Claude Sonnet 4.6 (Max): benchmark results
Claude Sonnet 4.6 evaluated at the max reasoning-effort setting. Provider: Anthropic. Released 2026-02-17. Access: API.
Aggregate Rating 1755 ± 12, rank #223 of 2168 rated models, from 132 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI Finance Agent | 63.33 | Accuracy (%) | 98.2 |
| Vals AI TaxEval v2 | 77.11 | Accuracy (%) | 97.9 |
| AA Terminal-Bench Hard | 53.03 | Accuracy (%) | 96.2 |
| AA Global-MMLU-Lite - Japanese | 92.58 | Accuracy (%) | 95.9 |
| AA Global-MMLU-Lite - Portuguese | 92.5 | Accuracy (%) | 95.9 |
| AA Global-MMLU-Lite - Bengali | 90.92 | Accuracy (%) | 95.5 |
| AA Global-MMLU-Lite - Italian | 92.92 | Accuracy (%) | 95.5 |
| AA Global-MMLU-Lite - Korean | 91.08 | Accuracy (%) | 93.6 |
| AA Global-MMLU-Lite | 90.48 | Accuracy (%) | 91.8 |
| AA Global-MMLU-Lite - Arabic | 90.17 | Accuracy (%) | 91.8 |
| AA Global-MMLU-Lite - Burmese | 88.17 | Accuracy (%) | 91.8 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | 48 | Omniscience Index | 91.5 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-6-max · How It Works · Data refreshed daily, snapshot 2026-10-20.