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

True-False Question Answering on Image Implication True-False 1.0 (test)

74Accuracy

MetaphorStar-32B

-2.9617.023756.98Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
74
2026.02
70
62
2026.02
62
58
2026.02
56
56
54
52
2026.02
50
2026.02
50
42
2026.02
42
2026.02
40
2026.02
38
38
36
2026.02
36
2026.02
36
36
2026.02
28
2026.02
28
2026.02
20
20
2026.02
0