Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
8.8ECE
16
Apr 3, 2026
81.3Accuracy
16
Apr 3, 2026
45.58Single-Hop Performance
16
Mar 31, 2026
82Exact Match (EM)
16
Apr 7, 2026
98ATR
16
Mar 30, 2026
95Accuracy
16
Mar 18, 2026
68Accuracy
16
Mar 11, 2026
81.08Accuracy
16
Jun 4, 2026
91.7Accuracy
16
Mar 4, 2026
50.43Arc Challenge (C) Accuracy
16
Mar 4, 2026
51.31Precision
16
Feb 26, 2026
38.7Exact Match Accuracy
16
Feb 26, 2026
38.6Exact Match (EM)
16
Feb 26, 2026
36.4Exact Match Accuracy
16
Feb 26, 2026
52.7Exact Match (EM)
16
Feb 26, 2026
42.9Exact Match Accuracy
16
Feb 26, 2026
86.7Seed Score
16
Feb 26, 2026
0.636PR-AUC
16
Feb 26, 2026
0.595PR-AUC
16
Feb 26, 2026
0.681PR-AUC
16
Feb 26, 2026
60PR-AUC
16
Feb 26, 2026
72.2PR-AUC
16
Feb 26, 2026
0.766PR-AUC
16
Feb 26, 2026
38.8Accuracy
16
Feb 26, 2026
84.9English Correctness
16
Feb 26, 2026