Report Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
38.23ROUGE-1
8
Jun 16, 2026
37.35ROUGE-1
8
Jun 16, 2026
3.9Trajectory Coverage
8
May 15, 2026
4.9Trajectory Coverage
8
May 15, 2026
79.5BLEU-1
7
Jun 29, 2026
41BLEU-4
7
May 27, 2026
21.7GREEN
7
Apr 28, 2026
53.2CheXbert Macro F1 (14)
6
Apr 16, 2026
37.33ROUGE
6
Apr 6, 2026
33.69ROUGE
6
Apr 6, 2026
33.36ROUGE Score
6
Apr 6, 2026
35.03ROUGE
6
Apr 6, 2026
20.45LLM Score
6
Feb 27, 2026
50.8Nugget Recall
6
Feb 26, 2026
21.6BLEU-4
6
Feb 26, 2026
10.19F1 (b)
5
Jul 8, 2026
38.94ROUGE-1
5
Jun 16, 2026
30.14ROUGE-L
5
May 20, 2026
18.39ROUGE-L
5
May 20, 2026
27.2Radgraph F1
5
Apr 8, 2026
42.7Precision
4
Jun 25, 2026
33.4BLEU-2
4
Jun 25, 2026
0.235BLEU-4
4
May 8, 2026
48.5BLEU-1
4
Apr 9, 2026
33.13API Score
4
Feb 26, 2026