Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
43.92Vanilla Accuracy
14
Feb 26, 2026
34.6EM
14
Feb 26, 2026
39.6EM
14
Feb 26, 2026
34.4EM
14
Feb 26, 2026
51.1Score
14
Feb 26, 2026
66.8Accuracy
14
Feb 26, 2026
100BAR
14
Feb 26, 2026
55Average Score
14
Feb 26, 2026
95.2Accuracy
14
Feb 26, 2026
54.9EM
14
Feb 26, 2026
39.51Accuracy
14
Feb 26, 2026
42.12AN' Score
14
Feb 26, 2026
59.23AN
14
Feb 26, 2026
11.7ROUGE-L
14
Feb 26, 2026
19.1ROUGE-L
14
Feb 26, 2026
57.2ROUGE-L
14
Feb 26, 2026
26.6ROUGE-L Score
14
Feb 26, 2026
99.6WebQ Accuracy
14
May 28, 2026
87.82F1 Score
14
Feb 26, 2026
38.8OBQA
14
Feb 26, 2026
93.9Hits@1
14
Feb 26, 2026
89.23OpenbookQA Score
13
Jul 3, 2026
46.2Accuracy
13
Jun 29, 2026
64.5Accuracy
13
Jun 19, 2026
56.37Pass@1 Accuracy
13
Jun 9, 2026