Anthropic
Claude Opus 4.7 benchmark results
15 results on 10 benchmarks from 3 sources.
Also listed as: claude-opus-4-7-high · claude-opus-4-7 · claude-opus-4-7_max · Claude Opus 4.7 (max) · claude-opus-4-7_xhigh · Claude Opus 4.7 (xhigh) · claude-opus-4-7_unknown · Claude Opus 4.7 (unknown)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1501 | 5 | Overall, style control on; 65192 votes; 95% CI 1497–1505“claude-opus-4-7-high” | Official leaderboard | Oct 8, 2026 |
| LMArena Text | 1494 | 10 | Overall, style control on; 66315 votes; 95% CI 1490–1498“claude-opus-4-7” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1558 | 36 | Overall; 17956 votes; 95% CI 1552–1563“claude-opus-4-7-high” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1555 | 38 | Overall; 18297 votes; 95% CI 1550–1561“claude-opus-4-7” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1298 | 4 | Overall, style control on; 23169 votes; 95% CI 1292–1305“claude-opus-4-7” | Official leaderboard | Oct 2, 2026 |
| LMArena Vision | 1298 | 5 | Overall, style control on; 22755 votes; 95% CI 1291–1304“claude-opus-4-7-high” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 90.2% | 40 | Epoch AI run, accuracy; effort: xhigh | Independent run | Apr 17, 2026 |
| GPQA Diamond | 86.4% | 74 | Epoch AI run, accuracy; effort: max | Independent run | Aug 6, 2026 |
| SWE-bench Verified | 83.5% | 1 | Epoch AI run (Epoch scaffold); effort: max | Independent run | Apr 20, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 97.8% | 30 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh | Independent run | Apr 17, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 86.7% | 84 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: max | Independent run | Aug 6, 2026 |
| Humanity's Last Exam | 36.2% | 10 | Compiled by Epoch AI; effort: unknown | Third-party compilation via Epoch AI | Apr 16, 2026 |
| OSWorld 2.0 | 18.2% | 8 | Binary accuracy; 500 steps; reasoning: max; effort: max | Official leaderboard via Epoch AI | Apr 16, 2026 |
| τ²-bench | 40.2% | 7 | banking_knowledge domain, pass^1; effort: max; submitted by Sierra; v1.0.1 | Official leaderboard | Jul 23, 2026 |
| Terminal-Bench 2.0 | 80.2% | 6 | Terminal-Bench 2.0; agent: WOZCODE; effort: unknown | Official leaderboard via Epoch AI | Apr 16, 2026 |
FAQ
Where do these Claude Opus 4.7 scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.