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

Value Estimation research benchmarks · SOTA2 Research

Value Estimation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

-0.759Bias

8

May 29, 2026

Sepsis simulator

0.001Bias

8

May 29, 2026

Suboptimal-RoboSuite Value-Bench

0.04Hesitation RMSE

7

Jun 24, 2026

Suboptimal-Value-Bench ARX

0.05Hesitation RMSE

7

Jun 24, 2026

Suboptimal-Value-Bench AgileX

0.07Hesitation RMSE

7

Jun 24, 2026

Suboptimal-Value-Bench AgileX (retry segments)

0.79Retry-VOC

5

Jun 24, 2026

Suboptimal-Value-Bench RoboSuite (retry segments)

0.75Retry-VOC

4

Jun 24, 2026

Suboptimal-Value-Bench ARX (retry segments)

0.79Retry VOC

4

Jun 24, 2026

Real-robot manipulation tasks (Pick up Spoon, Stack Blocks, Fold Towel, Open Drawer) (held-out)

99.4VOC

4

Jun 24, 2026

Popular datasets

Suboptimal-Value-Bench Sepsis Simulator Robosuite ICU Sepsis Real-robot manipulation tasks

Follow for updates

Join SOTA2 Contact