Video Captioning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
195.6CIDEr
157
Apr 10, 2026
104.2CIDEr
142
Jun 1, 2026
189.4CIDEr
111
Feb 27, 2026
40.4METEOR
108
Mar 24, 2026
80.3CIDEr
107
Mar 24, 2026
12.31METEOR
104
Jun 1, 2026
221CIDEr
98
Feb 27, 2026
99.5CIDEr
76
Apr 10, 2026
84.2CIDEr
74
Jul 9, 2026
80.7CIDEr
72
Jun 11, 2026
80.3CIDEr
68
Mar 25, 2026
56.6F1 Score
43
Mar 31, 2026
190CIDEr
42
Feb 27, 2026
49.2Short Accuracy
35
May 28, 2026
39.32Token/s
24
Apr 8, 2026
36.49Throughput (Tokens/s)
24
Apr 8, 2026
94.5CIDEr
24
Feb 27, 2026
58.3F1 Score
22
Feb 26, 2026
66.1CIDEr
22
Feb 27, 2026
20.04METEOR
22
Feb 26, 2026
48.21Precision
21
Jul 7, 2026
84.9Appearance Description Precision
21
Feb 26, 2026
75.9CIDEr
20
Feb 26, 2026
76.53AR
17
Jul 7, 2026
46.9DVC F1
16
Feb 26, 2026