Compare / MiniMax M2.7 vs Kimi K2.6
MiniMax M2.7 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 M2.7 | Kimi K2.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,422 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,423 | 1,455 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,363 | 1,433 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,452 | 1,503 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,407 | 1,456 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,415 | 1,461 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,386 | 1,441 |
| OpenHands Indexreported | Average% resolved | 43.4% | 57.1% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 27.9% | 41.2% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 18.8% | 25.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 25.5% | 74.5% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 75.6% | 74.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 69.1% | 70.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 36.0% | 18.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.38 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 37.6 | 64.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.4% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.9% | 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.