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

Galaxy

Benchmarks

Task NameDataset NameSOTA ResultTrend
Image ClassificationGalaxy10
Accuracy87
13
Scientific Multimodal ReasoningGalaxy-10
Accuracy57.72
10
Symbolic RegressionGalaxy (test)
Median RMSE0.2824
5
Symbolic RegressionGalaxy
Median Program Size86
3
Density EstimationGalaxy (test)
Bits-per-Dimension2.2591
3
Showing 5 of 5 rows