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

PROGRESS-BENCH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Viewpoint RobustnessProgress-Bench 1.0 (test)
ΔNSE-1.1
16
Progress ReasoningProgress-Bench Cross-View 1.0 (test)
NSE15.2
16
Progress ReasoningProgress-Bench Same-View 1.0 (test)
NSE10.3
16
Progress EstimationPROGRESS-BENCH Answerable samples 1.0
NSE (Vision)13.8
16
Showing 4 of 4 rows