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

Video Reasoning on MVBench

64.7MVBench Score

Triage

40.98847.14453.359.456Oct 19, 2025Nov 5, 2025Nov 22, 2025Dec 9, 2025Dec 26, 2025Jan 12, 2026Jan 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.01
64.7-
2026.01
64.5-
2025.10
64.1-
2025.10
63.9-
2026.01
63.8-
2026.01
63.7-
2026.01
63-
2025.10
61-
2025.10
60.9-
2025.10
60.8-
2025.10
60.7-
2025.10
60.6-
2025.10
60.4-
2026.01
60-
2026.01
59.2-
2026.01
58.9-
58.8-
2026.01
58.5-
2026.01
58.5-
2026.01
58.3-
2026.01
58.2-
2026.01
58.1-
2026.01
58-
2026.01
58-
56.7-
2026.01
56.1-
2026.01
55.9-
2026.01
55.8-
2026.01
55.7-
2026.01
55.7-
2026.01
55.7-
2026.01
55.5-
2026.01
55.3-
2026.01
55.1-
54.6-
2025.10
53.2-
2025.10
52.9-
2025.10
52.5-
2025.10
41.9-
2026.04
-68.27
2026.04
-67.82
2026.04
-65.73
2026.04
-70.86
2026.04
-67.88
2026.04
-67.71
2026.04
-69.16
2026.05
-67.1
2026.05
-65.5
2026.05
-69.6
2026.05
-69.5
2026.05
-71.15
-54.6
-51.1
-57.3
-51.7
2026.05
-59.6
2026.05
-62.1
2026.05
-51.1
2026.05
-41.9
2026.05
-43
2026.05
-54.85
2026.05
-51.2
2026.05
-46.6
2026.05
-54.6
2026.05
-64.6
2026.05
-61.1
2026.05
-53.9
2026.05
-62.4
-42.4
2026.05
-60.5
2026.05
-60.9
2026.05
-62.7
2026.05
-61.1