Compare / Gemini 3.6 Flash vs Kimi K2.5
Gemini 3.6 Flash 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 3.6 Flash | Kimi K2.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,453 | 1,436 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,470 | 1,445 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,472 | 1,441 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,469 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,500 | 1,483 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,473 | 1,439 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,482 | 1,450 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,428 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 69.2 | 46.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 34.0 | 23.5 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.8% | 87.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 40.8% | 30.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 78.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 77.5% | 45.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 29.9% | 14.2% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 66.2% | 34.3% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 9.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 69.8 | 62.4 |
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.