# Image-to-TikZ on MathVista GPS

Source: [Image-to-TikZ on MathVista GPS](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps>)

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

Data updated: 2026-03-25T13:06:23.716Z

Evaluation of model performance on generating TikZ code from images using the MathVista GPS dataset, assessed using metrics like CLIP, SigLip, and DINO.

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 | Image-to-TikZ |
| Dataset (including any stated split) | MathVista GPS |
| Metric | CLIP Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [CLIP Score](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps.md?metric=CLIP%20Score>): Higher is better; unit: PERCENT.

- [SigLip Score](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps.md?metric=SigLip%20Score>): Higher is better; unit: PERCENT.

- [DINO Score](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps.md?metric=DINO%20Score>): Higher is better; unit: PERCENT.

- [FID](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps.md?metric=FID>): Lower is better; unit: SCALAR.

- [CSR](<https://www.sota2.com/research/sota/image-to-tikz-on-mathvista-gps.md?metric=CSR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CLIP Score | Result date | Report paper |
| --- | --- | --- | --- |
| GeoTikzBridge-Base-38B | 91.5 | Not recorded | 69c36c000636e5bf4afc6464 |
| GeoTikzBridge-Base-38B | 91.5 | Not recorded | 69c36c000636e5bf4afc6464 |
| GeoTikzBridge-Base-8B | 89.5 | Not recorded | 69c36c000636e5bf4afc6464 |
| GeoTikzBridge-Base-8B | 89.5 | Not recorded | 69c36c000636e5bf4afc6464 |
| FigCodifier | 88.4 | Not recorded | 69c36c000636e5bf4afc6464 |
| FigCodifier-8B | 88.4 | Not recorded | 69c36c000636e5bf4afc6464 |
| InternVL3-78B | 86 | Not recorded | 69c36c000636e5bf4afc6464 |
| Qwen2.5-VL-72B | 85.8 | Not recorded | 69c36c000636e5bf4afc6464 |
| Qwen2.5-VL-72B | 85.8 | Not recorded | 69c36c000636e5bf4afc6464 |
| Qwen2.5-VL-32B | 83.2 | Not recorded | 69c36c000636e5bf4afc6464 |
| Qwen3-VL-30B | 80.2 | Not recorded | 69c36c000636e5bf4afc6464 |
| Qwen3-VL-30B-A3B | 80.2 | Not recorded | 69c36c000636e5bf4afc6464 |
| InternVL3.5-38B | 78.6 | Not recorded | 69c36c000636e5bf4afc6464 |
| InternVL3.5-38B | 78.6 | Not recorded | 69c36c000636e5bf4afc6464 |
| GLM4.5V-106B | 76.9 | Not recorded | 69c36c000636e5bf4afc6464 |
| GLM4.5-V-106B-A12B | 76.9 | Not recorded | 69c36c000636e5bf4afc6464 |

### GeoTikzBridge-Base-38B

CLIP Score: 91.5. Result ID: 69c3dd8147f34ce924ad40fe.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"parameter\_size":"38B"}. This record does not assert independent reproduction.

### GeoTikzBridge-Base-38B

CLIP Score: 91.5. Result ID: 69c3dd8147f34ce924ad4110.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"Parameters":"38B"}. This record does not assert independent reproduction.

### GeoTikzBridge-Base-8B

CLIP Score: 89.5. Result ID: 69c3dd8147f34ce924ad40fd.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"parameter\_size":"8B"}. This record does not assert independent reproduction.

### GeoTikzBridge-Base-8B

CLIP Score: 89.5. Result ID: 69c3dd8147f34ce924ad410f.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction.

### FigCodifier

CLIP Score: 88.4. Result ID: 69c3dd8147f34ce924ad40fc.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789d1e209131cea795a9.md>)

[Implementation](<https://github.com/mathllm/MathCoder>)

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

### FigCodifier-8B

CLIP Score: 88.4. Result ID: 69c3dd8147f34ce924ad410e.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789d1e209131cea795a9.md>)

[Implementation](<https://github.com/mathllm/MathCoder>)

Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction.

### InternVL3-78B

CLIP Score: 86. Result ID: 69c3dd8147f34ce924ad410b.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Parameters":"78B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-72B

CLIP Score: 85.8. Result ID: 69c3dd8147f34ce924ad40f8.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

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

Recorded evaluation configuration: {"parameter\_size":"72B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-72B

CLIP Score: 85.8. Result ID: 69c3dd8147f34ce924ad4109.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

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

Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-32B

CLIP Score: 83.2. Result ID: 69c3dd8147f34ce924ad4108.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

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

Recorded evaluation configuration: {"Parameters":"32B"}. This record does not assert independent reproduction.

### Qwen3-VL-30B

CLIP Score: 80.2. Result ID: 69c3dd8147f34ce924ad40f9.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"parameter\_size":"30B"}. This record does not assert independent reproduction.

### Qwen3-VL-30B-A3B

CLIP Score: 80.2. Result ID: 69c3dd8147f34ce924ad410a.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Parameters":"30B-A3B"}. This record does not assert independent reproduction.

### InternVL3.5-38B

CLIP Score: 78.6. Result ID: 69c3dd8147f34ce924ad40fa.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

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

Recorded evaluation configuration: {"parameter\_size":"38B"}. This record does not assert independent reproduction.

### InternVL3.5-38B

CLIP Score: 78.6. Result ID: 69c3dd8147f34ce924ad410c.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

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

Recorded evaluation configuration: {"Parameters":"38B"}. This record does not assert independent reproduction.

### GLM4.5V-106B

CLIP Score: 76.9. Result ID: 69c3dd8147f34ce924ad40fb.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"parameter\_size":"106B"}. This record does not assert independent reproduction.

### GLM4.5-V-106B-A12B

CLIP Score: 76.9. Result ID: 69c3dd8147f34ce924ad410d.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c000636e5bf4afc6464.md>)

Recorded evaluation configuration: {"Parameters":"106B-A12B"}. This record does not assert independent reproduction.

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