Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
22.59EM@1
16
Feb 26, 2026
72.2Accuracy (Biology)
15
Jun 16, 2026
80.1Accuracy
15
Jun 2, 2026
41.88Exact Match (EM)
15
May 29, 2026
96Algebra Score
15
May 27, 2026
33.41Rouge-L
15
May 26, 2026
38.8Rouge-L
15
May 26, 2026
45Rouge-L
15
May 26, 2026
839.81Tokens
15
May 18, 2026
49.93Accuracy
15
May 18, 2026
46.2Accuracy
15
May 18, 2026
72.64Accuracy
15
May 18, 2026
30.9Accuracy
15
May 18, 2026
1.61d Leakage Rate
15
May 15, 2026
87.51Accuracy
15
May 13, 2026
74.17Recall@1
15
May 12, 2026
72.33R@1
15
May 12, 2026
61Fact Retrieval Accuracy
15
Apr 24, 2026
89.48AUC
15
Apr 20, 2026
89.8Recall@1
15
Apr 20, 2026
280.3Total Score
15
Apr 16, 2026
92.18Accuracy (ARC-E)
15
May 12, 2026
42.2Accuracy
15
Apr 10, 2026
68Accuracy
15
Apr 21, 2026
93Accuracy
15
Apr 7, 2026