Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.4Accuracy
5
Feb 26, 2026
67.5EM
5
Feb 26, 2026
46.95EM
5
Feb 26, 2026
45.26Accuracy
4
Jul 7, 2026
55.32Accuracy
4
Jul 7, 2026
42AURC
4
Jul 7, 2026
0.54AURC
4
Jul 7, 2026
22.53Accuracy
4
Jul 3, 2026
6.17Average Response Latency (s)
4
Jul 2, 2026
6.2Average Latency (s)
4
Jul 2, 2026
5.98Average response latency (s)
4
Jul 2, 2026
60.4Exact Match
4
Jul 1, 2026
64Exact Match
4
Jul 1, 2026
94Accuracy
4
Jun 30, 2026
98.98Accuracy
4
Jun 30, 2026
98.28Accuracy
4
Jun 30, 2026
99.09Accuracy
4
Jun 30, 2026
56.4Accuracy
4
Jun 29, 2026
72.6Accuracy
4
Jun 18, 2026
87.7Accuracy
4
Jun 18, 2026
73Content Accuracy
4
Jun 17, 2026
55.7Accuracy
4
Jun 17, 2026
33.6Normalized Accuracy
4
Jun 16, 2026
48.57Answer Accuracy
4
Jun 11, 2026
64.2Accuracy
4
Jun 11, 2026