Response Selection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.675MAP
94
Feb 26, 2026
0.927Recall@1 (R10)
81
Feb 26, 2026
0.886Recall@1 (Top 10)
58
Feb 26, 2026
91.1Recall@1 (Top 100)
27
Feb 26, 2026
90.3R@1/20
25
Feb 26, 2026
91.9MRR
20
Feb 26, 2026
68.5Accuracy (1/100)
17
Feb 27, 2026
83.66Accuracy
16
Feb 26, 2026
0.88Accuracy
16
Feb 26, 2026
78.07Accuracy
16
Feb 26, 2026
64.36Accuracy
16
Feb 26, 2026
75.03Accuracy
16
Feb 26, 2026
87.9R@20
16
Feb 26, 2026
82.79R@1
11
Feb 26, 2026
87.45R@1
11
Feb 26, 2026
181.8Perplexity@Top-1
11
Feb 26, 2026
194.8Perplexity@1
11
Feb 26, 2026
89.7R@2
10
Feb 26, 2026
89.14R@2
10
Feb 26, 2026
87.63Recall@2
10
Feb 26, 2026
94.9R2@1
8
Feb 26, 2026
71.8R@1 (R100)
7
Feb 26, 2026
84.3R@1 (K=100)
6
Feb 26, 2026
97.85R@1
3
Feb 26, 2026
86.9R@1 (R20 Context)
3
Feb 26, 2026