Compare / GPT-5.2 vs gpt-5.3-chat-latest
GPT-5.2 vs gpt-5.3-chat-latest
10 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-5.2 | gpt-5.3-chat-latest |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,419 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,444 | 1,459 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,391 | 1,408 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,475 | 1,471 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,427 | 1,436 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,437 | 1,450 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,411 | 1,428 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 76.0% | 8.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.36 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 49.4 | 60.6 |
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.