# Flowchart-to-Mermaid translation on FLOWVQA subset

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

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

Data updated: 2026-02-26T06:02:44.116Z

Evaluation of model performance translating flowchart images into Mermaid syntax using the FLOWVQA subset, measured by structural accuracy metrics (SA, FA, SV, SF, C).

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 translation |
| Dataset (including any stated split) | FLOWVQA subset |
| Metric | SA |
| 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

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

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

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

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

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

## Recorded results

| Method | SA | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-2.5-Flash | 98.8 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4.1-mini | 98.4 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4.1 | 97.4 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4o | 95.4 | Not recorded | 692fc45cd6b0dd33429334f6 |
| GPT-4o-mini | 83.1 | Not recorded | 692fc45cd6b0dd33429334f6 |

### Gemini-2.5-Flash

SA: 98.8. Result ID: 699632ce5698665ec474e95b.

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

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

Recorded evaluation configuration: {"Framework":"Flowchart2Mermaid"}. This record does not assert independent reproduction.

### GPT-4.1-mini

SA: 98.4. Result ID: 699632ce5698665ec474e958.

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

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

Recorded evaluation configuration: {"Framework":"Flowchart2Mermaid"}. This record does not assert independent reproduction.

### GPT-4.1

SA: 97.4. Result ID: 699632ce5698665ec474e957.

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

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

Recorded evaluation configuration: {"Framework":"Flowchart2Mermaid"}. This record does not assert independent reproduction.

### GPT-4o

SA: 95.4. Result ID: 699632ce5698665ec474e959.

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

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

Recorded evaluation configuration: {"Framework":"Flowchart2Mermaid"}. This record does not assert independent reproduction.

### GPT-4o-mini

SA: 83.1. Result ID: 699632ce5698665ec474e95a.

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

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

Recorded evaluation configuration: {"Framework":"Flowchart2Mermaid"}. This record does not assert independent reproduction.

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