# Robotic Manipulation on MetaWorld (Difficulty Scores)

Source: [Robotic Manipulation on MetaWorld (Difficulty Scores)](<https://www.sota2.com/research/sota/robotic-manipulation-on-metaworld-difficulty-scores>)

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

Data updated: 2026-02-26T06:04:05.171Z

Evaluation of robotic manipulation performance on the MetaWorld benchmark, reporting scores broken down by difficulty levels: Easy, Medium, Hard, and Very Hard.

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) | MetaWorld |
| Metric | Score (Easy) |
| Unit | SCALAR |
| 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

- [Score (Easy)](<https://www.sota2.com/research/sota/robotic-manipulation-on-metaworld-difficulty-scores.md?metric=Score%20(Easy)>): Higher is better; unit: SCALAR.

- [Score (Medium)](<https://www.sota2.com/research/sota/robotic-manipulation-on-metaworld-difficulty-scores.md?metric=Score%20(Medium)>): Higher is better; unit: SCALAR.

- [Score (Hard)](<https://www.sota2.com/research/sota/robotic-manipulation-on-metaworld-difficulty-scores.md?metric=Score%20(Hard)>): Higher is better; unit: SCALAR.

- [Score (Very Hard)](<https://www.sota2.com/research/sota/robotic-manipulation-on-metaworld-difficulty-scores.md?metric=Score%20(Very%20Hard)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| FreqPolicy | 90.6 | Not recorded | 68fa79581e209131cea7d2f9 |
| FlowPolicy\* | 89.6 | Not recorded | 68fa79581e209131cea7d2f9 |
| DP3\* | 89 | Not recorded | 68fa79581e209131cea7d2f9 |
| SDM | 86.5 | Not recorded | 68fa79581e209131cea7d2f9 |
| DP | 83.6 | Not recorded | 68fa79581e209131cea7d2f9 |
| ManiCM | 83.6 | Not recorded | 68fa79581e209131cea7d2f9 |

### FreqPolicy

Score (Easy): 90.6. Result ID: 699ae26d5698665ec47264d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

Recorded evaluation configuration: {"NFE":1}. This record does not assert independent reproduction.

### FlowPolicy\*

Score (Easy): 89.6. Result ID: 699ae26d5698665ec47264d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76381e209131cea6beff.md>)

Recorded evaluation configuration: {"NFE":1}. This record does not assert independent reproduction.

### DP3\*

Score (Easy): 89. Result ID: 699ae26d5698665ec47264d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c76.md>)

[Implementation](<https://github.com/YanjieZe/3D-Diffusion-Policy>)

Recorded evaluation configuration: {"NFE":10}. This record does not assert independent reproduction.

### SDM

Score (Easy): 86.5. Result ID: 699ae26d5698665ec47264d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76461e209131cea6c1a6.md>)

Recorded evaluation configuration: {"NFE":1}. This record does not assert independent reproduction.

### DP

Score (Easy): 83.6. Result ID: 699ae26d5698665ec47264cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72841e209131cea56f68.md>)

Recorded evaluation configuration: {"NFE":10}. This record does not assert independent reproduction.

### ManiCM

Score (Easy): 83.6. Result ID: 699ae26d5698665ec47264d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79581e209131cea7d2f9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1f1e209131cea86ad1.md>)

Recorded evaluation configuration: {"NFE":1}. This record does not assert independent reproduction.

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