AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Mistral Large

Mistral·

LLMsflagshipcloud + local

Overview

Flagship model with top-tier reasoning capabilities.

Capabilities and innovations

32k ContextMulti-lingualStrong reasoning32k Context WindowMulti-lingual ExcellenceFunction Calling

Benchmarks

BenchmarkScoreSource
GPQA Diamond42.5%unsourced
Humanity’s Last Exam (no tools)5.2%unsourced
SWE-bench Verified18.3%unsourced
MMLU81.2%unsourced
  • SWE-bench Pro: benchmark did not exist at release
  • MMLU-Pro: benchmark did not exist at release
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Links

More from Mistral

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.