Compare / Llama 3.2 3B Instruct vs o4 Mini
Llama 3.2 3B Instruct vs o4 Mini
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 | Llama 3.2 3B Instruct | o4 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,146 | 1,379 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,145 | 1,337 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,179 | 1,408 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,146 | 1,369 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,167 | 1,391 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,143 | 1,354 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 52.1% | 87.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 6.2% | 35.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 4.0% | 41.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 21.9% | 53.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 87.5% | 81.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 82.7% | 81.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 58.3% | 70.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 1.0% | 75.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 31.0% | 19.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 10.4 | 46.9 |
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.