Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.3Accuracy
8
May 12, 2026
80Accuracy
8
Apr 28, 2026
11.997BLEU
8
Apr 21, 2026
2.718ECE' Gain
8
Apr 21, 2026
0ECE' Gain
8
Apr 21, 2026
73.61Normalized Accuracy
8
Apr 20, 2026
73.7Overall Accuracy
8
Apr 15, 2026
63.21F1 Score
8
Apr 15, 2026
46.64o-J Score
8
Apr 14, 2026
78.12Pass@1
8
Apr 14, 2026
34.51Pass@1
8
Apr 14, 2026
92.42Accuracy (ARC-C avg.@8)
8
Apr 14, 2026
43.43Average Score (@8)
8
Apr 14, 2026
89.69Accuracy (ACC)
8
Apr 13, 2026
99.5Accuracy
8
Apr 3, 2026
44.5Accuracy
8
Apr 2, 2026
64Precision
8
Apr 2, 2026
90.4Accuracy
8
Apr 1, 2026
40.61Accuracy
8
Apr 1, 2026
63.21Accuracy
8
Mar 31, 2026
44EM
8
Mar 31, 2026
47.6OpenBookQA Score
8
Mar 31, 2026
27Average Correctness
8
Mar 27, 2026
77.84Accuracy
8
Apr 16, 2026
256Tokens
8
Mar 20, 2026