Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Failure-revealing testing for VLA models research benchmarks · SOTA2 Research

Failure-revealing testing for VLA models

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Robotic Manipulation Tasks Simulation (test)

90.38Failure Detection

2

Jun 2, 2026

Popular datasets

Robotic Manipulation Tasks

Follow for updates

Join SOTA2 Contact