Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.5Performance (F1/EM)
11
May 19, 2026
56.62Accuracy
11
May 15, 2026
65.4Accuracy
11
May 12, 2026
85.67Accuracy (ACC)
11
May 11, 2026
93.67ACC
11
May 11, 2026
98Accuracy
11
May 11, 2026
11.7IDK Score
11
May 1, 2026
97Accuracy
11
Apr 28, 2026
98Accuracy
11
Apr 28, 2026
80.38OP
11
Apr 24, 2026
60.88MedQA Accuracy
11
Apr 21, 2026
60.24o-J Score
11
Apr 14, 2026
67.714o-J Score
11
Apr 14, 2026
48.844o-J
11
Apr 14, 2026
53.97pass@128
11
Apr 10, 2026
100Coverage Rate
11
Apr 9, 2026
41.6EM
11
Apr 8, 2026
66.6EM
11
Apr 8, 2026
52.4EM
11
Apr 8, 2026
38.4EM
11
Apr 8, 2026
21.8Exact Match (EM)
11
Apr 8, 2026
42.6EM
11
Apr 8, 2026
83.02Accuracy
11
May 11, 2026
39.81BLEU-1
11
Apr 3, 2026
0Cost (cents)
11
Mar 24, 2026