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

Multiple Choice Classification on When2Call

78.63Accuracy

Task Calibration

48.688456.461764.23572.0083May 11, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
78.63
2026.05
74.8
2026.05
74.59
2026.05
74.49
2026.05
74.39
2026.05
74.38
2026.05
74.19
2026.05
74.1
2026.05
73
2026.05
72.1
2026.05
71.3
2026.05
70.4
2026.05
69.8
2026.05
69.17
2026.05
68.87
2026.05
68.57
2026.05
67.67
2026.05
67.47
2026.05
60.63
2026.05
51.14
2026.05
50.81
2026.05
50.49
2026.05
50.49
2026.05
49.84