Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84F1 Score (CoQA)
7
May 15, 2026
78.4F1 Score
7
May 15, 2026
3.54Wall-clock Time (hours)
7
May 12, 2026
62.3ARC-E Score
7
May 11, 2026
99.2EM (raw)
7
May 8, 2026
45.27F1 Score
7
May 8, 2026
46.59F1 Score
7
May 8, 2026
43.31F1 Score
7
May 8, 2026
39.37F1 Score
7
May 8, 2026
64.5Accuracy (Acc)
7
May 8, 2026
72.5Accuracy
7
May 8, 2026
69Accuracy
7
May 8, 2026
55.5Overall F1
7
May 4, 2026
81AUROC
7
May 1, 2026
52Occ
7
May 1, 2026
72.35Accuracy
7
May 1, 2026
45.84ROUGE-1
7
Apr 28, 2026
21.41ROUGE-1
7
Apr 28, 2026
51.5Accuracy
7
Apr 27, 2026
77.53Accuracy
7
Apr 24, 2026
95.97Accuracy
7
Apr 24, 2026
36.58Accuracy
7
Apr 23, 2026
34.36Normalized Accuracy
7
Apr 23, 2026
54.3Accuracy
7
Apr 21, 2026
49.1F1 Score
7
Apr 21, 2026