# Scientific Image Synthesis on Science-T2I (test)

Source: [Scientific Image Synthesis on Science-T2I (test)](<https://www.sota2.com/research/sota/scientific-image-synthesis-on-science-t2i-test>)

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

Data updated: 2026-04-02T08:24:33.464Z

Evaluation of models performing Scientific Image Synthesis on the Science-T2I test set, measured across Physics, Chemistry, and Biology domains.

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 | Scientific Image Synthesis |
| Dataset (including any stated split) | Science-T2I (test) |
| Metric | Physics Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Physics Score](<https://www.sota2.com/research/sota/scientific-image-synthesis-on-science-t2i-test.md?metric=Physics%20Score>): Higher is better; unit: SCALAR.

- [Chemistry Score](<https://www.sota2.com/research/sota/scientific-image-synthesis-on-science-t2i-test.md?metric=Chemistry%20Score>): Higher is better; unit: SCALAR.

- [Biology Score](<https://www.sota2.com/research/sota/scientific-image-synthesis-on-science-t2i-test.md?metric=Biology%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/scientific-image-synthesis-on-science-t2i-test.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Physics Score | Result date | Report paper |
| --- | --- | --- | --- |
| FLUX.2\[dev\] | 53.19 | Not recorded | 68fa781a1e209131cea76cdb |
| Qwen-Image | 34.58 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.2\[klein-9B-Base\] | 30.28 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.2\[klein-9B\] | 29.44 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.2\[klein-4B\] | 28.75 | Not recorded | 68fa781a1e209131cea76cdb |
| SD 3.5 Large | 27.64 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.2\[klein-4B-Base\] | 27.22 | Not recorded | 68fa781a1e209131cea76cdb |
| Z-Image-Turbo | 26.81 | Not recorded | 68fa781a1e209131cea76cdb |
| Z-Image | 26.53 | Not recorded | 68fa781a1e209131cea76cdb |
| Bagel | 25.28 | Not recorded | 68fa781a1e209131cea76cdb |
| SANA | 23.89 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.1\[schnell\] | 23.19 | Not recorded | 68fa781a1e209131cea76cdb |
| SD 3.5 Medium | 23.06 | Not recorded | 68fa781a1e209131cea76cdb |
| FLUX.1\[dev\] | 22.64 | Not recorded | 68fa781a1e209131cea76cdb |
| GLM-Image | 22.22 | Not recorded | 68fa781a1e209131cea76cdb |
| LongCat-Image | 21.94 | Not recorded | 68fa781a1e209131cea76cdb |
| Lumina-Image-2 | 20.28 | Not recorded | 68fa781a1e209131cea76cdb |
| SDXL | 16.11 | Not recorded | 68fa781a1e209131cea76cdb |

### FLUX.2\[dev\]

Physics Score: 53.19. Result ID: 69ce27ae47f34ce924b74338.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### Qwen-Image

Physics Score: 34.58. Result ID: 69ce27ae47f34ce924b74337.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.2\[klein-9B-Base\]

Physics Score: 30.28. Result ID: 69ce27ae47f34ce924b74335.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.2\[klein-9B\]

Physics Score: 29.44. Result ID: 69ce27ae47f34ce924b74336.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.2\[klein-4B\]

Physics Score: 28.75. Result ID: 69ce27ae47f34ce924b74334.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### SD 3.5 Large

Physics Score: 27.64. Result ID: 69ce27ae47f34ce924b74330.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72621e209131cea56163.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.2\[klein-4B-Base\]

Physics Score: 27.22. Result ID: 69ce27ae47f34ce924b74332.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### Z-Image-Turbo

Physics Score: 26.81. Result ID: 69ce27ae47f34ce924b74333.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d2156d6b0dd33429319e4.md>)

[Implementation](<https://github.com/Tongyi-MAI/Z-Image>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### Z-Image

Physics Score: 26.53. Result ID: 69ce27ae47f34ce924b7432e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d2156d6b0dd33429319e4.md>)

[Implementation](<https://github.com/Tongyi-MAI/Z-Image>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### Bagel

Physics Score: 25.28. Result ID: 69ce27ae47f34ce924b74331.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a311e209131cea81aad.md>)

[Implementation](<https://bagel-ai.org/>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### SANA

Physics Score: 23.89. Result ID: 69ce27ae47f34ce924b7432b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75531e209131cea67334.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.1\[schnell\]

Physics Score: 23.19. Result ID: 69ce27ae47f34ce924b74328.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### SD 3.5 Medium

Physics Score: 23.06. Result ID: 69ce27ae47f34ce924b7432d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72621e209131cea56163.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### FLUX.1\[dev\]

Physics Score: 22.64. Result ID: 69ce27ae47f34ce924b7432f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### GLM-Image

Physics Score: 22.22. Result ID: 69ce27ae47f34ce924b7432a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### LongCat-Image

Physics Score: 21.94. Result ID: 69ce27ae47f34ce924b74329.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad3e6cfd488761a4eb09.md>)

[Implementation](<https://github.com/meituan-longcat/LongCat-Image>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### Lumina-Image-2

Physics Score: 20.28. Result ID: 69ce27ae47f34ce924b7432c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745c5.md>)

[Implementation](<https://github.com/Alpha-VLLM/Lumina-Image-2.0>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

### SDXL

Physics Score: 16.11. Result ID: 69ce27ae47f34ce924b74327.

[Reporting paper](<https://www.sota2.com/research/paper/68fa781a1e209131cea76cdb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70011e209131cea487fb.md>)

Recorded evaluation configuration: {"Prompt Type":"implicit","Evaluator":"Qwen3.5-27B"}. This record does not assert independent reproduction.

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