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

Visual Reasoning on MM-Vet

82.7Score

UniDFlow

5.32425.41245.565.588Sep 30, 2024Dec 30, 2024Apr 1, 2025Jul 1, 2025Oct 1, 2025Dec 31, 2025Apr 2, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.02
82.7
2026.02
79.4
2026.02
76.2
2026.02
73
2026.02
72.5
2024.09
69.1
2026.02
67.2
2024.09
64
2026.02
62.8
2026.02
61.8
2024.09
57.4
2024.09
56.8
2024.09
52
2026.02
50
2024.09
48.7
2026.04
48.7
2024.09
46.2
2026.04
44.3
2024.09
43.9
2024.09
43.7
2024.09
43.7
2026.04
43.2
2024.09
42.2
2024.09
42.1
2024.09
41
2026.04
40.9
2026.02
40.7
2024.09
39.8
2024.09
39.7
2024.09
39.4
2024.09
38.2
2024.09
37.4
2024.09
34.8
2024.09
32
2026.02
27.7
2024.09
25.8
2024.09
23.8
2026.04
18.5
2026.04
11.1
2026.02
8.3