Home Model series Claude Sonnet Claude Sonnet 4.6 Claude Sonnet 4.6 · MedCalc-Bench · Verified dataset · Scores and configurations Claude Sonnet 4.6 · MedCalc-Bench · Verified dataset · Scores and configurations Claude Sonnet 4.6 record for MedCalc-Bench · Verified dataset. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Sonnet 4.6 · MedCalc-Bench scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 86.24% Reported 86.24% · Unit % Published Unconfirmed
Adaptive thinking, max effort Settings Adaptive thinking enabled; max effort; default temperature and top_p unless an evaluation specifies otherwise. Unknowns Context window is evaluation-dependent; Table 2.1.A states it does not exceed 1M tokens. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol MedCalc-Bench Verified dataset; five-run average; multi-turn agentic loop with Python REPL. Conditions Adaptive thinking and max effort; instructed to write and execute Python code for calculations. View this score in rankings
Benchmark versions and metrics Aliases MedCalc-Bench Verified
Accuracy · % · Higher is better