Claude Sonnet 5 (High): benchmark results
Claude Sonnet 5 evaluated at the high reasoning-effort setting. Provider: Anthropic. Released 2026-06-30. Access: API.
Aggregate Rating 1770 ± 9, rank #196 of 2168 rated models, from 230 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FDE-Bench - Containerization | 77.6 | Resolved rate (%; the 49 containerization-axis tasks (single | 100 |
| Horangi 4 - BFCL | 71.71 | Accuracy (%) | 100 |
| Horangi 4 - KorQuAD 1.0 | 89.1 | F1 (x100) | 98.1 |
| Horangi 4 - BigCodeBench (100-task subset) | 59 | Pass rate (%) | 95.2 |
| Horangi 4 - KoBBQ | 97 | Accuracy (%) | 94.7 |
| LisanBench | 0.37 | Mean Path Length / Current Maximum | 93.5 |
| Horangi 4 - KMMLU-Pro | 90 | Accuracy (%) | 93.3 |
| Chatbot Arena (Text - Expert) | 1511 | Arena Score | 93.1 |
| Horangi 4 - Ko-TruthfulQA | 95 | Accuracy (%) | 92.8 |
| Horangi 4 - Ko-MT-Bench | 89.25 | Judge rating (1-10, x10) | 92.3 |
| Chatbot Arena (Text - Coding) | 1519 | Arena Score | 91.3 |
| Chatbot Arena (Text - Instruction Following) | 1466 | Arena Score | 90.4 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-high · How It Works · Data refreshed daily, snapshot 2026-10-20.