Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.68Accuracy
5
Apr 29, 2026
39.3NQ Score
5
Apr 28, 2026
74.8Accuracy
5
Apr 24, 2026
1.291Average Length (s)
5
Apr 23, 2026
1.081Average Latency (s)
5
Apr 23, 2026
39.2Entity Log Score
5
Apr 23, 2026
25.04F1 Score
5
Apr 21, 2026
39.44F1
5
Apr 21, 2026
48.3F1 Score
5
Apr 21, 2026
32.8F1 Score
5
Apr 21, 2026
28.5SECE Score
5
Apr 21, 2026
18.7SECE (%)
5
Apr 21, 2026
19.7ECE
5
Apr 21, 2026
60.9Accuracy
5
Apr 21, 2026
15Accuracy
5
Apr 21, 2026
7.4Accuracy Improvement (Δ)
5
Apr 21, 2026
75.72Accuracy
5
Apr 16, 2026
86.02Short QA Score
5
Apr 15, 2026
32.6F1 Score
5
Apr 15, 2026
23EM
5
Apr 15, 2026
62.2EM
5
Apr 15, 2026
12.47F1 Score
5
Apr 15, 2026
0.64MAE
5
Apr 8, 2026
76SQuAD 1.1 EM/F1 Score
5
Apr 6, 2026
76.4Accuracy
5
Apr 3, 2026