---
title: Xiaomi-Robotics-1-VLABench
canonical_url: "https://www.modelscope.cn/models/XiaomiRobotics/Xiaomi-Robotics-1-VLABench"
md_url: "https://www.modelscope.cn/models/XiaomiRobotics/Xiaomi-Robotics-1-VLABench.md"
repository: XiaomiRobotics/Xiaomi-Robotics-1-VLABench
last_updated: 2026-08-14
license: apache-2.0
pipeline_tag: robotics
tasks:
  - robotics
model_type:
  - mibot
architectures:
  - MiBoTForActionGeneration
parameters: 5.1B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 29
stars: 0
---

# Xiaomi-Robotics-1-VLABench

> Xiaomi-Robotics-1-VLABench - XiaomiRobotics 在 ModelScope 开源的模型。Xiaomi-Robotics-1-VLABench

XiaomiRobotics/Xiaomi-Robotics-1-VLABench 是 ModelScope 魔搭社区上的 5.1B 参数robotics模型，采用 apache-2.0 许可。

- **Repository**: XiaomiRobotics/Xiaomi-Robotics-1-VLABench
- **License**: apache-2.0
- **Tasks**: robotics
- **Parameters**: 5.1B
- **Downloads**: 29
- **Stars**: 0
- **Last updated**: 2026-08-14

Source: https://www.modelscope.cn/models/XiaomiRobotics/Xiaomi-Robotics-1-VLABench

---

# Xiaomi-Robotics-1-VLABench

This repository contains the Hugging Face checkpoint used by **Xiaomi-Robotics-1** for **VLABench** evaluation. It includes the model weights, custom Transformers model and processor code, tokenizer files, and VLABench action normalization statistics.

## Requirements

The reference environment uses:

```text
Python 3.11
PyTorch 2.8.0
Transformers 4.57.1
FlashAttention 2
```

The custom model and processor must be loaded with `trust_remote_code=True`.

For the VLABench simulation environment, follow the companion source repository at `eval_vlabench/README.md`. The evaluation client uses a separate `vlabench` conda environment with Python 3.10 and the pinned MuJoCo / `dm_control` dependencies described there.

## Loading

```python
import torch
from transformers import AutoModel, AutoProcessor

model_id = "XiaomiRobotics/Xiaomi-Robotics-1-VLABench"

processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
    use_fast=False,
)

model = AutoModel.from_pretrained(
    model_id,
    trust_remote_code=True,
    attn_implementation="flash_attention_2",
    dtype=torch.bfloat16,
).cuda()
```

For reproducible multi-GPU evaluation, use the standard multi-server launcher in the companion **Xiaomi-Robotics-1** source repository.

## VLABench Evaluation

Use the companion Xiaomi-Robotics-1 source repository and follow `eval_vlabench/README.md`.

The released processor supports the `vlabench_choice` robot key.

### Action interface

```text
raw action shape:        [10, 60]
executable dimensions:  first 7 dimensions
position delta:          dims 0:3
Euler rotation delta:    dims 3:6
gripper:                 dim 6
action chunk size:       10
replanning interval:     5 steps
```

### Reference evaluation configuration

```text
benchmark:               VLABench
tracks:                  5
tasks per track:         10
episodes per task:       50
total task-track entries: 50
total episodes:          2500
robot type:              vlabench_choice
state dimension:         60
action dimension:        7
action chunk size:       10
replanning steps:        5
CoT during evaluation:   disabled
```

The five evaluated tracks are:

- `track_1_in_distribution`
- `track_2_cross_category`
- `track_3_common_sense`
- `track_4_semantic_instruction`
- `track_6_unseen_texture`

The ten evaluated tasks are:

- `add_condiment`
- `insert_flower`
- `select_book`
- `select_chemistry_tube`
- `select_drink`
- `select_fruit`
- `select_mahjong`
- `select_painting`
- `select_poker`
- `select_toy`

Reported metrics are **success rate (SR)**, **intention score (IS)**, and **progress score (PS)**.

## Reference Results

### Overall

| Metric | Value |
| --- | ---: |
| Success Rate (SR) | **59.1%** |
| Intention Score (IS) | **69.9%** |
| Progress Score (PS) | **70.3%** |

Track values are macro averages across the ten tasks in that track. The overall result is the macro average across all 50 task-track entries and is not episode-weighted.

### Results by track

| Track | SR | IS | PS |
| --- | ---: | ---: | ---: |
| `track_1_in_distribution` | **75.6%** | **79.8%** | **85.0%** |
| `track_2_cross_category` | **53.0%** | **66.4%** | **66.6%** |
| `track_3_common_sense` | **48.4%** | **58.2%** | **58.3%** |
| `track_4_semantic_instruction` | **55.8%** | **70.2%** | **66.8%** |
| `track_6_unseen_texture` | **62.6%** | **74.8%** | **74.9%** |
| **Overall** | **59.1%** | **69.9%** | **70.3%** |

### Average by task across all tracks

| Task | SR | IS | PS |
| --- | ---: | ---: | ---: |
| `add_condiment` | 40.4% | 84.0% | 60.1% |
| `insert_flower` | 40.4% | 98.8% | 69.2% |
| `select_book` | 56.4% | 75.6% | 66.0% |
| `select_chemistry_tube` | 80.4% | 0.4% | 85.6% |
| `select_drink` | 49.2% | 90.4% | 65.2% |
| `select_fruit` | 60.8% | 94.0% | 75.8% |
| `select_mahjong` | 70.4% | 87.6% | 73.6% |
| `select_painting` | 63.2% | 82.8% | 63.2% |
| `select_poker` | 66.8% | 75.2% | 67.1% |
| `select_toy` | 62.8% | 10.0% | 77.4% |


## License

Apache License 2.0. See `LICENSE`.

## Citation

```bibtex
@article{team2026xiaomi,
  title={Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories},
  author={Team, Xiaomi Robotics and Guo, Jun and Jin, Piaopiao and Li, Jason and Li, Peiyan and Li, Yingyan and Liu, Futeng and Peng, Wanli and Qin, Optimus and Su, Yifei and others},
  journal={arXiv preprint arXiv:2607.15330},
  year={2026}
}
```