Mistral Medium 3.5 is the best vision-capable Mistral model, pairing 29.9 intelligence with image and document understanding. Mistral Medium 3.1 (14.7) and Mistral Medium 3 (12.5) round out the top three.
Multimodal large language models that accept image input, ranked by intelligence. The best vision language models (VLMs) for understanding images, documents and charts.
Mistral Medium 3.5 is the best vision-capable Mistral model, pairing 29.9 intelligence with image and document understanding. Mistral Medium 3.1 (14.7) and Mistral Medium 3 (12.5) round out the top three.
Mistral Medium 3.1 (14.7) is the closest alternative on this metric, followed by Mistral Medium 3 (12.5). See the full ranking above for the tradeoffs.
modelgrep tracks 19 Mistral models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Mistral Medium 3.5. 10 of them qualify for this ranking.