Compare / Claude Opus 4.5 vs gemini-3-pro
Claude Opus 4.5 vs gemini-3-pro
21 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.5 | gemini-3-pro |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,465 | 1,451 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,187 | 1,201 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,459 | 1,481 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,472 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,469 | 1,484 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,503 | 1,498 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,483 | 1,473 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,474 | 1,485 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,467 | 1,481 |
| OpenHands Indexreported | Average% resolved | 60.6% | 49.0% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 41.2% | 36.8% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 37.5% | 25.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 69.1% | 44.2% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 76.6% | 70.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 78.5% | 68.6% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 70.0% | 66.0% |
| tau2-benchreported | Task success (pass^1)% of tasks | 84.0% | 80.5% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 51.8% | 47.4% |
| tau2-benchreported | Task success (pass^1)% of tasks | 79.6% | 75.9% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 78.1% | 74.6% |
| tau2-benchreported | Task success (pass^1)% of tasks | 92.3% | 91.0% |
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.