Compare / GPT-4.1 Nano vs GPT-5.2
GPT-4.1 Nano vs GPT-5.2
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 Nano | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,321 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,307 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,313 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,300 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,322 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,299 | 1,411 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 83.4% | 87.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 18.9% | 45.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 23.6% | 43.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 33.0% | 55.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 93.8% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 73.0% | 81.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 60.8% | 70.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 11.0% | 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.