Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
69.3MMLU Accuracy
21
May 20, 2026
83.7Accuracy
21
Apr 16, 2026
42.85Factual Accuracy
21
Feb 26, 2026
28.27Factual Accuracy
21
Feb 26, 2026
49.2Factual Accuracy
21
Feb 26, 2026
47Factual Accuracy
21
Feb 26, 2026
0.434Perf
21
Feb 26, 2026
44.29F1 Score
21
Feb 27, 2026
88.5Accuracy
21
Feb 26, 2026
90.9Accuracy
21
Feb 26, 2026
90Accuracy
21
Feb 26, 2026
92.8Accuracy
21
Feb 26, 2026
98.1Accuracy
21
Feb 26, 2026
98.6Accuracy
21
Feb 26, 2026
0.92Faith
21
Feb 26, 2026
93.4Faithfulness
21
Feb 26, 2026
0.908Faith
21
Feb 26, 2026
87.48Faith
21
Feb 26, 2026
0.946Faithfulness
21
Feb 26, 2026
60.9Accuracy
21
Mar 18, 2026
37.23EM
21
Jun 26, 2026
65.5Accuracy
21
Feb 26, 2026
77.6Accuracy
21
Feb 26, 2026
89.34EM
21
Feb 26, 2026
77.6Accuracy
21
Feb 26, 2026