Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) — benchmark results

Claude Sonnet 4.6 evaluated in adaptive-reasoning mode at max effort. Provider: Anthropic. Released 2026-02-17. Access: API.

Unified ELO 1868 ± 20, rank #89 of 1776 rated models, from 59 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Omniscience - Software Engineering (SWE) - HTML78Accuracy (%)96.2
AA Terminal-Bench Hard53.03Accuracy (%)96.2
AA Global-MMLU-Lite - Japanese92.58Accuracy (%)96.1
AA Global-MMLU-Lite - Portuguese92.5Accuracy (%)96
AA Omniscience - Software Engineering (SWE) - Rust80Accuracy (%)96
AA Omniscience - Software Engineering (SWE) - Swift80Accuracy (%)95.9
AA Global-MMLU-Lite - Bengali90.92Accuracy (%)95.8
Tau3 Banking30.52Success Rate (%)95.8
AA Global-MMLU-Lite - Italian92.92Accuracy (%)95.7
Artificial Analysis Intelligence Index47.21Intelligence Index95.6
UGI - Writing64.15Writing Score95.5
AA Omniscience - Software Engineering (SWE) - C83Accuracy (%)95.1

Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-6-adaptive-reasoning-max-effort · How the rankings work · Data refreshed daily, snapshot 2026-07-22.