Compare / Claude Opus 4.7 vs GPT-5.4
Claude Opus 4.7 vs GPT-5.4
28 results from 6 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,494 | 1,470 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,212 | 1,195 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,485 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,508 | 1,482 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,488 | 1,443 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,535 | 1,515 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,503 | 1,471 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,502 | 1,475 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,465 |
| Microsoft STATE-Benchreported | Consistency (pass^5)% of tasks | 33.9% | 38.0% |
| Microsoft STATE-Benchreported | Customer support task success (pass@1)% of tasks | 51.0% | 57.6% |
| Microsoft STATE-Benchreported | Shopping assistant task success (pass@1)% of tasks | 54.0% | 53.6% |
| Microsoft STATE-Benchreported | Task success (pass@1)% of tasks | 53.4% | 55.7% |
| Microsoft STATE-Benchreported | Travel task success (pass@1)% of tasks | 55.0% | 55.9% |
| Microsoft STATE-Benchreported | User experiencescore from 1 to 5 | 3.46 | 3.49 |
| OpenHands Indexreported | Average% resolved | 69.7% | 64.3% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 48.5% | 36.8% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 56.2% | 56.2% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 81.2% | 82.4% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 81.6% | 75.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 80.8% | 70.4% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 24.7% | 21.6% |
| tau2-benchreported | Task success (pass^1)% of tasks | 40.2% | 39.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 1.0% | 30.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 61.4 | 68.8 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.0% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.0% | 7.0% |
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.