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

Correctness Prediction on MathQA

66.15Accuracy

KMEANS

60.242861.776463.3164.8436Jan 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
66.15
2026.01
66.09
2026.01
65.95
2026.01
65.85
2026.01
65.75
2026.01
65.74
2026.01
65.59
2026.01
65.5
2026.01
65.38
2026.01
65.25
2026.01
65.22
2026.01
65.22
2026.01
65.12
2026.01
65.09
2026.01
64.29
2026.01
64.09
2026.01
62.81
2026.01
60.47