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

Video Reasoning on MMVU Multiple-choice (test)

75.4Accuracy

GPT-4o

43.57651.83860.168.362Nov 25, 2025Dec 19, 2025Jan 13, 2026Feb 7, 2026Mar 3, 2026Mar 28, 2026Apr 22, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.04
75.4
2025.11
75.4
2026.04
66.5
2026.04
66.1
2026.04
66.1
2026.04
65.8
2026.04
65.4
2026.04
65.4
2026.04
65.3
2025.11
65
2026.04
64.2
2025.11
64.2
2026.04
63.8
2026.04
63.8
2026.04
63.5
2026.04
61.6
2026.04
61.3
2026.04
60
2026.04
60
2026.04
59.2
2025.11
50.1
2026.04
49.2
2025.11
49.2
2026.04
46.9
2026.04
44.8