Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Zero-shot Evaluation on Various Tasks Average (test)

79.95Average Accuracy

FP16

33.576445.615757.65569.6943Nov 27, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.11
79.95-
2025.11
77.05-
2025.11
76.3-
2025.11
76.14-
2025.11
76.06-
2025.11
75.68-
2025.11
75.09-
2025.11
73.47-
2025.11
73.23-
2025.11
72.97-
2025.11
72.55-
2025.11
71.5-
2025.11
71.33-
2025.11
70.93-
2025.11
70.27-
2025.11
69.87-
2025.11
69.39-
2025.11
69.08-
2025.11
68.96-
2025.11
68.91-
2025.11
68.7-
2025.11
68.56-
2025.11
67.18-
2025.11
66.98-
2025.11
66.39-
2025.11
66.25-
2025.11
66.23-
2025.11
65.79-
2025.11
65.76-
2025.11
65.66-
2025.11
65.37-
2025.11
65.01-
2025.11
64.98-
2025.11
63.52-
2025.11
61.34-
2025.11
61.34-
2025.11
57.73-
2025.11
35.36-
2025.03
-64.8
2025.03
-57.5
2025.03
-56.5
2025.03
-56.6
2025.03
-57.8
2025.03
-67.8
2025.03
-61.5
2025.03
-60.6
2025.03
-62
2025.03
-63.1
2025.03
-68.6
2025.03
-36.8
2025.03
-38.8
2025.03
-51.8
2025.03
-53.6
2025.03
-57.8
2025.03
-75.4
2025.03
-48.7
2025.03
-44.1
2025.03
-44.2
2025.03
-39.7
2025.03
-51.4