Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70Correct Count
4
May 15, 2026
51.53Accuracy (56K Context)
4
May 14, 2026
14.2Accuracy
4
May 14, 2026
92.8Precision
4
May 13, 2026
100Precision
4
May 13, 2026
100Precision
4
May 13, 2026
93.2Precision
4
May 13, 2026
87.2Precision
4
May 13, 2026
37.8Mean Score
4
May 11, 2026
6.1Mean Score
4
May 11, 2026
0.392Mean Score (Bamboogle QA)
4
May 11, 2026
18.6Mean Score (Musique QA)
4
May 11, 2026
38.8Mean Performance
4
May 11, 2026
50.4Mean Performance
4
May 11, 2026
65.5Mean Score (TriviaQA)
4
May 11, 2026
47Mean Score
4
May 11, 2026
96.7Accuracy
4
May 11, 2026
27.34Delta EM
4
May 8, 2026
2.57Acceptance Length (τ)
4
May 7, 2026
84.7ARC-C Score
4
May 4, 2026
72.8Accuracy
4
May 4, 2026
89.33Precision
4
Apr 28, 2026
1Steps
4
Apr 24, 2026
1Steps
4
Apr 24, 2026
1Steps
4
Apr 24, 2026