Mistral Medium 3.5 is the best vision-capable Mistral model, pairing 39.2 intelligence with image and document understanding. Mistral Large 3 2512 (22.8) and Mistral Medium 3.1 (21.3) round out the top three.
Multimodal large language models that accept image input, ranked by intelligence. The best vision-capable AI models for understanding images, documents and charts.
Mistral Medium 3.5 is the best vision-capable Mistral model, pairing 39.2 intelligence with image and document understanding. Mistral Large 3 2512 (22.8) and Mistral Medium 3.1 (21.3) round out the top three.
Mistral Large 3 2512 (22.8) is the closest alternative on this metric, followed by Mistral Medium 3.1 (21.3). 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.