Claude Opus 5 (High): benchmark results

Provider: Anthropic. Released 2026-07-24. Access: API.

Unified ELO 1785 ± 1, rank #11 of 3078 rated models, from 108 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI Coding Daily (Claude Code) - React-TS Code Quality17.67React-TS Code Quality (max 20) points, LLM-judged rubric sco100
AI Coding Daily (Claude Code) - Total53.72Total points (max 60)100
Chatbot Arena (Document)1516Elo100
Chatbot Arena (Text - Mathematical)1535Arena Score100
DataBench88Score (%)100
DiG-bench - Games Beaten50Games beaten (of 70)100
FutureEval15.41Unified Forecasting Score100
LisanBench1Mean Path Length / Current Maximum100
OpenCompass Knowledge - Science97.5Score (%)100
OpenCompass Knowledge - Social Science94.6Score (%)100
OpenCompass LLM - Knowledge94.1Score (%)100
OpenCompass LLM - Math77.3Score (%)100

Interactive version: theaggregate.ai/model?slug=claude-opus-5-high · How It Works · Data refreshed daily, snapshot 2026-09-19.