# Flowchart to Mermaid code translation on FLOWVQA (test)

Source: [Flowchart to Mermaid code translation on FLOWVQA (test)](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test>)

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

Data updated: 2026-02-26T05:42:05.477Z

Evaluation of model performance translating flowcharts into Mermaid code using the test split of the FLOWVQA dataset, typically measured using entity/relation F1 scores and Cosine Similarity.

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 | Flowchart to Mermaid code translation |
| Dataset (including any stated split) | FLOWVQA (test) |
| Metric | Entity Precision |
| 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

- [Entity Precision](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Entity%20Precision>): Higher is better; unit: PERCENT.

- [Entity Recall](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Entity%20Recall>): Higher is better; unit: PERCENT.

- [Entity F1 Score](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Entity%20F1%20Score>): Higher is better; unit: PERCENT.

- [Relation Precision](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Relation%20Precision>): Higher is better; unit: PERCENT.

- [Relation Recall](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Relation%20Recall>): Higher is better; unit: PERCENT.

- [Relation F1 Score](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Relation%20F1%20Score>): Higher is better; unit: PERCENT.

- [Cosine Similarity](<https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test.md?metric=Cosine%20Similarity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Entity Precision | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4.1-mini | 98.6 | Not recorded | 692fc45cd6b0dd33429334f6 |
| Gemini-2.5-Flash | 98.6 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4.1 | 97.5 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4o | 94.9 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4o-mini | 82.7 | Not recorded | 692fc45cd6b0dd33429334f6 |

### GPT-4.1-mini

Entity Precision: 98.6. Result ID: 699632ce5698665ec474e95d.

[Reporting paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini-2.5-Flash

Entity Precision: 98.6. Result ID: 699632ce5698665ec474e960.

[Reporting paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4.1

Entity Precision: 97.5. Result ID: 699632ce5698665ec474e95c.

[Reporting paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o

Entity Precision: 94.9. Result ID: 699632ce5698665ec474e95e.

[Reporting paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o-mini

Entity Precision: 82.7. Result ID: 699632ce5698665ec474e95f.

[Reporting paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc45cd6b0dd33429334f6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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