Claude Opus 4.1 (20250805): benchmark results
August 5, 2025 Claude Opus 4.1 snapshot, tracked when sources report the dated API model. Provider: Anthropic. Released 2025-08-05. Access: API.
Aggregate Rating 1736 ± 10, rank #132 of 1656 rated models, from 194 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - Ko-HellaSwag | 90 | Accuracy (%) | 99 |
| Horangi 4 - KoBBQ | 99 | Accuracy (%) | 99 |
| Vals AI MGSM | 94.44 | Accuracy (%) | 97.6 |
| ForecastBench Baseline - Scratchpad - Market | 61.6 | Market Brier Index (difficulty-adjusted, higher is better) | 97.1 |
| Horangi 4 - GLP - Logical Reasoning | 89.5 | Score (%) | 97.1 |
| Arabic Broad Leaderboard - Writing (incl Dialects) | 8 | Average Score (0-10) | 96.7 |
| Horangi 4 - KorQuAD 1.0 | 88.85 | F1 (x100) | 96.2 |
| WebApp1K Duo | 76.9 | Pass@1 (%) | 95.8 |
| ForecastBench Baseline - Zero-Shot - Overall | 60.8 | Overall Brier Index (difficulty-adjusted, higher is better) | 95.6 |
| SEAL - MASK | 94.2 | Score | 95.5 |
| UGI - Writing | 66.51 | Writing Score | 95.5 |
| Vals AI MATH 500 | 95.4 | Accuracy (%) | 94.3 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-1-20250805 · How It Works · Data refreshed daily, snapshot 2026-10-20.