Compare / MiniMax M3 vs GPT-5.2
MiniMax M3 vs GPT-5.2
14 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | MiniMax M3 | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,433 | 1,425 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,434 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,450 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,406 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,471 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,435 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,440 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,422 | 1,411 |
| OpenHands Indexreported | Average% resolved | 57.2% | 58.8% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 36.8% | 30.9% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 25.0% | 50.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 66.7% | 65.5% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 76.4% | 74.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 81.1% | 73.2% |
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.