Claude Sonnet 5.5 (High): benchmark results
Provider: Anthropic. Released 2026-09-28. Access: API.
Aggregate Rating 1883 ± 13, rank #58 of 2245 rated models, from 90 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WebDev Arena (HTML) | 1709 | Arena Score | 97.1 |
| o11y-bench - Pass^3 | 89.06 | Tasks passed on all three attempts, Pass^3 (%) | 97.1 |
| Chatbot Arena (Code) | 1715 | Elo | 96.5 |
| SelfBench - getsentry/sentry | 82.05 | Task success (%) on 78 tasks rebuilt from the repository's m | 96.4 |
| WebDev Arena (Frontend) | 1745 | Arena Score | 96.4 |
| WebDev Arena (Gaming) | 1833 | Arena Score | 96.4 |
| WebDev Arena (Reference-Based Design) | 1776 | Arena Score | 96.4 |
| WebDev Arena (Simulations) | 1813 | Arena Score | 96.4 |
| o11y-bench - Pass@3 | 100 | Tasks passed on at least one of three attempts, Pass@3 (%) | 96.4 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 65.93 | Chance-Corrected Score (0-100) | 96.2 |
| WebDev Arena | 1698.82 | Arena Score | 96.2 |
| WebDev Arena (Content Creation Tools) | 1668 | Arena Score | 96.2 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-5-high · How It Works · Data refreshed daily, snapshot 2026-11-16.