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

Logical Reasoning on LogiQA2

86.4Accuracy

GPT-4.5

22.23238.89155.5572.209Jun 2, 2026Jun 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
86.4-
2026.06
83.1-
2026.06
79.2-
2026.06
74.8-
2026.06
74.1-
2026.06
73.6-
2026.06
72.9-
2026.06
72.4-
2026.06
71.8-
2026.06
70.1-
2026.06
69.3-
69.2-
2026.06
68.4-
2026.06
66.8-
2026.06
65.7-
2026.06
64.9-
2026.06
64.3-
2026.06
61.2-
61-
2026.06
60.1-
2026.06
34.4-
2026.06
32.984.9
2026.06
30.560.5
2026.06
24.7-