Mistral AI rolled out a major update to Codestral 2501, expanding native context length to 256K tokens. The model achieves over 98% accuracy on 200k Fill-in-the-Middle (FIM) benchmarks, with broad multilingual fluency spanning 80+ mainstream and emerging languages including Rust, Go, Python, Solidity, and Zig.

Key Takeaways

  • βœ“Context window expanded to 256K tokens for repo-scale file comprehension.
  • βœ“Achieves 98%+ FIM accuracy across long 200k spans with strict syntax adherence.
  • βœ“Available immediately via La Plateforme API and the Mistral Vibe CLI.
ADSponsored