Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84.44F1 Score
2
Apr 28, 2026
79.81F1 Score
2
Apr 28, 2026
23EM
2
Apr 24, 2026
0.68Accuracy
2
Apr 23, 2026
54.82Accuracy
2
Apr 23, 2026
86Accuracy
2
Apr 23, 2026
48.6Accuracy
2
Apr 14, 2026
26Retrieval F1 (BoW)
2
Apr 14, 2026
168.73TPS
2
Apr 9, 2026
4PTR Adversarial Success Count
2
Apr 7, 2026
4PTR Advancement
2
Apr 7, 2026
0.37Log-likelihood Score
2
Apr 2, 2026
0.525Log-likelihood Score
2
Apr 2, 2026
0.515Log-likelihood Score
2
Apr 2, 2026
14.8PPE
2
Mar 23, 2026
16.2PPE
2
Mar 23, 2026
15.6PPE
2
Mar 23, 2026
0.113PPE
2
Mar 23, 2026
52.14Accuracy
2
Mar 18, 2026
45.4Accuracy
2
Mar 18, 2026
13Store Size
2
Mar 18, 2026
98.1Accuracy
2
Mar 18, 2026
57.2Normalized Log Accuracy
2
Mar 18, 2026
17ROUGE GM
2
Mar 18, 2026
52.2F1 Score
2
Mar 18, 2026