Compare / Mistral Large 3 2512 vs GPT-6 Sol
Mistral Large 3 2512 vs GPT-6 Sol
14 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Mistral Large 3 2512 | GPT-6 Sol |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,434 | 1,424 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,409 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,373 | 1,451 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,428 | 1,507 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,400 | 1,447 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,413 | 1,457 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,388 | 1,440 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 9.30 | 47.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.2% | 47.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 36.0% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 36.6% | 57.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 43.9% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.8% | 100.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 14.5% | 6.5% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.