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

Maze3D

Benchmarks

Task NameDataset NameSOTA ResultTrend
Structured video reasoningMaze3D Hard
Exact Match95.3
6
Structured video reasoningMaze3D Med.
Exact Match Rate100
6
Structured video reasoningMaze3D Easy
Exact Match Percentage100
6
Structured video reasoningMaze3D Overall
Exact Match (%)97.7
6
Showing 4 of 4 rows