Dialog Response Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.82Noun Precision
4
Feb 27, 2026
2.92Informativeness
4
Feb 26, 2026
19.7BLEU
3
Feb 26, 2026
17.21BLEU
3
Feb 26, 2026
20.69BLEU
3
Feb 26, 2026
32.95BLEU
3
Feb 26, 2026
38.25BLEU
3
Feb 26, 2026
32.73BLEU
3
Feb 26, 2026
38.08BLEU
3
Feb 26, 2026
—
—Noun Precision
0
Feb 26, 2026