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

MOST RELIABLE PATH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Algorithmic ReasoningMOST RELIABLE PATH 100 nodes
Key Accuracy579
6
Algorithmic ReasoningMOST RELIABLE PATH 50 nodes
Key Identification Accuracy3.04
6
Algorithmic ReasoningMOST RELIABLE PATH 20 nodes
Key Accuracy17.3
6
Showing 3 of 3 rows