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

Consistency Evaluation on Diagnostic (Avg. YouCook2, COIN, CrossTask) (test)

76.92State Accuracy

CAST

55.485661.050366.61572.1797Mar 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
76.9277.66
2026.03
75.4377.77
2026.03
68.3833.68
2026.03
67.272.28
2026.03
66.1869.11
2026.03
65.730.85
2026.03
58.4429.79
2026.03
56.3129.73