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

Chess Puzzles

Benchmarks

Task NameDataset NameSOTA ResultTrend
Grounded Chess ReasoningChess Puzzles (test)
Accuracy (Beginner)95
20
Chess Puzzle SolvingChess Puzzles Novel boards
Puzzle Accuracy100
12
Showing 2 of 2 rows