Video Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3.11Avg CoT
20
Jun 5, 2026
62.75Accuracy
19
May 8, 2026
67.7Score
19
Apr 14, 2026
97.4Overall Accuracy
18
May 12, 2026
78.1Overall Score
17
Jun 2, 2026
84.6Accuracy
16
Mar 5, 2026
49.3Accuracy
16
Mar 4, 2026
51.6Accuracy
16
Mar 4, 2026
50.5Accuracy
16
Mar 4, 2026
66.2Accuracy
15
Apr 10, 2026
68.9Accuracy
15
Apr 10, 2026
68.2Average Score
14
Jun 2, 2026
71.43Causal Accuracy
13
May 28, 2026
39.4Average Score
13
May 27, 2026
48.8Score
13
Jul 7, 2026
81.15Binary QA Accuracy (ACH)
13
Feb 26, 2026
68.5Score
12
Jul 7, 2026
65.4Accuracy
12
Jun 19, 2026
52.3Accuracy
12
Apr 20, 2026
44.3VSI
12
Feb 26, 2026
54.1Average Score
11
Jun 2, 2026
34Precision
11
May 18, 2026
44.3Precision
11
May 18, 2026
82.1Precision
11
May 18, 2026
63.64Narrative Accuracy
10
Mar 4, 2026