Xiaomi-Robotics-0

Open weightsXiaomi

3 of 6 axes published · values checked against their primary sources on 23 Oct 2026

1. Success

   Does it do the trained task? (% of trials, trained setup)

   98.1%

   SimulationGrade B · Paper or report with method (rubric or error bars)LIBERO clean

   Highest clean LIBERO score of the six models tested, simulation.

   Source: IndustrialVLA-Bench, arXiv 2609.25562 · Table 2

2. Robustness

   Does it survive the cell drifting? (% under the perturbation set)

   73.9%

   SimulationGrade B · Paper or report with method (rubric or error bars)LIBERO-Plus

   Non-language perturbations, simulation.

   Source: IndustrialVLA-Bench, arXiv 2609.25562 · Table 3

3. Instruction

   Does rewording the instruction break it? (% under paraphrase)

   75.7%

   SimulationGrade B · Paper or report with method (rubric or error bars)LIBERO-Para

   Paraphrased instructions, 22.4 points below clean.

   Source: IndustrialVLA-Bench, arXiv 2609.25562 · Table 4

4. Recovery

   Does it fix its own mistakes? (% of injected failures recovered)

   Owed

   Not reported.

5. Speed

   Is it as fast as a trained person? (human cycle time ÷ robot cycle time)

   Owed

   No human comparison. 25.4 ms per policy call (Table 5).

   Checked: IndustrialVLA-Bench, arXiv 2609.25562

6. Interventions

   How often does a person step in? (per 1,000 cycles)

   Owed

   Not reported.