Open-Book Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
35Accuracy
33
Feb 26, 2026
79.51Exact Match
17
Jun 4, 2026
57.52Accuracy
13
Jun 24, 2026
53.6Accuracy
13
Jun 24, 2026
89.4Normalized Log Accuracy
12
Mar 26, 2026
38.47Accuracy
6
Jun 24, 2026
43.36Score
6
Apr 1, 2026
55EM
6
Feb 26, 2026
12.8Normalized PLL Score
4
Feb 26, 2026