Report Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
41.4F1 Score
26
Jun 1, 2026
67.67Wtd Score
24
Jun 4, 2026
48.27Overall Score
20
Jun 19, 2026
54.9Factual Consistency (FC)
20
May 12, 2026
85.71Factual Consistency (FC)
20
May 12, 2026
15.6BLEU-4
20
Feb 26, 2026
49.5Comprehensiveness
16
Feb 26, 2026
21.6BLEU-4
16
Feb 26, 2026
55.6BLEU-1
15
Mar 25, 2026
78.8ScoreGPT
14
Apr 8, 2026
76.55ScoreGPT
14
Apr 8, 2026
4.6Accuracy
14
Mar 10, 2026
61.5Precision
14
Feb 27, 2026
1.242AC Score
13
May 26, 2026
35.06METEOR
12
Mar 4, 2026
43.1BLEU-1
12
Mar 4, 2026
42.6ROUGE-L
11
Jun 26, 2026
59.3CIDEr
11
Apr 9, 2026
50.2BLEU-1
11
Mar 18, 2026
70.4Clarity
10
Jun 19, 2026
33.1ROUGE-L
10
Feb 27, 2026
50.5F-D Score
9
Jul 8, 2026
0.144METEOR
9
Jun 4, 2026
66.7BLEU-1
9
Mar 25, 2026
38.68ROUGE-1
8
Jun 16, 2026