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
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 42.5% | unsourced |
| Humanity’s Last Exam (no tools) | 5.2% | unsourced |
| SWE-bench Verified | 18.3% | unsourced |
| MMLU | 81.2% | 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.