Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
37.8Exact Match
10
Apr 28, 2026
56.3Accuracy (Acc)
10
Apr 24, 2026
75.4Exact Match (EM)
10
Apr 23, 2026
92.5Exact Match
10
Apr 23, 2026
91.01Type 1 F1
10
Apr 21, 2026
43.11Exact Match (EM)
10
Apr 21, 2026
97.2Mean Confidence
10
Apr 21, 2026
54.49Exact Match (EM)
10
Apr 21, 2026
35.16EM
10
Apr 21, 2026
41.02EM
10
Apr 21, 2026
34.96Exact Match (EM)
10
Apr 21, 2026
27QA Accuracy
10
Apr 15, 2026
21.2EM
10
Apr 14, 2026
28.7EM
10
Apr 14, 2026
32EM
10
Apr 14, 2026
85.71SAME_CONCLUSION Score
10
Apr 13, 2026
53.2F1 Score
10
Apr 9, 2026
83.9Exact Match (EM)
10
Apr 9, 2026
49.8Exact Match (EM)
10
Apr 9, 2026
90.3Accuracy
10
Apr 8, 2026
66.8EM
10
Jun 4, 2026
80.63PiQA Accuracy
10
Apr 2, 2026
72.17F1 Score
10
Mar 25, 2026
17.05Exact Match (EM)
10
Mar 25, 2026
70.5Accuracy
10
Mar 18, 2026