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

Symbolic Reasoning on Coin Flip

99.9Accuracy

Auto-CoT

9.31632.83356.3579.867Oct 7, 2022May 5, 2023Dec 1, 2023Jun 28, 2024Jan 24, 2025Aug 22, 2025Mar 20, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2022.10
99.9
2023.06
99.9
2023.06
99.2
2023.06
99
2023.06
98
2023.06
97.4
2023.06
97.4
2022.10
97.2
2022.10
91.4
2023.06
91.4
2026.03
78.5
2026.03
77.75
2026.03
75.25
2026.03
75
2023.06
74.5
2026.03
69.25
2026.03
68.25
2026.03
66
2026.03
66
2022.10
57.2
2026.03
54.25
2022.10
53.8
2026.03
50.75
2023.06
49.1
2026.03
45
2026.03
44
2023.06
12.8