Compare / Gemma 3 4B vs Kimi K2 0711
Gemma 3 4B vs Kimi K2 0711
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 | Gemma 3 4B | Kimi K2 0711 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,330 | 1,409 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,274 | 1,371 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,260 | 1,417 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,267 | 1,381 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,303 | 1,418 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,298 | 1,375 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 53.9% | 87.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 8.6% | 29.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 0.4% | 50.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 19.6% | 59.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 100.0% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 61.1% | 81.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 60.8% | 78.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 1.0% | 66.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 9.0% | 22.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.29 | 0.29 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 24.0 | 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.