# Robotic Manipulation on Real-world household tasks 20 demonstrations (test)

Source: [Robotic Manipulation on Real-world household tasks 20 demonstrations (test)](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test>)

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

Data updated: 2026-02-26T05:39:25.079Z

Evaluation of robotic manipulation performance across 5 specific household tasks derived from the 20 demonstrations dataset, measured by individual task success rates and overall average success rate.

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) | Real-world household tasks 20 demonstrations (test) |
| Metric | Closing Drawer Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Closing Drawer Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Closing%20Drawer%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Putting Mask in Dresser Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Putting%20Mask%20in%20Dresser%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Putting Lettuce in Pan Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Putting%20Lettuce%20in%20Pan%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Pushing Mug to Goal Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Pushing%20Mug%20to%20Goal%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Folding Towel Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Folding%20Towel%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/robotic-manipulation-on-real-world-household-tasks-20-demonstrations-test.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Closing Drawer Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| R3M | 0.8 | Not recorded | 68fa6e011e209131cea3d5b4 |
| CLIP | 0.7 | Not recorded | 68fa6e011e209131cea3d5b4 |

### R3M

Closing Drawer Success Rate: 0.8. Result ID: 698ff2c83a6c314849fd0108.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e011e209131cea3d5b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e011e209131cea3d5b4.md>)

[Implementation](<https://github.com/facebookresearch/r3m>)

Recorded evaluation configuration: {"Trials":"10","Demonstrations":"20 per task","Protocol":"Behavior cloning","Robot":"Franka Emika Panda","Environment":"Real-world apartment"}. This record does not assert independent reproduction.

### CLIP

Closing Drawer Success Rate: 0.7. Result ID: 698ff2c83a6c314849fd0109.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e011e209131cea3d5b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Trials":"10","Demonstrations":"20 per task","Protocol":"Behavior cloning","Robot":"Franka Emika Panda","Environment":"Real-world apartment"}. This record does not assert independent reproduction.

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