Compare / Kimi K2 0711 vs GPT-5.2
Kimi K2 0711 vs GPT-5.2
17 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 0711 | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,409 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,371 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,417 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,381 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,418 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,375 | 1,411 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 87.3% | 87.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 29.0% | 45.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 50.6% | 43.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 59.1% | 55.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 75.0% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 81.6% | 81.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.7% | 70.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 66.5% | 75.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 22.0% | 76.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.29 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 52.5 | 49.4 |
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.