Audio Captioning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
91.1CIDEr
222
Jun 5, 2026
50.9CIDEr
82
Jun 4, 2026
0.199SPICE
75
Jun 4, 2026
80.3CIDEr
66
May 26, 2026
19.7METEOR
43
Jun 4, 2026
0.602BLEU-1
12
Jun 5, 2026
52CIDEr
11
Apr 14, 2026
48.5SPIDEr
10
Feb 26, 2026
19.36SPIDEr
9
Feb 26, 2026
31.88SPIDEr
9
Feb 26, 2026
39CIDEr-D
8
Jul 7, 2026
46.01Captioning Score
8
Mar 30, 2026
23.33Captioning Score
8
Mar 30, 2026
18.5B@4
8
Feb 26, 2026
0.735Div2 Score
6
Jun 4, 2026
53.7BLEU-1
6
Feb 26, 2026
70.4CIDEr
6
Feb 26, 2026
0.447LA-CLAP
4
Feb 26, 2026
0.469SBERT Similarity
4
Mar 27, 2026
0.478SBERT Similarity
4
Feb 26, 2026
48.8CIDEr
4
Feb 26, 2026
64CIDEr
4
Feb 26, 2026
29.4Score
4
Feb 26, 2026
66.52FENSE Score
3
Mar 27, 2026
60.11FENSE Content Long Score
3
Mar 27, 2026