Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51.16EM
10
Jun 26, 2026
24.18EM
10
Jun 26, 2026
29.34EM
10
Jun 26, 2026
30Accuracy
10
Jun 26, 2026
22.7ROUGE-L
10
Jun 18, 2026
25Exact Match (EM)
10
Jun 15, 2026
1.51Empirical Generalization Error G(W)
10
Jun 15, 2026
4.37F1
10
Jun 12, 2026
1.4F1 Score
10
Jun 12, 2026
72.93Accuracy
10
Jun 11, 2026
40.28F1 Score
10
Jun 11, 2026
0.47NLL
10
Jun 11, 2026
54.6TTFT (ms)
10
Jun 9, 2026
129Throughput (tokens/s)
10
Jun 9, 2026
84.68Accuracy
10
Jun 8, 2026
82.2F1 Score
10
Jun 5, 2026
48.9F1 Score
10
Jun 5, 2026
82.7Task Success
10
Jun 5, 2026
96.2Accuracy
10
Jun 4, 2026
98Accuracy
10
Jun 4, 2026
89Accuracy
10
Jun 4, 2026
95.22Accuracy
10
Jun 2, 2026
94.82Accuracy
10
Jun 2, 2026
96.81Correlation Score
10
May 27, 2026
83.59Accuracy
10
May 26, 2026