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

Logical Reasoning on LogiQA-2

83.8Accuracy

GPT-5

38.19650.035561.87573.7145Jul 12, 2024Oct 29, 2024Feb 15, 2025Jun 4, 2025Sep 21, 2025Jan 8, 2026Apr 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
83.8
2026.01
78.9
2026.01
78.2
2024.07
76.1
2026.01
72.9
2024.07
70.6
2024.07
69.8
2024.07
68.6
2026.01
66.8
2024.07
65.1
2026.01
62.7
2024.07
60.7
2026.04
60.1
2026.04
59.5
2026.04
59.4
2026.04
59.4
2026.04
59.4
2026.04
59.2
2026.04
59
2026.04
59
2026.04
58.8
2026.04
58.5
2026.04
58.3
2026.04
57.7
2026.04
57.7
2026.04
57
2026.04
56.8
2026.04
56.8
2026.04
56
2024.07
55.6
2026.04
55.5
2026.04
55.3
2026.04
55.2
2026.04
55.2
2026.04
54
2026.04
54
2024.07
52.2
2026.04
52.04
2026.04
51.84
2026.04
51.84
2024.07
51.6
2026.04
51.59
2026.04
51.53
2024.07
51.5
2026.04
51.4
2026.04
51.15
2026.04
51.02
2026.04
51.02
2024.07
51
2026.04
50.95
2026.04
50.7
2026.04
50.64
2026.01
50.4
2026.04
50.38
2026.04
50.38
2026.04
50.32
2026.04
50.32
2026.04
50.19
2026.04
50.13
2026.04
50.13
2026.04
50
2026.04
50
2026.04
50
2026.04
49.87
2026.04
49.8
2026.04
49.75
2026.04
49.43
2026.01
49.2
2026.04
48.98
2026.04
48.47
2026.04
47.8
2026.01
47.2
2026.01
47.1
2026.04
47
2026.04
45.7
2026.01
45.6
2026.01
45.3
2026.04
43.6
2024.07
42.2
2026.04
41.98
2026.04
41.79
2026.04
41.48
2026.04
41.22
2026.01
41.2
2026.04
41.16
2026.04
41.09
2026.04
41.09
2026.04
41.03
2026.04
40.84
2026.04
40.84
2026.01
40.8
2026.04
40.65
2026.01
40.3
2026.04
40.27
2026.04
40.2
2026.04
40.01
2026.04
40.01
2026.04
39.95
2026.04
39.95
2026.04
39.95
Showing 100 of 116 rows