Claude Opus 5 — benchmark results
Provider: Anthropic. Access: API.
Unified ELO 2006 ± 27, rank #20 of 1841 rated models, from 53 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchLM | 85.9 | Overall Score | 100 |
| Benchmarks.bio - scBench-Long | 41.27 | Pass Rate (%) | 100 |
| DeepSWE | 73.6 | Pass@1 (%) | 100 |
| LLM Stats (GDPval-AA) | 1861 | ELO | 100 |
| Vals AI Code Migration | 57.47 | Accuracy (%) | 100 |
| Vals AI CorpFin v2 | 73.19 | Accuracy (%) | 100 |
| Vals AI Finance Agent v2 | 58.63 | Accuracy (%) | 100 |
| Vals AI Legal Research Bench | 55.29 | Accuracy (%) | 100 |
| Vals AI MMLU-Pro | 91.59 | Accuracy (%) | 100 |
| Vals AI MMMU | 89.88 | Accuracy (%) | 100 |
| Vals AI MedCode | 63.57 | Accuracy (%) | 100 |
| Vals AI MedScribe | 90.98 | Accuracy (%) | 100 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5 · How It Works · Data refreshed daily, snapshot 2026-07-25.