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

Generation on MLLMU-Bench (Forget Set)

64.5Rouge Score

Vanilla

18.2230.23542.2554.265Feb 21, 2025May 8, 2025Jul 24, 2025Oct 8, 2025Dec 24, 2025Mar 10, 2026May 26, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2025.02
64.56.78
2025.02
59.46.4
2025.02
57.56.34
2026.05
57.1-
2026.05
56.7-
2026.05
56.7-
2026.05
56.5-
2026.05
56.1-
2026.05
55.7-
2026.05
55.5-
2026.05
55.2-
2026.05
53.2-
2026.05
52.6-
2026.05
51.8-
2026.05
51.7-
2026.05
51.5-
2025.02
50.33.48
2026.05
50.3-
2026.05
50.2-
2026.05
50.2-
2025.02
49.13.27
2025.02
48.53.38
2026.05
48.4-
2025.02
48.13.73
2026.05
47.9-
2026.05
45.4-
2026.05
44.7-
2026.05
42.1-
2026.05
31.6-
2026.05
31.4-
2026.05
30.8-
2026.05
27.4-
2026.05
25.3-
2026.05
25.2-
2026.05
25.1-
2026.05
22.1-
2026.05
20-