Conversational Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.9Accuracy
35
Jun 9, 2026
70.85Exact Match (EM)
32
Feb 26, 2026
40.7PRR
22
Apr 29, 2026
34.2P@1 (All)
21
Feb 26, 2026
1Avg Rank (F1)
20
Feb 26, 2026
42.39F1 Score
20
Feb 26, 2026
20.73F1
20
Feb 26, 2026
50.83F1 Score
20
Feb 26, 2026
26F1 Score
20
Feb 26, 2026
88.8Overall F1
17
Feb 26, 2026
0.849Overall F1
14
Feb 27, 2026
50.7F1 Score
12
May 18, 2026
120EM (%)
12
Feb 26, 2026
20.9EM
12
Feb 26, 2026
86.5AIBC
12
Feb 26, 2026
57.14Average Score (w/o HDial)
12
Feb 26, 2026
1.253Overall Score
10
Jun 29, 2026
84.4Overlap F1
10
Feb 26, 2026
72.9Overlap F1
10
Feb 26, 2026
62.65F1 Score
10
Feb 26, 2026
53.51Accuracy
9
Apr 14, 2026
56.2Accuracy
9
Apr 14, 2026
58.05Accuracy
9
Apr 14, 2026
59.4Accuracy
9
Apr 14, 2026
0.397P@1
9
Feb 26, 2026