Temporal Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.663F1
85
Jun 16, 2026
77.7EM
25
Jun 16, 2026
44.09F1 Score
24
Feb 26, 2026
80.39EM
24
Feb 26, 2026
63.4R-1
20
Jun 16, 2026
85.4Exact Match (EM)
18
Apr 28, 2026
75.4P@1
18
Feb 26, 2026
49.8Exact Match (EM)
17
Apr 28, 2026
48EM
17
Apr 28, 2026
65.95Accuracy
13
Jun 5, 2026
84.75Accuracy
13
Jun 5, 2026
59.76F1
12
Mar 20, 2026
0.504R-1
12
Feb 26, 2026
58R-1 Score
12
Feb 26, 2026
0.491P@1
10
Feb 26, 2026
49.7Nugget R@20
9
May 1, 2026
85Set Accuracy
7
Feb 26, 2026
95.1Set Accuracy
7
Feb 26, 2026
44Score
5
Feb 26, 2026
50.3Accuracy
4
May 7, 2026
75.1Accuracy
4
May 7, 2026
100Accuracy
4
May 7, 2026
100Accuracy
4
May 7, 2026
32.2Accuracy
4
Apr 28, 2026
56.5P@1 (Overall)
4
Feb 26, 2026