Dialogue Response Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
18.31BLEU
6
Feb 26, 2026
16.84Activity Precision
6
Feb 27, 2026
10.65BLEU-2
5
Jun 12, 2026
10.68BLEU-2
5
Jun 12, 2026
24.13BLEU-1
5
Jun 12, 2026
23.86BLEU-1
5
Jun 12, 2026
0.242BLEU-1
5
Jun 12, 2026
24.32BLEU-1
5
Jun 12, 2026
20.01BLEU-1
5
Jun 12, 2026
20.57BLEU-1
5
Jun 12, 2026
20.19BLEU-1
5
Jun 12, 2026
19.54BLEU-1
5
Jun 12, 2026
2.66Score at Month 9
5
Feb 27, 2026
3.61Metric Value (Month 9)
5
Feb 27, 2026
0.68Kappa
5
Feb 26, 2026
3.15GPT Score
4
Jun 15, 2026
2.61GPT Score
4
Jun 15, 2026
99Grammaticality
4
Feb 26, 2026
100BLEU
4
Feb 26, 2026
12.4PPL
4
Feb 26, 2026
40Precision
4
Feb 26, 2026
1.22Precision
4
Feb 26, 2026
4.02Coherence
3
Feb 26, 2026
4.09Coherence
3
Feb 26, 2026
89Accuracy
3
Feb 26, 2026