Compare / MiniMax M2.5 vs Kimi K2.6
MiniMax M2.5 vs Kimi K2.6
18 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | MiniMax M2.5 | Kimi K2.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,386 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,400 | 1,455 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,357 | 1,433 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,425 | 1,503 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,381 | 1,456 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,391 | 1,461 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,369 | 1,441 |
| OpenHands Indexreported | Average% resolved | 45.2% | 57.1% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 25.0% | 41.2% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 12.5% | 25.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 47.9% | 74.5% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 72.6% | 74.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 68.1% | 70.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 41.0% | 18.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.38 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 41.7 | 64.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.2% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 9.1% | 10.8% |
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.