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

Hazard Knowledge Evaluation on WMDP

68.98Accuracy

CoA

22.564834.614946.66558.7151Mar 24, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
68.98
2026.03
68.16
2026.03
67.76
2026.03
67.48
2026.03
67.48
2026.03
65.17
2026.03
65.03
2026.03
61.77
2026.03
61.22
2026.03
60.41
2026.03
59.59
2026.03
51.84
2026.03
48
2026.03
42
2026.03
35.24
2026.03
29.39
2026.03
28
2026.03
24.35