Claude Opus 4.1: benchmarks and ranking
Claude Opus 4.1 (Anthropic) — overall rank: #95 / 153, overall score: 35.4 (90% interval 26.7–45.2), leaderboards: 3. Released: 2025-08-05 · Price (in/out): $15 / $75
Rank on each leaderboard
| Leaderboard | Rank | Published value |
|---|---|---|
| Artificial Analysis | Not rated | — |
| LiveBench | Not rated | — |
| Epoch AI | #95 / 230 | 144.76 |
| ARC Prize (ARC-AGI) | Not rated | — |
| Scale AI SEAL | #26 / 44 | 11.52 |
| Vals AI | Not rated | — |
| Terminal-Bench | Not rated | — |
| EQ-Bench | Not rated | — |
| SimpleBench | #49 / 112 | 60 |
| BenchLM.ai | Not rated | — |
Domain scores
- Coding: 45.3
- Reasoning: 46.6
- Math: 43.9
- Knowledge: 59.1
- Writing: 65.1
- Instructions: 43.9
- Chat & EQ: 36.7
- Business: 72.7
- Japanese: 70.6