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

Model Accuracy on Model Utility Evaluation Set

30.22Accuracy (ACC)

ChatBug

-1.16726.981415.1323.2786Apr 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
30.22
2026.04
27.92
2026.04
27.85
2026.04
22.65
2026.04
17.2
2026.04
13.04
2026.04
11.33
2026.04
9.1
2026.04
6.99
2026.04
6.62
2026.04
6.53
2026.04
3.72
2026.04
3.58
2026.04
3.28
2026.04
3.01
2026.04
2.75
2026.04
1.99
2026.04
1.71
2026.04
1.45
2026.04
1.41
2026.04
1.18
2026.04
1.01
2026.04
0.21
2026.04
0.04