Rankings / Mistral AI
Mistral Large 2512
release date unknown
BenchAtlas Index
as of 2026-07-14
base configuration
rank #255
8 families · 3 categories · medium
Benchmark evidence
9 results
knowledge science
| GPQA Diamond implementation=vals-ai | 68.4 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | 79.8 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | 66.2 % | independent | Vals AI |
professional
| CaseLaw | 61.4 % | independent | Vals AI | |
| CorpFin | 61.0 % | independent | Vals AI | |
| LegalBench | 79.1 % | independent | Vals AI | |
| MedQA | 82.2 % | independent | Vals AI | |
| TaxEval | 73.1 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 42.9 % | independent | Vals AI |