Claude Sonnet 5.5 (Medium): benchmark results

Provider: Anthropic. Released 2026-09-28. Access: API.

Aggregate Rating 1781 ± 15, rank #196 of 2286 rated models, from 69 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
The Aggregate - Lichess Pairwise Strength (25 Pairs)88Accuracy (%)94.4
Conceptual Reasoning Index - Argument Evaluation (LMCA)65.45Chance-Corrected Score (0-100)94
Conceptual Reasoning Index - Consistency (ACCoRD)83.39Chance-Corrected Score (0-100)92.7
Conceptual Reasoning Index73.9Chance-Corrected Score (0-100)90.8
AI for Education SEND84.4Accuracy (%)86.7
AI for Education Pedagogy - Science91.26Accuracy (%)79.5
AI for Education Pedagogy - Primary91.55Accuracy (%)77.9
Maze-Bench58.47Mean Score77.1
AI for Education Pedagogy - Secondary86.95Accuracy (%)76.4
Conceptual Reasoning Index - Decision Theory (DTBench)89.78Chance-Corrected Score (0-100)75.3
AI for Education Pedagogy87.54Accuracy (%)74.6
o11y-bench - Pass@396.88Tasks passed on at least one of three attempts, Pass@3 (%)73.6

Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-5-medium · How It Works · Data refreshed daily, snapshot 2026-11-20.