Compare / Gemini 3.7 Flash vs Kimi K2 0905
Gemini 3.7 Flash vs Kimi K2 0905
14 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.7 Flash | Kimi K2 0905 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,403 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,483 | 1,404 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,492 | 1,382 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,512 | 1,417 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,487 | 1,390 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,419 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,382 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 15.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 94.5% | 76.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.9% | 6.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.0% | 53.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 7.0% | 22.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.31 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 77.5 | 54.4 |
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.