Claude Opus 4 (20250514) — benchmark results
May 14, 2025 Claude Opus 4 snapshot, tracked when sources report the dated API model. Provider: Anthropic. Released 2025-05-14. Access: API.
Unified ELO 1696 ± 13, rank #278 of 1776 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety BBQ | 99.3 | BBQ accuracy (%) | 100 |
| Web-Bench | 28 | Pass@1 (%) | 100 |
| RewardBench Factuality | 82.67 | Accuracy (%) | 98 |
| RewardBench Math | 74.91 | Score (%) | 96.9 |
| AraGen | 80.96 | 3C3H Score (%) | 95.5 |
| RewardBench Ties | 83.75 | Score (%) | 95.3 |
| HELM Capabilities - MMLU-Pro | 85.9 | COT correct | 95 |
| HELM Capabilities - IFEval | 91.77 | IFEval Strict Acc | 94 |
| WebApp1K Duo | 76.3 | Pass@1 (%) | 90.6 |
| SuperGPQA | 61.43 | Accuracy (%) | 89.7 |
| Vals AI MGSM | 93.78 | Accuracy (%) | 89.2 |
| HindiGen | 74.49 | 3C3H Score (%) | 88.2 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-20250514 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.