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

Correctness Prediction on Overall Combined Datasets

70.12Accuracy

IRT-NET

60.219262.789665.3667.9304Jan 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
70.12
2026.01
70.03
2026.01
69.57
2026.01
69.47
2026.01
69.33
2026.01
69.27
2026.01
69.07
2026.01
68.33
2026.01
68.32
2026.01
68.31
2026.01
68.12
2026.01
68.09
2026.01
67.9
2026.01
67.38
2026.01
67.33
2026.01
66.34
2026.01
66.14
2026.01
60.6