Compare / MiniMax M2.1 vs Kimi K2.5
MiniMax M2.1 vs Kimi K2.5
11 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | MiniMax M2.1 | Kimi K2.5 |
|---|---|---|---|
| OpenHands Indexreported | Average% resolved | 41.2% | 49.2% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 16.2% | 32.8% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 18.8% | 18.8% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 40.6% | 63.6% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 68.8% | 68.8% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 61.4% | 61.9% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 31.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 41.6 | 62.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.5% | 92.2% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 11.8% | 14.2% |
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.