Mistral

Mistral Large 3

Dec 2, 2025Former stealth modelOpen weightsModels.devHugging Face

Compare

Intelligence

9.3

#448 of 744Rank 448 of 744 measured models

Coding

20.1

#230 of 298Rank 230 of 298 measured models

Output speed

75.3 t/s

#238 of 403Rank 238 of 403 measured models

Price/1M

$0.75

#335 of 659Rank 335 of 659 measured models

Context window

256K

#518 of 1199Rank 518 of 1199 measured models

Cost per task

$0.0311

#29 of 193Rank 29 of 193 measured models

Mistral Large 3 scores 9.3 on the Artificial Analysis Intelligence Index, ranking 448th of 744 measured models. The closest models on this index are Gemini 2.5 Flash-Lite Preview (Sep '25) (9.3), Llama 4 Maverick (9.3), and Mistral Large 3 2512 (9.3). At $0.75 per million tokens (3:1 input/output blended price), it is priced close to Mistral Large 3 2512 ($0.75), more expensive than Gemini 2.5 Flash-Lite Preview (Sep '25) ($0.175) and Llama 4 Maverick ($0.405). With an output speed of 75.3 t/s, it is faster than Llama 4 Maverick (57.7 t/s).