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 1769 ± 2, rank #90 of 1656 rated models, from 3725 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AEC-Bench (Nomic Tools) - Submittal Review | 23.1 | Mean reward (0-100) from the task verifier on the 36 submitt | 100 |
| AEC-Bench - Detail Title Accuracy | 86.7 | Mean reward (0-100) from the task verifier on the 15 detail- | 100 |
| AEC-Bench - Note Callout Accuracy | 42.9 | Mean reward (0-100) from the task verifier on the 14 note-ca | 100 |
| AI World Cup 2026 - Group-Stage Outcome Accuracy | 63.89 | Group-stage outcome accuracy (%; share of the 72 group-stage | 100 |
| AIMultiple - TweetEval Hate | 82 | Macro-F1 (%) | 100 |
| AgentMeter - Task Quality | 0.63 | Task quality: mean evaluator reward (0-1; 30-task Core Subse | 100 |
| AgentSocialBench - Information Abstraction | 0.85 | Information Abstraction Score (0-1; 0, 0.5 or 1 per cross-bo | 100 |
| AgentSocialBench - Task Completion Quality | 0.87 | Task Completion Quality (0-1; five-level grade of the coordi | 100 |
| AgentTrap | 33 | Attack success (self-reported) | 100 |
| AgentViSS - Interaction Management | 71.32 | Mean of the interaction-regulation and interaction-outcome t | 100 |
| AgentViSS - Interaction Outcome (Direct Vision) | 88.8 | Interaction-outcome task score (achieving the role's visuall | 100 |
| AgentViSS - Interaction Outcome (Verbalized Vision) | 90.64 | Interaction-outcome task score (achieving the role's visuall | 100 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-6 · How It Works · Data refreshed daily, snapshot 2026-10-20.