Claude Opus 5 (Max) — benchmark results
Provider: Anthropic. Access: API.
Unified ELO 2181 ± 56, rank #5 of 1841 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutomationBench | 26.2 | Pass Rate (%) | 100 |
| Vals AI ProofBench | 78 | Accuracy (%) | 99.5 |
| ARC-AGI-2 | 90.42 | Accuracy (%) | 99.4 |
| ARC-AGI-1 | 97.5 | Accuracy (%) | 98.8 |
| Epoch AI - Scicode | 55.67 | Score | 97.6 |
| OTIS Mock AIME 2024-25 | 98.89 | Accuracy (%) | 96.2 |
| VoxelBench | 2127 | Rating | 95.8 |
| Epoch AI - Critpt | 29.14 | Score | 94.4 |
| Epoch AI - Apex Agents | 43.5 | Score | 93.9 |
| ClockBench | 60.7 | Accuracy (%) | 90.3 |
| FrontierMath - Tiers 1-3 (v2) | 85.61 | Accuracy (%, 285 private v2 problems) | 89.5 |
| Epoch AI - Cursorbench | 70 | Score | 89.3 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-max · How It Works · Data refreshed daily, snapshot 2026-07-25.