Compare / GPT-4.1 Mini vs o3
GPT-4.1 Mini vs o3
15 results from 3 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 | o3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,379 | 1,426 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,349 | 1,383 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,384 | 1,449 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,373 | 1,403 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,383 | 1,432 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,361 | 1,396 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 81.7% | 86.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 26.9% | 51.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 34.1% | 62.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 50.5% | 63.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 87.5% | 93.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 84.6% | 81.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 74.8% | 73.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 57.0% | 77.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 12.7% | 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.