Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.273Spearman's rho
12
May 13, 2026
0.718Spearman's rho
12
May 13, 2026
60.8Normalized Accuracy (zero-shot)
12
May 12, 2026
67.8F1 Score
12
May 12, 2026
92Accuracy
12
May 12, 2026
93.2Accuracy
12
May 12, 2026
1,597NC Score
12
May 12, 2026
61.4QA Accuracy
12
May 6, 2026
80.5Overall Accuracy
12
Apr 30, 2026
85.8Overall Accuracy
12
Apr 30, 2026
32.59Accuracy
12
Apr 23, 2026
40.8F1 Score
12
Apr 20, 2026
25.52Accuracy
12
Apr 14, 2026
90.42F1 (Pos)
12
Apr 14, 2026
90.42F1 (Positional)
12
Apr 14, 2026
89.82F1 (Positive)
12
Apr 14, 2026
66.87F1 (Pos)
12
Apr 14, 2026
37.1EM
12
Apr 14, 2026
66.3CEM (%)
12
Apr 14, 2026
76.3CEM
12
Apr 14, 2026
71.2CEM
12
Apr 14, 2026
70.34Accuracy
12
Apr 14, 2026
43.89SPICE
12
Mar 24, 2026
88.55Accuracy (Exist)
12
Mar 24, 2026
44.7HotpotQA Score
12
Mar 20, 2026