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

Tree Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
General and structural reasoningTree-Bench
Accuracy56.54
10
Visual ReasoningTree Bench
Score39
9
OCRTree Bench
Score49.1
9
Real-World UnderstandingTree Bench
Accuracy42.5
7
Showing 4 of 4 rows