Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Claim Verification on 9-dataset aggregate retrieval-free setting (test)

84ROC-AUC

GPT-4.1

47.18456.74266.375.858Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
8478.3
2026.03
78.269.6
2026.03
77.770.1
2026.03
77.773.1
2026.03
77.568.9
2026.03
76.567.1
2026.03
7570.5
2026.03
74.768.4
2026.03
73.368.7
2026.03
73.369
2026.03
73.168.9
2026.03
72.869.3
2026.03
72.266.5
2026.03
7264.5
2026.03
7267.6
2026.03
71.667.6
2026.03
71.468.3
2026.03
71.164.1
2026.03
70.966.9
2026.03
70.667
2026.03
70.266.1
2026.03
7065.4
2026.03
69.867.6
2026.03
69.665.5
2026.03
69.564.6
2026.03
69.464.6
2026.03
69.164.5
2026.03
69.165.6
2026.03
6964.9
2026.03
68.864.9
2026.03
68.665.6
2026.03
68.464.5
2026.03
6864.4
2026.03
67.864.7
2026.03
67.564.3
2026.03
67.364.2
2026.03
67.165.5
2026.03
66.864.4
2026.03
66.663.1
2026.03
66.663.1
2026.03
66.462.8
2026.03
65.761.6
2026.03
65.762.4
2026.03
65.462.6
2026.03
65.362.5
2026.03
64.961.2
2026.03
64.761.2
2026.03
64.761.5
2026.03
63.961.1
2026.03
63.860.7
2026.03
63.860.9
2026.03
63.660.6
2026.03
63.160.2
2026.03
63.160.2
2026.03
62.559
2026.03
61.960.8
2026.03
61.958.9
2026.03
61.658.6
2026.03
61.457.9
2026.03
60.958
2026.03
60.856.6
2026.03
58.757.1
2026.03
58.658.2
2026.03
5351.8
2026.03
51.151
2026.03
50.550.6
2026.03
50.350.6
2026.03
50.255.1
2026.03
5050.2
2026.03
48.649.2