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

Hallucination Evaluation on MOH

69.5HR^D

baseline

-0.49217.67935.8554.021Feb 11, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.02
69.567.9
2026.02
56.836.5
2026.02
52.268.6
2026.02
51.165.1
2026.02
50.753.2
2026.02
49.949
2026.02
46.235
2026.02
45.648.3
2026.02
45.328.2
2026.02
45.263.4
2026.02
43.817.5
2026.02
39.451.1
2026.02
38.338.8
2026.02
31.736.6
2026.02
28.118.8
2026.02
11.558
2026.02
920
2026.02
4.715.5
2026.02
4.159
2026.02
3.647
2026.02
2.217.4