Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.1Accuracy
12
Jul 1, 2026
42.1Exact Match (EM)
12
Jun 30, 2026
46.1EM
12
Jun 30, 2026
71.8EM
12
Jun 30, 2026
56.1EM
12
Jun 30, 2026
86.6Accuracy
12
Jun 29, 2026
28.2TruthfulQA Score
12
Jun 19, 2026
92EM
12
Jun 19, 2026
55EM
12
Jun 19, 2026
65.8F1 Score
12
Jun 18, 2026
78.7F1 Score
12
Jun 18, 2026
95.48Accuracy (Q)
12
Jun 16, 2026
83.89Q Score
12
Jun 16, 2026
0.874Accuracy
12
Jun 16, 2026
50Accuracy
12
Jun 11, 2026
73.9Accuracy
12
Jun 8, 2026
95.2Accuracy
12
Jun 5, 2026
99.99Accuracy
12
Jun 4, 2026
77.03Accuracy
12
Jun 4, 2026
77.32Accuracy
12
Jun 4, 2026
88.78Accuracy
12
Jun 4, 2026
63.31Performance Score
12
Jun 2, 2026
49.5Accuracy
12
Jun 2, 2026
91.2Accuracy
12
Jun 2, 2026
87.75Accuracy
12
May 26, 2026