Compare / Gemini 3.8 Flash vs Kimi K2 0711
Gemini 3.8 Flash vs Kimi K2 0711
13 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 3.8 Flash | Kimi K2 0711 |
|---|---|---|---|
| BulletBenchmeasured by us | Web search% correct | 0.1% | 78.7% |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,409 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,529 | 1,417 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,488 | 1,381 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,492 | 1,418 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,486 | 1,375 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 40.9 | 12.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 95.3% | 76.6% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.8% | 7.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.0% | 53.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 13.0% | 22.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.29 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 78.5 | 52.5 |
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.