Claude Opus 5 (Thinking): benchmark results

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

Aggregate Rating 1942 ± 35, rank #19 of 2170 rated models, from 15 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ProfBench66.2Overall Rubric Score (%)100
Shade Computer Use Prompt Injection - Attack Success Rate (Sonnet 5 & Opus 5 System Cards)0.54Attack Success Rate (%)100
Shade Computer Use Prompt Injection - Attack Success Rate with Probes (Sonnet 5 & Opus 5 System Cards)0.25Attack Success Rate (%)100
Sonar LLM Leaderboard - Java - Pass Rate88.6Passing tests (%)100
Sonar LLM Leaderboard - Java - Bug Density0.59Bugs per 1,000 lines of code (lower is better)89.7
Anthropic Browser Use Prompt Injection - Attack Success Rate (Sonnet 5 & Opus 5 System Cards)3.7Attack Success Rate (%)75
Shade Coding Prompt Injection - Attack Success Rate with Probes (Sonnet 5 & Opus 5 System Cards)0.18Attack Success Rate (%)75
OpenTumorBoard - Board Simulation2.53Conclusion alignment (1-5) of a simulated multidisciplinary 73.1
PSF-Med - Frontier Hardest 500 - MIMIC-CXR7.88Paraphrase Flip Rate (%)60
Sonar LLM Leaderboard - Java - Vulnerability Density0.25Vulnerabilities per 1,000 lines of code (lower is better)57.5
Shade Coding Prompt Injection - Attack Success Rate (Sonnet 5 & Opus 5 System Cards)0.56Attack Success Rate (%)50
PSF-Med - Frontier Hardest 5009.53Paraphrase Flip Rate (%)40

Interactive version: theaggregate.ai/model?slug=claude-opus-5-thinking · How It Works · Data refreshed daily, snapshot 2026-11-05.