Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.614BLEU-1
8
Feb 26, 2026
44.1BLEU-1
8
Feb 26, 2026
0.9µbias
8
Feb 26, 2026
2.8Mu Bias (STEM)
8
Feb 26, 2026
66.67Accuracy
8
Feb 26, 2026
29.9ARC-C
8
Feb 26, 2026
27.7Accuracy
8
Feb 26, 2026
40EM
8
Feb 26, 2026
79.99SQuAD 2
8
Feb 26, 2026
88.13Accuracy
8
Feb 26, 2026
36.14Accuracy
8
Feb 26, 2026
45.5Accuracy
8
Feb 26, 2026
50.37EM
8
Feb 26, 2026
67.7Avg Score
8
Feb 26, 2026
89F1 (en)
8
Feb 26, 2026
45.5MRR
8
Feb 26, 2026
53.3F1
8
Feb 26, 2026
29.6F1
8
Feb 26, 2026
0.832MAP
8
Feb 26, 2026
55.64EM
8
Feb 26, 2026
75.9Accuracy
8
Feb 26, 2026
4.55Average Error Rate
8
Feb 26, 2026
46.2EM
8
Feb 26, 2026
79.2Accuracy
8
Feb 26, 2026
77.2EM
8
Feb 26, 2026