Conversational Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.681F1 Score
9
Feb 26, 2026
67.7F1 Score
9
Feb 26, 2026
44.5L Metric
8
Feb 26, 2026
60.3EM
8
Feb 26, 2026
66.1F1 Score
7
Feb 26, 2026
32.1P@1
7
Feb 26, 2026
72.4Easy Accuracy
7
Feb 26, 2026
70.76F1 (Comparative)
6
Feb 26, 2026
83.4Overall F1
6
Feb 26, 2026
32.1F1 Score
5
Jun 4, 2026
21.9Performance (%)
5
Feb 26, 2026
67.5Performance
5
Feb 26, 2026
53.7Performance
5
Feb 26, 2026
66.9Accuracy
5
Feb 26, 2026
33.9P@1
5
Feb 26, 2026
0.406P@1
5
Feb 26, 2026
43.41Exact Match Acc
4
Feb 26, 2026
1Relative Latency
4
Feb 26, 2026
37EM
3
Feb 26, 2026
69.09Average Score
3
Feb 26, 2026
1.06Accuracy
2
Feb 26, 2026
85F1 Score
2
Feb 26, 2026
44.3F1 Score
2
Feb 26, 2026