Compare / GPT-4.1 Mini vs o4 Mini
GPT-4.1 Mini vs o4 Mini
14 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-4.1 Mini | o4 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,379 | 1,379 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,349 | 1,337 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,384 | 1,408 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,373 | 1,369 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,383 | 1,391 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,361 | 1,354 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 81.7% | 87.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 26.9% | 35.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 34.1% | 41.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 50.5% | 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 | 84.6% | 81.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 74.8% | 70.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 57.0% | 75.5% |
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.