Claude Opus 4 (20250514) (Thinking): benchmark results
Claude Opus 4 (20250514) evaluated with thinking enabled. Provider: Anthropic. Released 2025-05-22. Access: API.
Aggregate Rating 1686 ± 21, rank #404 of 2168 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Chat Mode - Fluency | 0.97 | Fluency Score | 100 |
| pfgen-bench - Chat Mode - Helpfulness | 0.9 | Helpfulness Score | 100 |
| pfgen-bench - Chat Mode - Score | 0.95 | pfgen Score (mean of three) | 100 |
| pfgen-bench - QA Mode - Fluency | 1 | Fluency Score | 100 |
| pfgen-bench - QA Mode - Helpfulness | 0.91 | Helpfulness Score | 100 |
| pfgen-bench - QA Mode - Score | 0.96 | pfgen Score (mean of three) | 100 |
| HELM Capabilities - MMLU-Pro | 87.5 | COT correct | 98.5 |
| Web-Bench | 25.6 | Pass@1 (%) | 97.9 |
| pfgen-bench - Chat Mode - Truthfulness | 0.96 | Truthfulness Score | 97.1 |
| pfgen-bench - QA Mode - Truthfulness | 0.97 | Truthfulness Score | 96.4 |
| UGI - Writing | 66.83 | Writing Score | 95.8 |
| UGI - Natural Intelligence | 56.7 | NatInt Score | 90.8 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-20250514-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.