Claude Opus 5.5 (High): benchmark results

Provider: Anthropic. Released 2026-09-22. Access: API.

Unified ELO 1803 ± 1, rank #2 of 1935 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI Coding Daily (Claude Code) - Total57.83Total points (max 60)100
MathArena - ARXIV_FALSE June100Accuracy (%)100
MathArena Arxiv False95Accuracy (%)100
ARC-AGI-198.5Accuracy (%)98.9
ARC-AGI-293.33Accuracy (%)98.9
DataBench65Score (%)96.8
Next.js Agent Evals (Claude Code) - Success Rate97Evals passed, pass@4 (%)94.4
Bug Hunt Bench - LMS18.7Planted Bugs Fixed (out of 60)91
Bug Hunt Bench31.7Planted Bugs Fixed (out of 105)85.4
Next.js Agent Evals (Claude Code) - Success Rate with AGENTS.md97Evals passed with bundled Next.js docs in AGENTS.md, pass@4 83.3
AI Coding Daily (Claude Code) - React-TS Code Quality19.33React-TS Code Quality (max 20) points, LLM-judged rubric sco80
MathArena Arxiv81.67Accuracy (%)79.2

Interactive version: theaggregate.ai/model?slug=claude-opus-5-5-high · How It Works · Data refreshed daily, snapshot 2026-09-25.