Claude Opus 4.5 (20251101) (Thinking): benchmark results
Claude Opus 4.5 (20251101) evaluated with thinking enabled. Provider: Anthropic. Released 2025-11-24. Access: API.
Aggregate Rating 1731 ± 22, rank #279 of 2168 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI MGSM | 95.2 | Accuracy (%) | 100 |
| UGI - Writing | 70.34 | Writing Score | 98.3 |
| UGI - Natural Intelligence | 65.22 | NatInt Score | 94.4 |
| SEAL - MASK | 92.53 | Score | 93.9 |
| MedQA | 95.88 | Score (%) | 90.4 |
| Vals AI MedQA | 95.88 | Accuracy (%) | 90.4 |
| AIME | 95.42 | Score (%) | 88.4 |
| Vals AI AIME | 95.42 | Accuracy (%) | 88.4 |
| LegalBench | 84.6 | Score (%) | 83.6 |
| TaxEval v2 | 74.86 | Score (%) | 83.2 |
| MMLU Pro | 87.26 | Score (%) | 80.6 |
| SEAL - Humanity's Last Exam (Text Only) | 26.32 | Score | 78.9 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-5-20251101-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.