Fact Checking
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.3F1 Macro
14
Feb 26, 2026
87.2Accuracy
13
Mar 9, 2026
77.7Accuracy
12
Apr 23, 2026
91.9Balanced Accuracy
12
Mar 4, 2026
72.55Macro F1
12
Feb 26, 2026
71.82Macro F1 (2-hop)
12
Feb 26, 2026
93.1Accuracy
12
Jun 29, 2026
68.2Accuracy
11
Feb 26, 2026
62.1Balanced Accuracy
10
May 12, 2026
56.4Balanced Accuracy
10
May 12, 2026
0.2Cost ($)
10
Feb 26, 2026
55.1Acc
10
Feb 26, 2026
0.48Hu-METEOR (Q only)
9
Feb 26, 2026
88.78F1 Score
8
Mar 24, 2026
86.56Accuracy
8
Mar 24, 2026
75ROC-AUC
7
Apr 29, 2026
4.68Explanation Correctness
7
Apr 16, 2026
89.8Balanced Accuracy
7
Feb 26, 2026
78.7Accuracy
6
Feb 26, 2026
66.1Accuracy
6
Feb 26, 2026
78.5Overall Accuracy
6
Feb 26, 2026
81.2Balanced Accuracy
6
Feb 26, 2026
0.46Hu-METEOR (Q only)
6
Feb 26, 2026
77.5Accuracy
5
Feb 26, 2026
85.83Accuracy
4
Mar 31, 2026