LIBERO-Plus OOD robustnessBrowse 296

LIBERO-Plus OOD robustness

Can the model plan, use tools, and finish a multi-step task?

Version not specifiedExact reported variant
Agents6 ranked models7 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

6
RankModelBest scoreBest reported setting
1Qwen-RobotManipQwen99.9%Reported configurationQwen report2 values · 1 reportJun 15, 2026 · source
2StarVLAExternal baseline95.7%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
3π₀.₅Physical Intelligence94.1%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
4ABot-M0External baseline91.6%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
5Being-H0.7External baseline90.0%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
6π₀Physical Intelligence81.4%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model plan, use tools, and finish a multi-step task?

Agentic execution across tools, environments, or long-running workflows. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

LIBERO-Plus evaluates camera, robot, language, lighting, background, noise, and layout perturbations; total is the source's aggregate.

Method / source
LIBERO-Plus OOD robustness · Benchmaxxer