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

Question Answering on Molmo2-Moment (M2M) v1 (test)

79.4Accuracy

Oracle

27.81641.20854.667.992May 22, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.05
79.4
2026.05
77.9
2026.05
76.9
2026.05
68
2026.05
63.4
2026.05
63.1
2026.05
63
2026.05
62.7
2026.05
62.3
2026.05
62.3
2026.05
61.6
2026.05
61.6
2026.05
61.1
2026.05
60.8
2026.05
60.7
2026.05
60.3
2026.05
59.5
2026.05
59
2026.05
58.2
2026.05
58.2
2026.05
58.2
2026.05
57.6
2026.05
57.5
2026.05
57.5
2026.05
56.8
2026.05
55
2026.05
53.3
2026.05
52.8
2026.05
52.5
2026.05
52.2
2026.05
51.9
2026.05
51.9
2026.05
51.5
2026.05
45
2026.05
39.3
2026.05
35.9
2026.05
29.9
2026.05
29.8