Compare / Mistral Large 3 2512 vs Grok 4.5
Mistral Large 3 2512 vs Grok 4.5
19 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 | Grok 4.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,434 | 1,465 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,409 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,373 | 1,452 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,428 | 1,488 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,400 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,413 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,388 | 1,459 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 20.1 | 72.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 9.30 | 38.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 68.0% | 93.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.2% | 42.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 36.0% | 79.3% |
| Artificial Analysisreported | SciCode% of problems | 36.6% | 55.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 12.0% | 81.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 10.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 5.8% | 42.1% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 15.0% | 21.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.38 | 0.32 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 41.6 | 60.0 |
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.