# Robot Manipulation on ALOHA (in-domain)

Source: [Robot Manipulation on ALOHA (in-domain)](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain>)

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

Data updated: 2026-05-29T11:41:10.556Z

Evaluation of Robot Manipulation performance on the in-domain subset of the ALOHA dataset, focusing on success rates for specific tasks including Pick and Place, Table Cleaning, Bowl Stacking, and Towel Folding.

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 | Robot Manipulation |
| Dataset (including any stated split) | ALOHA (in-domain) |
| Metric | Pick and Place Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Pick and Place Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Pick%20and%20Place%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Table Cleaning Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Table%20Cleaning%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Bowl Stacking Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Bowl%20Stacking%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Bowl Pick & Place Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Bowl%20Pick%20%26%20Place%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Towel Folding Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Towel%20Folding%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Fine-grained Manipulation Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Fine-grained%20Manipulation%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/robot-manipulation-on-aloha-in-domain.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pick and Place Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-VLA-alohaw/ pretrain | 96.2 | Not recorded | 6a191dbedbd7150506f82a0f |
| π0.5 | 73.1 | Not recorded | 6a191dbedbd7150506f82a0f |
| GR00T N1.6 | 30.8 | Not recorded | 6a191dbedbd7150506f82a0f |
| Qwen-VLA-alohaw/o pretrain | 30.8 | Not recorded | 6a191dbedbd7150506f82a0f |

### Qwen-VLA-alohaw/ pretrain

Pick and Place Success Rate: 96.2. Result ID: 6a197b4cfbc373592c14d34b.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

Recorded evaluation configuration: {"Pre-training strategy":"fine-tuned from Qwen-VLA-Base"}. This record does not assert independent reproduction.

### π0.5

Pick and Place Success Rate: 73.1. Result ID: 6a197b4cfbc373592c14d349.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

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

### GR00T N1.6

Pick and Place Success Rate: 30.8. Result ID: 6a197b4cfbc373592c14d348.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779a1e209131cea74489.md>)

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

### Qwen-VLA-alohaw/o pretrain

Pick and Place Success Rate: 30.8. Result ID: 6a197b4cfbc373592c14d34a.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dbedbd7150506f82a0f.md>)

Recorded evaluation configuration: {"Pre-training strategy":"trained from scratch"}. This record does not assert independent reproduction.

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