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

Sliding Puzzle

Benchmarks

Task NameDataset NameSOTA ResultTrend
Sliding PuzzleSliding Puzzle
Solve Rate56.3
7
Structured video reasoningSliding Puzzle Hard
Exact Match Rate88.7
6
Structured video reasoningSliding Puzzle Med.
Success Rate89
6
Structured video reasoningSliding Puzzle Easy
Exact Match Rate77
6
Structured video reasoningSliding Puzzle Overall
Exact Match (%)86.5
6
Showing 5 of 5 rows