Claude Opus 4.1 (Thinking): benchmark results
Claude Opus 4.1 evaluated with thinking enabled. Provider: Anthropic. Released 2025-08-05. Access: API.
Unified ELO 1626 ± 1, rank #333 of 1761 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchTable | 82.7 | Total Score (%) | 98.8 |
| Wolfram LLM Benchmarking Project | 64.7 | Correct Functionality (%) | 93.3 |
| Ducky Bench (Stabby Quack) | 1408 | ELO | 92.9 |
| AA Long Context Reasoning | 76 | Accuracy (%) | 79.7 |
| MathVision | 66 | Overall Accuracy (%) | 79.7 |
| AA Terminal-Bench Hard | 34.34 | Accuracy (%) | 79.4 |
| Artificial Analysis Intelligence Index | 26.89 | Intelligence Index | 76.3 |
| AA-LCR | 73.33 | Accuracy (self-reported) | 74.2 |
| Ducky Bench (Africa) | 1150 | ELO | 69.2 |
| AA GPQA Diamond | 80.9 | Accuracy (%) | 68.1 |
| AA IFBench | 55.44 | Accuracy (%) | 66.8 |
| AA TAU-2 Bench | 71.37 | Accuracy (%) | 63.8 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-1-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.