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

Robot Manipulation research benchmarks – Page 26 · SOTA2 Research

Robot Manipulation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Popcorn-scooping (out-of-distribution)

DuoCore-FS-slow

70Pick Up Cup SR

3

Feb 26, 2026

RoboTwin Hard Simulation

13Hanging Mug Success Rate

3

Feb 26, 2026

RoboTwin Easy Simulation

0.24Hanging Mug

3

Feb 26, 2026

100Basketball Success Rate (B)

3

Feb 26, 2026

Extended Real-World Evaluation Aggregate

73Average Success Rate (SR)

3

Feb 26, 2026

RLBench View (train)

52.9SR (Avg)

3

Feb 26, 2026

Stack Two Bowls Real-world (test)

100Subtask 1 Score

3

Feb 26, 2026

Find the Block and Place It in the Basket Real-world (test)

100Subtask 1 Success Rate

3

Feb 26, 2026

Sort All Fruits into the Basket Real-world (test)

6,670Subtask 1 Success Rate

3

Feb 26, 2026

Put All Objects into the Basket Real-world (test)

50Subtask 1 Success

3

Feb 26, 2026

5 Tasks Unseen Target Setup (train)

100Task 1 (Cola Can) Approach

3

Feb 26, 2026

5 Tasks Unseen Distractor Setup (train)

100Task 1 (cola can) App Success

3

Feb 26, 2026

5 Tasks Basic Setup (train)

100Task 1 (cola can) Approach Rate

3

Feb 26, 2026

64Nut Success Rate

3

Feb 26, 2026

Real-world manipulation tasks 1.0 (test)

96.7Pick Success Rate (Irregular Object)

3

Feb 26, 2026

SAGE Generated Scenes (test)

46Success Rate

3

Feb 26, 2026

Holodeck Generated Scenes Baseline 2 (test)

24.7Success Rate

3

Feb 26, 2026

SceneWeaver Baseline 1 Generated Scenes (test)

39.1Success Rate

3

Feb 26, 2026

RLBench 18 Tasks multi-variation

46.4Success Rate

3

Feb 26, 2026

88Adjust Bottle Success Rate

2

Jul 7, 2026

AgileX PiPER real-world (test)

π0.5 + VLA-Corrector

78.3Pick-place Success Rate

2

Jul 3, 2026

LIBERO-Plus (first 200 tasks in each category)

MolMoAct + E-TTS

91.2Spatial Success Rate

2

Jun 26, 2026

VLABench Track 6

6IF

2

Jun 26, 2026

VLABench Track 4

6IF

2

Jun 26, 2026

VLABench Track 3

10IF

2

Jun 26, 2026

Page 26 of 31

Popular datasets

LIBERO RoboTwin RLBench SimplerEnv Real-world Robot Manipulation

Follow for updates

Join SOTA2 Contact