Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.69Normalized Sub-EM Accuracy
11
Feb 26, 2026
80.47Normalized Sub-EM Accuracy
11
Feb 26, 2026
81.25Normalized Sub-EM Accuracy
11
Feb 26, 2026
82.03Normalized Sub-EM Accuracy
11
Feb 26, 2026
0.813Normalized Sub-EM Accuracy
11
Feb 26, 2026
0.82Sub-EM Accuracy
11
Feb 26, 2026
5.494NACE (mean)
11
Feb 26, 2026
39.05BLEU
11
Feb 26, 2026
53.69Accuracy
11
Feb 26, 2026
54.4EM
11
Feb 26, 2026
71.4Exact F1
11
Feb 26, 2026
0.791Accuracy
11
Feb 26, 2026
83.12EM
11
Feb 26, 2026
80F1 Score (es)
11
Mar 13, 2026
76.5F1 Score
11
Feb 26, 2026
82.4Exact Match (EM)
11
Feb 26, 2026
100Accuracy
11
Feb 26, 2026
82.52AUC
10
Jul 7, 2026
84.47AUC
10
Jul 7, 2026
82.32AUC
10
Jul 7, 2026
54.17Accuracy
10
Jun 30, 2026
55.73Accuracy
10
Jun 30, 2026
38.1EM
10
Jun 30, 2026
60EM
10
Jun 30, 2026
47.96EM
10
Jun 26, 2026