Claude Opus 5: benchmark results
Provider: Anthropic. Released 2026-07-24. Access: API.
Unified ELO 1772 ± 1, rank #12 of 1553 rated models, from 226 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Pedagogy - Technology | 91.51 | Accuracy (%) | 100 |
| AI for Education SEND | 88.99 | Accuracy (%) | 100 |
| Agents' Last Exam | 31.6 | Pass Rate (%) | 100 |
| Android Bench | 91.8 | Score (%) | 100 |
| BenchBench-Protocol | 59.2 | Normalized Rubric Score (%) | 100 |
| Benchmarks.bio - BioSecBench-Function | 50.3 | Pass Rate (%) | 100 |
| Benchmarks.bio - BioSecBench-Surveillance | 60.8 | Pass Rate (%) | 100 |
| Benchmarks.bio - VariantBench | 49.72 | Pass Rate (%) | 100 |
| Benchmarks.bio - scBench-Long | 41.27 | Pass Rate (%) | 100 |
| BioMysteryBench Human-Solvable | 90.1 | Accuracy (self-reported) | 100 |
| BridgeBench Arena | 1009.8 | Confidence-weighted Elo | 100 |
| CHI-Bench | 54.7 | Overall Pass@1 (%) | 100 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5 · How It Works · Data refreshed daily, snapshot 2026-09-08.