Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
68.75EM
5
Feb 26, 2026
52EM
5
Feb 26, 2026
83.9EM
5
Feb 26, 2026
57.8EM
5
Feb 26, 2026
0.992HIT@1
5
Feb 26, 2026
62.26Accuracy
5
Feb 26, 2026
40.58F1 Score
5
Feb 26, 2026
43.16F1 Score
5
Feb 26, 2026
42.35Average EM
5
Feb 26, 2026
42Temporal Accuracy (FEM)
5
Feb 26, 2026
50Temporal Score (FEM)
5
Feb 26, 2026
36.66ROUGE-L
5
Feb 26, 2026
46.83ROUGE-L
5
Feb 26, 2026
72.9Score
5
Feb 26, 2026
86.7F1 Score
5
Feb 26, 2026
43.21F1
5
Feb 26, 2026
68.52F1 Score
5
Feb 26, 2026
42.74F1 Score
5
Feb 26, 2026
35.93EM
5
Feb 26, 2026
81.43EM
5
Feb 26, 2026
0.864Accuracy
5
Feb 26, 2026
0.649HealthBench Score
5
Feb 26, 2026
99.2Accuracy
5
Feb 26, 2026
95.2Accuracy
5
Feb 26, 2026
43.07Accuracy
5
Feb 26, 2026