Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.4Accuracy
4
Apr 23, 2026
27.8Accuracy
4
Apr 21, 2026
0.725Accuracy
4
Apr 21, 2026
51.8Accuracy
4
Apr 21, 2026
88Type 1 Accuracy
4
Apr 21, 2026
31.65Token F1
4
Apr 21, 2026
65.27Accuracy
4
Apr 16, 2026
83.3TF
4
Apr 15, 2026
40IPhO Accuracy
4
Apr 14, 2026
82.1CoverEM
4
Apr 14, 2026
52.4CoverEM
4
Apr 14, 2026
48.5CoverEM
4
Apr 14, 2026
49.1CoverEM
4
Apr 14, 2026
45CoverEM
4
Apr 14, 2026
45F1 Score
4
Apr 10, 2026
329.2CIDEr
4
Apr 10, 2026
9.9nAUPC
4
Apr 8, 2026
5.7nAUPC
4
Apr 8, 2026
38.1nAUPC
4
Apr 8, 2026
4.3nAUPC
4
Apr 8, 2026
11.3nAUPC
4
Apr 8, 2026
98Exact Match (EM)
4
Apr 8, 2026
4.89GenericJudge Score
4
Apr 8, 2026
4.46GenericJudge Score
4
Apr 8, 2026
4.58GenericJudge Score
4
Apr 8, 2026