Mistral Medium 3.5 is the best Mistral model for coding, with a 46.9 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. Mistral Medium 3.1 (20.5) is next.
AI models ranked by the Artificial Analysis Coding Index, measuring real-world software engineering ability across benchmarks like SWE-bench, SciCode and terminal tasks. The best AI coding models for code generation, debugging and agentic development.
Mistral Medium 3.5 is the best Mistral model for coding, with a 46.9 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. Mistral Medium 3.1 (20.5) is next.
Mistral Medium 3.1 (20.5) is the closest alternative on this metric. 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. 2 of them qualify for this ranking.