Claude Opus 5.5 (Max): benchmark results
Provider: Anthropic. Released 2026-09-22. Access: API.
Aggregate Rating 1997 ± 6, rank #4 of 2178 rated models, from 320 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Agent Arena | 15.53 | Net Improvement (%) | 100 |
| Agent Arena - Confirmed Success | 17.29 | Confirmed Success (%) | 100 |
| Anthropic ECI - September 2026 Fit (Opus 5.5 System Card) | 169.36 | AECI Score | 100 |
| ArXivMath August 2026 No Tools (Anthropic Internal Harness) | 91.2 | Accuracy (%) | 100 |
| ArXivMath August 2026 Tools (Anthropic Internal Harness) | 96.9 | Accuracy (%) | 100 |
| Chatbot Arena (Code) | 1813 | Elo | 100 |
| Chatbot Arena (Image-to-WebDev) | 1749 | Arena Score | 100 |
| CursorBench 4.0 | 57.8 | Score (%) | 100 |
| DataBench | 70.5 | Score (%) | 100 |
| Elorian Glimpse Card - CharXiv-R | 93.4 | Accuracy (%) | 100 |
| Epoch AI - Dtbench | 98.93 | Score | 100 |
| Epoch AI - Furniture Assembly | 83.33 | Score | 100 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-5-max · How It Works · Data refreshed daily, snapshot 2026-11-07.