Claude Opus 4.6 (Adaptive Reasoning, Max Effort) — benchmark results
Claude Opus 4.6 evaluated in adaptive-reasoning mode at max effort. Provider: Anthropic. Released 2026-02-05. Access: API.
Unified ELO 1878 ± 26, rank #82 of 1776 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Global-MMLU-Lite - Chinese | 93.58 | Accuracy (%) | 100 |
| AA Global-MMLU-Lite - English | 95.17 | Accuracy (%) | 100 |
| AA Global-MMLU-Lite - Korean | 93 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - R | 74 | Accuracy (%) | 99.6 |
| AA Global-MMLU-Lite - Bengali | 92.08 | Accuracy (%) | 99.2 |
| AA Global-MMLU-Lite - German | 93.42 | Accuracy (%) | 99.2 |
| AA Global-MMLU-Lite - Hindi | 91.92 | Accuracy (%) | 99.1 |
| AA Global-MMLU-Lite - Portuguese | 93.92 | Accuracy (%) | 99.1 |
| UGI - Writing | 70.7 | Writing Score | 99.1 |
| AA Global-MMLU-Lite - Arabic | 92.25 | Accuracy (%) | 98.3 |
| AA Global-MMLU-Lite - Italian | 93.83 | Accuracy (%) | 98.3 |
| AA Global-MMLU-Lite - Japanese | 93.08 | Accuracy (%) | 98.3 |
Interactive version: theaggregate.ai/model?slug=claude-opus-4-6-adaptive-reasoning-max-effort · How the rankings work · Data refreshed daily, snapshot 2026-07-22.