# Robotic Manipulation on LIBERO-Pro (test)

Source: [Robotic Manipulation on LIBERO-Pro (test)](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-01T08:07:20.258Z

Evaluation of robotic manipulation performance specifically on the test split of the LIBERO-Pro dataset, reporting success rates across Semantic, Object, Position, and Task dimensions.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Robotic Manipulation |
| Dataset (including any stated split) | LIBERO-Pro (test) |
| Metric | Semantic SR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Semantic SR](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test.md?metric=Semantic%20SR>): Higher is better; unit: PERCENT.

- [Object SR](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test.md?metric=Object%20SR>): Higher is better; unit: PERCENT.

- [Position SR](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test.md?metric=Position%20SR>): Higher is better; unit: PERCENT.

- [Task SR](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test.md?metric=Task%20SR>): Higher is better; unit: PERCENT.

- [Average SR](<https://www.sota2.com/research/sota/robotic-manipulation-on-libero-pro-test.md?metric=Average%20SR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Semantic SR | Result date | Report paper |
| --- | --- | --- | --- |
| OpenVLA | 97.2 | Not recorded | 69f433b755a3c32af89fd280 |
| ABot-M0 | 97.1 | Not recorded | 69f433b755a3c32af89fd280 |
| PRTS | 97 | Not recorded | 69f433b755a3c32af89fd280 |
| π0.5 | 95.8 | Not recorded | 69f433b755a3c32af89fd280 |
| Qwen3-VL-PI | 95.5 | Not recorded | 69f433b755a3c32af89fd280 |
| π0 | 90.5 | Not recorded | 69f433b755a3c32af89fd280 |

### OpenVLA

Semantic SR: 97.2. Result ID: 69f45f2c47f34ce924da2c97.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a36.md>)

[Implementation](<https://openvla.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ABot-M0

Semantic SR: 97.1. Result ID: 69f45f2c47f34ce924da2c99.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eb026c97a0b3e3b5e6786.md>)

[Implementation](<https://github.com/amap-cvlab/ABot-Manipulation>)

Recorded evaluation configuration: {"batch size":"32","steps":"30K"}. This record does not assert independent reproduction.

### PRTS

Semantic SR: 97. Result ID: 69f45f2c47f34ce924da2c9c.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

Recorded evaluation configuration: {"batch size":"32","steps":"30K"}. This record does not assert independent reproduction.

### π0.5

Semantic SR: 95.8. Result ID: 69f45f2c47f34ce924da2c9b.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa783a1e209131cea774f1.md>)

Recorded evaluation configuration: {"batch size":"256","steps":"30K"}. This record does not assert independent reproduction.

### Qwen3-VL-PI

Semantic SR: 95.5. Result ID: 69f45f2c47f34ce924da2c98.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e11f7d0172140ec75af3.md>)

Recorded evaluation configuration: {"batch size":"32","steps":"30K"}. This record does not assert independent reproduction.

### π0

Semantic SR: 90.5. Result ID: 69f45f2c47f34ce924da2c9a.

[Reporting paper](<https://www.sota2.com/research/paper/69f433b755a3c32af89fd280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"batch size":"32","steps":"30K"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.