Compare / Claude Sonnet 4.5 vs GPT-4.1 Mini
Claude Sonnet 4.5 vs GPT-4.1 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 | Claude Sonnet 4.5 | GPT-4.1 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,461 | 1,379 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,454 | 1,349 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,498 | 1,384 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,464 | 1,373 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,457 | 1,383 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,454 | 1,361 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 95.0% | 81.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 65.0% | 26.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 61.4% | 34.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 73.2% | 50.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 68.8% | 87.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.7% | 84.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 81.1% | 74.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 81.0% | 57.0% |
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.