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

Logical Reasoning on ProntoQA (test)

99.72Accuracy

HBLR

36.571252.965669.3685.7544Oct 28, 2023Apr 1, 2024Sep 4, 2024Feb 7, 2025Jul 13, 2025Dec 16, 2025May 22, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2025.12
99.72-
2025.12
99.57-
2025.12
99.55-
2025.12
99.36-
2023.10
98.69.78
2025.12
98.47-
2025.12
98.43-
2023.10
98.214.18
2025.12
97.67-
2023.10
97.618.91
2025.12
97.28-
2025.12
97.16-
2023.10
95.610.56
2025.12
94.79-
2023.10
93.811.38
2023.10
93.416
2023.10
93.210.74
2023.10
92.416.93
2023.10
91.219.3
2023.10
911
2023.10
90.812.09
2025.12
90.5-
2026.05
89-
2023.10
88.613.58
2025.12
87.83-
2023.10
86.816
2025.12
84.21-
2023.10
841
2026.05
81.5-
2026.05
81-
2026.05
79-
2023.10
77.41
2025.12
77.4-
2025.12
75.58-
2026.05
75-
2025.12
74.93-
2026.05
73-
2026.05
72-
2025.12
71.95-
2026.05
69-
2026.05
68-
2025.12
67.8-
2025.12
67.21-
2026.05
67-
2026.05
64-
2026.05
62-
2026.05
61-
2026.05
60-
2026.05
58-
2026.05
56.5-
2026.05
52.5-
2023.10
51.81
2026.05
48-
2025.12
46.04-
2026.05
44-
2026.05
41-
2026.05
39-