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

BenchmarkScoreMetricPercentile
WebDev Arena (HTML)1709Arena Score97.1
o11y-bench - Pass^389.06Tasks passed on all three attempts, Pass^3 (%)97.1
Chatbot Arena (Code)1715Elo96.5
SelfBench - getsentry/sentry82.05Task success (%) on 78 tasks rebuilt from the repository's m96.4
WebDev Arena (Frontend)1745Arena Score96.4
WebDev Arena (Gaming)1833Arena Score96.4
WebDev Arena (Reference-Based Design)1776Arena Score96.4
WebDev Arena (Simulations)1813Arena Score96.4
o11y-bench - Pass@3100Tasks passed on at least one of three attempts, Pass@3 (%)96.4
Conceptual Reasoning Index - Argument Evaluation (LMCA)65.93Chance-Corrected Score (0-100)96.2
WebDev Arena1698.82Arena Score96.2
WebDev Arena (Content Creation Tools)1668Arena Score96.2

Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-5-high · How It Works · Data refreshed daily, snapshot 2026-11-16.