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

General Reasoning on AGIEval

70.4Exact Match

GPT-4

27.44838.59949.7560.901Nov 18, 2023Apr 1, 2024Aug 14, 2024Dec 27, 2024May 11, 2025Sep 23, 2025Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2023.11
70.4
2026.01
66.1
2026.01
64.8
2026.01
59.6
2026.01
59.1
2026.01
58.7
2026.01
57
2023.11
53.13
2026.01
51.1
2023.11
49.93
2023.11
48.73
2023.11
48.18
2023.11
46.7
2026.01
45.9
2023.11
45.69
2023.11
45.1
2023.11
43.97
2026.01
43
2026.01
41.8
2023.11
38.85
2026.02
38.84
2026.01
38.6
2026.02
38.53
2026.02
38.47
2023.11
38.25
2026.02
37.9
2026.02
37.86
2026.02
37.85
2026.02
37.09
2026.02
36.96
2026.02
35.76
2026.02
34.51
2026.01
29.1