VLABench

Vision-language-action benchmark for evaluating robotic policy models through the AllenAI VLA evaluation harness leaderboard.

4rows
scoreprimary metric
2026-05-06sampled

Metadata

ID
vlabench
Category
Multimodal
Release
2024-12-24

Metrics

VLA score

Latest Results

Rows are ranked by the Hugging Face leaderboard API rank. Model display names are preserved from source modelId values.

Rank Subject VLA score Model Match Provenance Sampled
1 lerobot/pi0_base 44.50 — Imported 2026-05-06
2 lerobot/pi05_base 42 — Imported 2026-05-06
3 nvidia/GR00T-N1-2B 39.70 — Imported 2026-05-06
4 lerobot/pi0fast-base 34.10 — Imported 2026-05-06