Claude Opus 5.5 (Max): benchmark results
Provider: Anthropic. Access: API.
Unified ELO 1787 ± 1, rank #9 of 3363 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DataBench | 70.5 | Score (%) | 100 |
| LiveBench Olympiad | 93.25 | Score | 100 |
| LiveBench TypeScript | 63.33 | Score | 100 |
| Vals AI MedScribe | 91.43 | Accuracy (%) | 100 |
| Vals AI ProgramBench | 86.99 | Raw Pass Rate (%) | 100 |
| Vals AI RSI Index | 0.37 | Index Score (0-1) | 100 |
| LiveBench JavaScript | 81.82 | Score | 99.2 |
| LiveBench Code Generation | 91.55 | Score | 98.4 |
| LiveBench Integrals With Game | 100 | Score | 98.4 |
| LiveBench Code Completion | 86.96 | Score | 97.6 |
| Bug Hunt Bench - LMS | 23.5 | Planted Bugs Fixed (out of 60) | 97.5 |
| ARC-AGI-2 | 91.67 | Accuracy (%) | 96.6 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-5-max · How It Works · Data refreshed daily, snapshot 2026-09-23.