# 2D image-based manipulation on Adroit & DexArt

Source: [2D image-based manipulation on Adroit & DexArt](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart>)

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

Data updated: 2026-03-16T08:49:04.670Z

Evaluation of 2D image-based manipulation performance across the Adroit and DexArt datasets, reporting success rates for individual tasks (Door, Hammer, Pen, etc.) and the overall average.

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 | 2D image-based manipulation |
| Dataset (including any stated split) | Adroit & DexArt 2D image-based manipulation |
| Metric | Door Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Door Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Door%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Hammer Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Hammer%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Pen Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Pen%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Bucket Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Bucket%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Faucet Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Faucet%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Laptop Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Laptop%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Toilet Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Toilet%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/2d-image-based-manipulation-on-adroit-and-dexart.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Door Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| OFP (Ours) | 68.3 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| FM Policy | 63.7 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| FM Policy | 61.3 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| OneDP | 53.3 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| DP | 51.7 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| MP1 | 49.3 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| CP | 46.3 | Not recorded | 69b78e9c0636e5bf4afbdca1 |
| DP | 44.7 | Not recorded | 69b78e9c0636e5bf4afbdca1 |

### OFP (Ours)

Door Success Rate: 68.3. Result ID: 69b7c37b47f34ce9249f7a1f.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

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

### FM Policy

Door Success Rate: 63.7. Result ID: 69b7c37b47f34ce9249f7a1a.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76c61e209131cea6ef37.md>)

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### FM Policy

Door Success Rate: 61.3. Result ID: 69b7c37b47f34ce9249f7a1b.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76c61e209131cea6ef37.md>)

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

### OneDP

Door Success Rate: 53.3. Result ID: 69b7c37b47f34ce9249f7a1d.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a8f.md>)

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

### DP

Door Success Rate: 51.7. Result ID: 69b7c37b47f34ce9249f7a18.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

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

Recorded evaluation configuration: {"NFE":"100"}. This record does not assert independent reproduction.

### MP1

Door Success Rate: 49.3. Result ID: 69b7c37b47f34ce9249f7a1e.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba67.md>)

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

### CP

Door Success Rate: 46.3. Result ID: 69b7c37b47f34ce9249f7a1c.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e91e209131cea5edc9.md>)

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

### DP

Door Success Rate: 44.7. Result ID: 69b7c37b47f34ce9249f7a19.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9c0636e5bf4afbdca1.md>)

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

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

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