Claude Opus 5.5: benchmark results
Anthropic's Claude Opus 5.5 (September 22, 2026), the first release in the Claude 5.5 family and the Opus-tier successor to Claude Opus 5. Provider: Anthropic. Released 2026-09-22. Access: API.
Aggregate Rating 1987 ± 4, rank #3 of 1640 rated models, from 1174 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Code2Video-AA (Dataset 0.3.0) | 1535.57 | Mean axis Elo (GPT-5.5 xhigh anchor=1000) | 100 |
| AA Coding Agent Index v2.0 | 61.65 | Coding Agent Index (0-100) | 100 |
| AA Coding Agent Index v2.0 - FrontierCode v1.1 | 55.97 | Mean Score (%) | 100 |
| AA FrontierCode 2.0 | 46.44 | Guardrail-gated Rubric Score (%) | 100 |
| AA GDP.pdf - Engineering - Criterion Pass Rate | 84.35 | Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - HR - Criterion Pass Rate | 90.16 | Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - Healthcare - Criterion Pass Rate | 93.1 | Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - STEM/Research - Criterion Pass Rate | 81.47 | Criterion Pass Rate (%) | 100 |
| AA GDPval | 1866.27 | ELO | 100 |
| AA Humanity's Last Exam | 61.35 | Accuracy (%) | 100 |
| AA SciCode | 66.9 | Accuracy (%) | 100 |
| AA-Briefcase - Analytical Quality Elo | 2133 | Elo | 100 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-5 · How It Works · Data refreshed daily, snapshot 2026-11-07.