Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
19.28EM
18
Feb 26, 2026
94.56Accuracy
18
Mar 4, 2026
0.822F1
18
Mar 5, 2026
23.96Average Score
18
Feb 26, 2026
28.4EM
18
Feb 26, 2026
82.3EM
18
Feb 26, 2026
18.4EM
17
May 28, 2026
53.2RACC
17
May 25, 2026
48.8Retrieval Accuracy (RACC)
17
May 25, 2026
89.4Accuracy
17
May 8, 2026
85.1Accuracy
17
May 8, 2026
85.9Accuracy (%)
17
May 6, 2026
99.8Accuracy (%)
17
May 6, 2026
99.6Accuracy
17
May 6, 2026
61.1Macro-F1
17
May 4, 2026
63.82HotpotQA Score
17
Apr 24, 2026
43.6Accuracy
17
Jun 18, 2026
83.73Hits@1
17
Apr 15, 2026
65.7EM
17
Apr 14, 2026
41.6EM
17
Apr 14, 2026
67.23Metric C
17
Jun 25, 2026
69.29F1
17
Apr 8, 2026
63.1Strict Accuracy
17
May 28, 2026
57PubMedQA Accuracy
17
Apr 3, 2026
85.9F1 Score
17
Apr 2, 2026