Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Correlation with Human Judgment on NLV and ChartLLM (171 sampled examples)

0.73Pearson Correlation

MatPlotBench

0.44920.52210.5950.6679Jan 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
0.73
2026.01
0.71
2026.01
0.65
2026.01
0.46