Conversational Response Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
33.2F1
15
Apr 28, 2026
31F1 Score
15
Apr 28, 2026
30.6F1 Score
15
Apr 28, 2026
0.112BLEU-4
13
Feb 26, 2026
19.2F1 Score
12
Apr 28, 2026
31.2F1 Score
11
Apr 28, 2026
26.3F1 Score
10
Feb 26, 2026
0.296F1 Score
10
Feb 26, 2026
0.947Dist-1
9
Feb 26, 2026
33.2F1 Score
9
Feb 26, 2026
17.8F1 Score
9
Feb 26, 2026
2.6Fluency
7
Feb 26, 2026
82Fluency
6
Feb 26, 2026
26.85BLEU
5
Feb 26, 2026
21.98Perplexity
4
Feb 26, 2026
45.43Perplexity
4
Feb 26, 2026
2.54Response Perplexity
2
May 18, 2026