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

Coin Flip

Benchmarks

Task NameDataset NameSOTA ResultTrend
Symbolic ReasoningCoin Flip
Accuracy99.9
27
Symbolic ReasoningCoin Flip
Accuracy80.75
10
Symbolic ReasoningCoin Flip OOD (test)
Accuracy65.7
6
Symbolic ReasoningCoin Flip (test)
Accuracy98.6
6
Symbolic ReasoningCoin Flip (OOD)
pass@195.1
2
Symbolic ReasoningCoin Flip 4 times
Accuracy (format-specific)91.4
2
Showing 6 of 6 rows