Compare / gpt-5.3-chat-latest vs GPT-5.4
gpt-5.3-chat-latest vs GPT-5.4
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-5.3-chat-latest | GPT-5.4 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,419 | 1,485 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,459 | 1,482 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,408 | 1,443 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,471 | 1,515 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,436 | 1,471 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,450 | 1,475 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,428 | 1,465 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 8.0% | 30.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 60.6 | 68.8 |
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.