Claude Sonnet 4.6: benchmark results

Sonnet-tier Claude with adaptive thinking and context compaction, which summarizes older conversation to keep longer tasks going. Supports computer use and code execution. Provider: Anthropic. Released 2026-02-17. Access: API.

Aggregate Rating 1755 ± 2, rank #162 of 10318 rated models, from 3831 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AEC-Bench (Nomic Tools) - Submittal Review23.1Mean reward (0-100) from the task verifier on the 36 submitt100
AEC-Bench - Detail Title Accuracy86.7Mean reward (0-100) from the task verifier on the 15 detail-100
AEC-Bench - Note Callout Accuracy42.9Mean reward (0-100) from the task verifier on the 14 note-ca100
AI World Cup 2026 - Group-Stage Outcome Accuracy63.89Group-stage outcome accuracy (%; share of the 72 group-stage100
AIMultiple - TweetEval Hate82Macro-F1 (%)100
AM-Bench0.2Misaligned responses with both a threat to the agent and an 100
AM-Bench - Opportunity Only0.4Misaligned responses with an opportunity to misbehave and th100
AM-Bench - Threat Only0.4Misaligned responses with a threat to the agent and the oppo100
Adversarial Humanities Benchmark9.2Attack success rate (%; share of humanities-style rewritten 100
Adversarial Humanities Benchmark - Child Sexual Exploitation0Attack success rate (%; share of humanities-style rewritten 100
Adversarial Humanities Benchmark - Hate15.9Attack success rate (%; share of humanities-style rewritten 100
Adversarial Humanities Benchmark - Non-Violent Crimes8.7Attack success rate (%; share of humanities-style rewritten 100

Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-6 · How It Works · Data refreshed daily, snapshot 2026-11-14.