# Chart-to-Code Generation on ChartMimic (Customized/Direct Metrics)

Source: [Chart-to-Code Generation on ChartMimic (Customized/Direct Metrics)](<https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-customized-direct-metrics>)

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

Data updated: 2026-04-15T07:22:12.265Z

Evaluation of models generating structured code from chart inputs using the ChartMimic dataset, specifically measured using Customized (Low/High) and Direct (Low/High) scoring metrics.

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 | Chart-to-Code Generation |
| Dataset (including any stated split) | ChartMimic |
| Metric | Customized Score (Low) |
| 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

- [Customized Score (Low)](<https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-customized-direct-metrics.md?metric=Customized%20Score%20(Low)>): Higher is better; unit: PERCENT.

- [Customized Score (High)](<https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-customized-direct-metrics.md?metric=Customized%20Score%20(High)>): Higher is better; unit: PERCENT.

- [Direct Score (Low)](<https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-customized-direct-metrics.md?metric=Direct%20Score%20(Low)>): Higher is better; unit: PERCENT.

- [Direct Score (High)](<https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-customized-direct-metrics.md?metric=Direct%20Score%20(High)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Customized Score (Low) | Result date | Report paper |
| --- | --- | --- | --- |
| JANUSCODERV-8B | 66.68 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| JANUSCODERV-7B | 64.72 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| GPT-4o | 59.4 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| InternVL3-8B | 51.88 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| InternVL3.5-8B | 51.56 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| Qwen2.5-VL-7B-Ins | 51.07 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| MiniCPM-V-2-6 | 27.53 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| Llama-3.2-11B-Vision-Ins | 18.87 | Not recorded | 69004e143ef7ccd74e5e2e9e |

### JANUSCODERV-8B

Customized Score (Low): 66.68. Result ID: 69df3c5f47f34ce924c79b5f.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### JANUSCODERV-7B

Customized Score (Low): 64.72. Result ID: 69df3c5f47f34ce924c79b5e.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### GPT-4o

Customized Score (Low): 59.4. Result ID: 69df3c5f47f34ce924c79b60.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"License":"Proprietary"}. This record does not assert independent reproduction.

### InternVL3-8B

Customized Score (Low): 51.88. Result ID: 69df3c5f47f34ce924c79b5a.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### InternVL3.5-8B

Customized Score (Low): 51.56. Result ID: 69df3c5f47f34ce924c79b5b.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Ins

Customized Score (Low): 51.07. Result ID: 69df3c5f47f34ce924c79b59.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### MiniCPM-V-2-6

Customized Score (Low): 27.53. Result ID: 69df3c5f47f34ce924c79b5c.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### Llama-3.2-11B-Vision-Ins

Customized Score (Low): 18.87. Result ID: 69df3c5f47f34ce924c79b5d.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

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