Compare / Gemini 3.1 Pro Preview vs Kimi K2.5
Gemini 3.1 Pro Preview vs Kimi K2.5
19 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.1 Pro Preview | Kimi K2.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,459 | 1,436 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,445 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,477 | 1,441 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,480 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,509 | 1,483 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,479 | 1,439 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,487 | 1,450 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,480 | 1,428 |
| OpenHands Indexreported | Average% resolved | 60.6% | 49.2% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 44.1% | 32.8% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 25.0% | 18.8% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 81.8% | 63.6% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 76.8% | 68.8% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 75.1% | 61.9% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 19.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 72.2 | 62.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.4% | 92.2% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 10.4% | 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.