CLARU
VLA-Arena2025apache-2.0

VLA-Arena Dataset (L1 - Large Variant)

An open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models featuring 55 tasks at difficulty level 1 with 2,750 human demonstrations across safety, distractor, extrapolation, and long-horizon domains.

Downloads100
Episodes2750
Hours10.606

Technical Profile

Modalities
rgbproprioceptionlanguage
Robot Embodiments
panda
Action Space
7-DoF
Environment
simulation
Task Types
manipulationgraspingpick_and_place
Episodes
2750
Total Hours
10.606
Data Format
LeRobot
License
apache-2.0
Part of the VLA-Arena Dataset (L1 - Large Variant) family

Access

View on HuggingFace

Need custom rgb data?

Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets

VLA-Arena Dataset (L1 - Large Variant)

An open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models with 55 tasks at difficulty level 1, containing 2,750 human demonstrations across safety, distractor, extrapolation, and long-horizon domains.

rgbproprioceptionlanguage
770 downloadsFeb 2026apache-2.0

VLA-Arena Dataset (L1 - Large Variant)

An open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models featuring 55 tasks at difficulty level 1 with 2,750 human demonstrations across safety, distractor, extrapolation, and long-horizon domains.

rgbproprioceptionlanguage
488 downloadsDec 2025apache-2.0

VLA-Arena Dataset (L1 - Large Variant)

An open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models, featuring 55 tasks at difficulty level 1 with 2,750 human demonstrations across safety, distractor, extrapolation, and long horizon domains.

rgbproprioceptionlanguage
36 downloadsDec 2025apache-2.0

Artery Single Tool

A robotics dataset created using LeRobot containing 40 episodes of robot demonstrations with joint positions and gripper camera observations.

rgbproprioception
null downloadsJul 2026apache-2.0

MVISTA-4D

Multi-view 4D robot-manipulation dataset spanning RobotWin (simulation), RLBench (simulation), and real-robot collection, used to train camera-controlled 4D generative world models. Each episode provides synchronized multi-view RGB + depth video plus robot joint/action and camera parameters.

rgbdepthpoint_cloudproprioception+1
null downloadsAug 2026mixed

EJ-DEMO/new_setup_test1_20260724_171053

A robotics dataset created using LeRobot containing demonstrations of a SO follower robot performing tasks with multi-camera RGB observations and joint position actions.

rgbproprioception
null downloadsJul 2026apache-2.0gated