# Object Placement on PARSEC novel environment categories

Source: [Object Placement on PARSEC novel environment categories](<https://www.sota2.com/research/sota/object-placement-on-parsec-novel-environment-categories>)

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

Data updated: 2026-06-17T06:44:58.298Z

Evaluation of the model's ability to perform the Object Placement task using the PARSEC novel environment categories dataset, measured by U-1D, U-2D, Non-Uniform, and Average success criteria.

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 | Object placement |
| Dataset (including any stated split) | PARSEC novel environment categories |
| Metric | U-1D Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [U-1D Success Rate](<https://www.sota2.com/research/sota/object-placement-on-parsec-novel-environment-categories.md?metric=U-1D%20Success%20Rate>): Higher is better; unit: PERCENT.

- [U-2D Success Rate](<https://www.sota2.com/research/sota/object-placement-on-parsec-novel-environment-categories.md?metric=U-2D%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Non-Uniform Success Rate](<https://www.sota2.com/research/sota/object-placement-on-parsec-novel-environment-categories.md?metric=Non-Uniform%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/object-placement-on-parsec-novel-environment-categories.md?metric=Average%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | U-1D Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| APOLLO | 56 | Not recorded | 6a322a2fd33dfb23e783ebce |
| PEM | 56 | Not recorded | 6a322a2fd33dfb23e783ebce |
| CSLM | 54 | Not recorded | 6a322a2fd33dfb23e783ebce |
| APRICOT-NI | 50 | Not recorded | 6a322a2fd33dfb23e783ebce |
| TidyBot-Random | 46 | Not recorded | 6a322a2fd33dfb23e783ebce |

### APOLLO

U-1D Success Rate: 56. Result ID: 6a324251fbc373592c2f23b3.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

Recorded evaluation configuration: {"Components":"PEM + CSLM assistance","LLM Backend":"GPT-4"}. This record does not assert independent reproduction.

### PEM

U-1D Success Rate: 56. Result ID: 6a324251fbc373592c2f23b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

Recorded evaluation configuration: {"Mode":"Ablation (PEM-only)"}. This record does not assert independent reproduction.

### CSLM

U-1D Success Rate: 54. Result ID: 6a324251fbc373592c2f23b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79af1e209131cea7edde.md>)

Recorded evaluation configuration: {"LLM Backend":"GPT-4"}. This record does not assert independent reproduction.

### APRICOT-NI

U-1D Success Rate: 50. Result ID: 6a324251fbc373592c2f23b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755b1e209131cea676bc.md>)

Recorded evaluation configuration: {"Mode":"Non-Interactive"}. This record does not assert independent reproduction.

### TidyBot-Random

U-1D Success Rate: 46. Result ID: 6a324251fbc373592c2f23b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a2fd33dfb23e783ebce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5013a.md>)

Recorded evaluation configuration: {"Mode":"Single-example rule induction","Variant":"Randomly samples demonstration"}. This record does not assert independent reproduction.

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