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

GiantSteps

Benchmarks

Task NameDataset NameSOTA ResultTrend
Key DetectionGS (GiantSteps) Linear Probing
Refined Accuracy66.1
15
Key DetectionGS GiantSteps (test)
GS Score79.6
9
Key EstimationGiantSteps
Weighted Error59.3
7
Showing 3 of 3 rows