Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84.3Accuracy
6
May 6, 2026
60.16Composite Accuracy
6
May 6, 2026
45.7Exact Match (EM)
6
May 4, 2026
81.6Score
6
Apr 24, 2026
56.1ARC Score
6
Apr 24, 2026
56.7Selection Accuracy
6
Apr 21, 2026
85.9Accuracy
6
Apr 21, 2026
51.5Accuracy
6
Apr 21, 2026
50Accuracy
6
Apr 21, 2026
40.16Time F1
6
Apr 16, 2026
0.162ANLS
6
Apr 15, 2026
56.34Accuracy
6
Apr 14, 2026
38.9MC1 Score
6
Apr 14, 2026
89.6F1 Score
6
Apr 14, 2026
21.6Overall Accuracy
6
Apr 13, 2026
21.6Accuracy
6
Apr 13, 2026
16.6Accuracy (%)
6
Apr 13, 2026
13.8Accuracy (%)
6
Apr 13, 2026
33.3Accuracy
6
Apr 13, 2026
22Accuracy
6
Apr 13, 2026
29.3Accuracy
6
Apr 13, 2026
86.3Throughput (Req/s)
6
Apr 10, 2026
38.26GPQA Score
6
Apr 9, 2026
46.3EM
6
Apr 9, 2026
16.6EM
6
Apr 9, 2026