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

Symbolic Reasoning on Coin Flip (Accuracy, Average Accuracy)

80.75Accuracy

RM-Primed

58.1364.002569.87575.7475Mar 20, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
80.7568.23
2026.03
79.7566.01
2026.03
78.7565.94
2026.03
7864.99
2026.03
74.2561.15
2026.03
69.2560.33
2026.03
66.2561.13
2026.03
65.7564.19
2026.03
60.7559.56
2026.03
5957.01