Home Model series Claude Sonnet Claude Sonnet 5 Claude Sonnet 5 · ChartMuseum · 1,162 test-split questions · Scores and configurations Claude Sonnet 5 · ChartMuseum · 1,162 test-split questions · Scores and configurations Claude Sonnet 5 record for ChartMuseum · 1,162 test-split questions. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Sonnet 5 · ChartMuseum scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 70.1% Reported 70.1% · Unit % Published Unconfirmed
Adaptive thinking, max effort, no tools Settings Adaptive thinking at max effort; no tools. Unknowns none recorded Tools Tools forbidden Reasoning budget max Framework not recorded Protocol ChartMuseum test split, 1,162 chart questions; five-run average. Conditions No tools; adaptive thinking and max effort; Sonnet 4.6 grader instead of GPT-4.1-mini. View this score in rankings Accuracy 86.7% Reported 86.7% · Unit % Published Unconfirmed
Adaptive thinking, max effort, tools enabled Settings Adaptive thinking at max effort; tools enabled as specified per benchmark. Unknowns none recorded Tools Tools allowed Reasoning budget max Framework not recorded Protocol ChartMuseum test split; five-run average. Conditions Python tools and image-cropping available; adaptive thinking and max effort; Sonnet 4.6 grader. View this score in rankings
Benchmark versions and metrics Aliases ChartMuseum
Accuracy · % · Higher is better