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

GEOS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Simulation deck generationGEOS v1 (val)
TreeSim92.1
11
Simulation deck generationGEOS v1 (held-out-eval)
TreeSim Score78.9
6
Geometry problem solvingGEOS
Accuracy67
5
Showing 3 of 3 rows