PhysicalAI.bestOur standard
Benchmark / simulation

LIBERO-Pro

LIBERO-Pro extends LIBERO evaluation to probe robustness beyond memorized initial states, objects and instructions.

Source contextPrimary specReviewed
Sources 2
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

LIBERO-Pro original paper

Xueyang Zhou and coauthors · Publication date not disclosed · Source accessed 2026-09-28

Reviewed recordLast reviewed 2 sources ↗6 sourced fields
Official source Suggest a correction

What the protocol tests

The original repository reuses the LIBERO runtime and publishes additional initialization and task-definition assets. This helps isolate perturbations but does not make the resulting tasks identical to the original suites.

Source contextPrimary specReviewed
Sources 2
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

LIBERO-Pro original paper

Xueyang Zhou and coauthors · Publication date not disclosed · Source accessed 2026-09-28

Reading results

Comparisons should retain perturbation type, severity, initialization files and checkpoint. Its independently named benchmark must remain distinct from LIBERO-Plus despite overlapping research questions.

Source contextPrimary specReviewed
Sources 2
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

LIBERO-Pro original paper

Xueyang Zhou and coauthors · Publication date not disclosed · Source accessed 2026-09-28

Methodology and reuse limits

The MIT code label does not automatically settle the terms of all downloaded datasets and assets.

Source contextPrimary specReviewed
Sources 2
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

LIBERO-Pro original paper

Xueyang Zhou and coauthors · Publication date not disclosed · Source accessed 2026-09-28

Evaluation protocol

Exact version / scope
LIBERO-Pro original robustness release
Primary specReviewed
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Environment
simulation
Primary specReviewed
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Metric definition
Task success rate under controlled perturbations
Primary specReviewed
Sources 1
LIBERO-Pro original paper

Xueyang Zhou and coauthors · Publication date not disclosed · Source accessed 2026-09-28

Task scope
Not publicly disclosed
Embodiment
Original LIBERO runtime and robot setup
Primary specReviewed
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Access & reuse

Access model
Public research documentation and evaluation resources
Primary specReviewed
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

License
Not publicly disclosed

Additional disclosed fields

Category
Robot evaluation benchmark
Primary specReviewed
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Reported benchmark results

Context before scores. Results from different benchmarks are not directly comparable. A simulation result does not establish real-world reliability, safety or commercial availability.
No result meets our complete revision and methodology requirements for this record yet. Inspect the original benchmark documentation before comparing published scores.

What this evidence does not establish

  • The MIT code label does not automatically settle the terms of all downloaded datasets and assets.

Relationships & deployments

benchmarkLIBERO ↗benchmarkLIBERO-Plus ↗modelOpenVLA ↗

Related reading is an editorial crosslink. Sourced connections describe relationships reported in the cited material. A link to a versioned profile does not establish compatibility with that version unless the connection note explicitly identifies it.

uses
LIBERO-Pro → LIBERO
Sources 1
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Connection reviewed 2026-09-28

Record history & verified changes

A research review records when we checked a source. It does not mark a product launch or a new deployment.

Initial reviewed record. No subsequent field change has been recorded.

Inspect the evidence

Sources & evidence

md-liberopro
Zxy-MLlab/LIBERO-PRO official repository

Zxy-MLlab · Repository · Publication date not disclosed · Source accessed 2026-09-28

License: MIT code. Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Referenced by 2 records: LIBERO · LIBERO-Pro

md-liberopro-paper
LIBERO-Pro original paper

Xueyang Zhou and coauthors · Paper · Publication date not disclosed · Source accessed 2026-09-28

Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Referenced by 1 record: LIBERO-Pro