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

Library

Benchmarks

Task NameDataset NameSOTA ResultTrend
Formal Theorem ProvingLibrary 10
Proof Length10
6
Automated Theorem ProvingLibrary Plane Geometry 1.0 (test)
Output Tokens (Thousands)0.08
6
Visual NavigationLibrary Dynamic
Success Rate80
6
Visual NavigationLibrary Static
SR1
6
Library ExtensionLibrary Ext.
Accuracy40
5
Object PlacementLibrary polygon
Object Count88.6
3
Object RearrangementLibrary 30 m × 30 m (simulation)
Bin Success Rate100
1
Showing 7 of 7 rows