Compare / Kimi K2 0905 vs Kimi K2.6
Kimi K2 0905 vs Kimi K2.6
12 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Kimi K2 0905 | Kimi K2.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,403 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,404 | 1,455 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,382 | 1,433 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,417 | 1,503 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,390 | 1,456 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,419 | 1,461 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,382 | 1,441 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 22.0% | 18.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.31 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 54.4 | 64.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.6% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 17.9% | 10.8% |
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.