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

Correctness Prediction on SoQA

67.85Accuracy

KMEANS

53.529257.247160.96564.6829Jan 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
67.85
2026.01
67.74
2026.01
67.48
2026.01
67.47
2026.01
66.83
2026.01
66.01
2026.01
65.9
2026.01
65.51
2026.01
65.24
2026.01
65.08
2026.01
64.84
2026.01
64
2026.01
63.94
2026.01
62.67
2026.01
61.76
2026.01
61.63
2026.01
61.4
2026.01
54.08