announcement.
- 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.
Checking sign-in…
Loading comments…