Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.84Accuracy
45
Apr 21, 2026
87.35Accuracy
45
Jun 12, 2026
75.4Robust Accuracy
45
Feb 26, 2026
68Robust Accuracy
45
Feb 26, 2026
89.1Answer Accuracy
45
Feb 26, 2026
67.13Single Hop F1
45
Apr 21, 2026
87.5F1 Score
45
May 21, 2026
89GPT Judge Accuracy
45
Feb 26, 2026
87.08Accuracy
45
May 7, 2026
84.2Answer F1
45
Feb 26, 2026
80.2Accuracy
44
May 20, 2026
53.8Accuracy
44
May 20, 2026
0.423PRR
44
Apr 29, 2026
84.39PIQA Accuracy
44
Jun 11, 2026
93.01Accuracy (After Attack)
44
Feb 26, 2026
80ASR Accuracy
43
Jun 23, 2026
95.1Accuracy
43
Jun 19, 2026
68.25MC2
43
May 15, 2026
79Accuracy
43
Feb 26, 2026
69.4Accuracy
43
Feb 26, 2026
81Answer F1
43
May 19, 2026
59.33Accuracy (EM)
42
Jun 23, 2026
55.6EM Accuracy
42
Jun 23, 2026
93.6Accuracy
42
Jun 12, 2026
62Accuracy
42
Jun 11, 2026