Anthropic
Claude Opus 5.5 benchmark results
7 results on 5 benchmarks from 3 sources.
Also listed as: claude-opus-5.5-high · claude-opus-5-5_max · Claude Opus 5.5 (max) · Claude Opus 5.5 (High) · Claude Opus 5.5 (XHigh) · Claude Opus 5.5 (Max)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1507 | 2 | Overall, style control on; 6272 votes; 95% CI 1499–1515“claude-opus-5.5-high” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 90.6% | 36 | Epoch AI run, accuracy; effort: max | Independent run | Sep 22, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 100.0% | 1 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: max | Independent run | Sep 22, 2026 |
| ARC-AGI-1 | 98.5% | 5 | Semi-private set; $0.16/task; CoT“Claude Opus 5.5 (High)” | Official leaderboard | Oct 22, 2026 |
| ARC-AGI-2 | 93.3% | 4 | Semi-private set; $0.41/task; CoT“Claude Opus 5.5 (High)” | Official leaderboard | Oct 22, 2026 |
| ARC-AGI-2 | 92.5% | 6 | Semi-private set; $0.67/task; CoT“Claude Opus 5.5 (XHigh)” | Official leaderboard | Oct 22, 2026 |
| ARC-AGI-2 | 91.7% | 9 | Semi-private set; $1.85/task; CoT“Claude Opus 5.5 (Max)” | Official leaderboard | Oct 22, 2026 |
FAQ
Where do these Claude Opus 5.5 scores come from?
From Epoch AI Benchmarking Hub, ARC Prize leaderboard, and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.