# Assembly Graph Extraction (Set Matching) on Assembly Manual Dataset (85 steps) (test)

Source: [Assembly Graph Extraction (Set Matching) on Assembly Manual Dataset (85 steps) (test)](<https://www.sota2.com/research/sota/assembly-graph-extraction-set-matching-on-assembly-manual-dataset-85-steps-test>)

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

Data updated: 2026-03-20T08:13:09.989Z

Evaluation of Assembly Graph Extraction performance using Set Matching on the test split of the Assembly Manual Dataset (85 steps).

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 | Assembly Graph Extraction (Set Matching) |
| Dataset (including any stated split) | Assembly Manual Dataset (85 steps) (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/assembly-graph-extraction-set-matching-on-assembly-manual-dataset-85-steps-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Success Rate](<https://www.sota2.com/research/sota/assembly-graph-extraction-set-matching-on-assembly-manual-dataset-85-steps-test.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Manual2Skill++ | 86.06 | Not recorded | 68fa7c531e209131cea8d907 |
| Manual2Skill++ | 82.68 | Not recorded | 68fa7c531e209131cea8d907 |
| Manual2Skill++ | 75.82 | Not recorded | 68fa7c531e209131cea8d907 |
| Manual2Skill++ | 74.55 | Not recorded | 68fa7c531e209131cea8d907 |
| Random Sampling | 53.51 | Not recorded | 68fa7c531e209131cea8d907 |
| Geometric Matching | 0.02 | Not recorded | 68fa7c531e209131cea8d907 |

### Manual2Skill++

F1 Score: 86.06. Result ID: 69bd00c047f34ce924a6e746.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Model backbone":"Gemini-2.5-Pro","Manual completeness":"Complete"}. This record does not assert independent reproduction.

### Manual2Skill++

F1 Score: 82.68. Result ID: 69bd00c047f34ce924a6e745.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Model backbone":"Gemini-2.5-Pro","Manual completeness":"Incomplete"}. This record does not assert independent reproduction.

### Manual2Skill++

F1 Score: 75.82. Result ID: 69bd00c047f34ce924a6e743.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Model backbone":"GPT-4o","Manual completeness":"Incomplete"}. This record does not assert independent reproduction.

### Manual2Skill++

F1 Score: 74.55. Result ID: 69bd00c047f34ce924a6e744.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Model backbone":"GPT-4o","Manual completeness":"Complete"}. This record does not assert independent reproduction.

### Random Sampling

F1 Score: 53.51. Result ID: 69bd00c047f34ce924a6e742.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Strategy":"Random pair generation"}. This record does not assert independent reproduction.

### Geometric Matching

F1 Score: 0.02. Result ID: 69bd00c047f34ce924a6e741.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c531e209131cea8d907.md>)

Recorded evaluation configuration: {"Description":"OpenCV-based heuristic"}. This record does not assert independent reproduction.

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