Compare / GPT-5.4 vs GPT-5.6 Luna
GPT-5.4 vs GPT-5.6 Luna
15 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-5.4 | GPT-5.6 Luna |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.04 | -0.05 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.01 | -0.04 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.02 | 0.02 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,470 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,485 | 1,461 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,443 | 1,412 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,515 | 1,491 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,471 | 1,446 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,475 | 1,454 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,465 | 1,435 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 30.0% | 15.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 68.8 | 53.7 |
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.