Factuality Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.3MC2
103
May 19, 2026
63MC1 Score
30
May 19, 2026
86.4MC1 Score
30
May 19, 2026
96.2Overall Score
25
Jun 23, 2026
84.5Pairwise Score
24
Jun 2, 2026
8.84Factuality Score
21
Feb 26, 2026
53.9Pearson Correlation
19
Feb 26, 2026
90.6Response Accuracy
18
Apr 15, 2026
81Accuracy (Response)
18
Apr 15, 2026
88.4Response Accuracy
18
Apr 15, 2026
75.55FACTOR Score
18
Feb 26, 2026
84.57Accuracy
16
Feb 26, 2026
80.2Balanced Accuracy
15
Feb 26, 2026
82.1Balanced Accuracy
15
Feb 26, 2026
76.5Balanced Accuracy
15
Feb 26, 2026
70.3Balanced Accuracy
15
Feb 26, 2026
68.7Accuracy (Response)
14
Apr 15, 2026
73.9Balanced Accuracy
14
Feb 26, 2026
0.799Balanced Accuracy
14
Feb 26, 2026
70.5Balanced Accuracy (CNN-FTS)
14
Feb 26, 2026
69.9CNN Score
13
Apr 3, 2026
83.9Accuracy
13
Feb 26, 2026
29.4Correctness Count
12
Feb 26, 2026
28.9Correct Count
12
Feb 26, 2026
0.686Average Score
12
Feb 26, 2026