# Text-to-Image Generation on UniGenBench++ (Short and Long Metrics)

Source: [Text-to-Image Generation on UniGenBench++ (Short and Long Metrics)](<https://www.sota2.com/research/sota/text-to-image-generation-on-unigenbench-plus-plus-short-and-long-metrics>)

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

Data updated: 2026-05-12T08:24:17.797Z

Evaluation of Text-to-Image generation models on the UniGenBench++ dataset, reporting scores specifically labeled as 'Short' and 'Long'.

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 | Text-to-Image Generation |
| Dataset (including any stated split) | UniGenBench++ |
| Metric | Score (Short) |
| Unit | SCALAR |
| 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

- [Score (Short)](<https://www.sota2.com/research/sota/text-to-image-generation-on-unigenbench-plus-plus-short-and-long-metrics.md?metric=Score%20(Short)>): Higher is better; unit: SCALAR.

- [Score (Long)](<https://www.sota2.com/research/sota/text-to-image-generation-on-unigenbench-plus-plus-short-and-long-metrics.md?metric=Score%20(Long)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score (Short) | Result date | Report paper |
| --- | --- | --- | --- |
| DALLE-3 | 68.85 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 65.89 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 65.36 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 64.76 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 64.22 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 64.17 | Not recorded | 6a02b424dbc836b87d8246e4 |
| ARR-RPO | 63.28 | Not recorded | 6a02b424dbc836b87d8246e4 |
| OmniGen2 | 63.09 | Not recorded | 6a02b424dbc836b87d8246e4 |
| Show-o2 | 61.9 | Not recorded | 6a02b424dbc836b87d8246e4 |
| Janus-Pro-7B | 61.36 | Not recorded | 6a02b424dbc836b87d8246e4 |
| FLUX.1-Dev | 60.97 | Not recorded | 6a02b424dbc836b87d8246e4 |
| BAGEL | 59.91 | Not recorded | 6a02b424dbc836b87d8246e4 |
| BLIP3o-4B | 59.57 | Not recorded | 6a02b424dbc836b87d8246e4 |
| JanusFlow | 47.1 | Not recorded | 6a02b424dbc836b87d8246e4 |
| Emu3 | 45.42 | Not recorded | 6a02b424dbc836b87d8246e4 |
| SDXL | 40.22 | Not recorded | 6a02b424dbc836b87d8246e4 |

### DALLE-3

Score (Short): 68.85. Result ID: 6a02e39f47f34ce924e59f4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5c4a1e209131ce9cfa25.md>)

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

### ARR-RPO

Score (Short): 65.89. Result ID: 6a02e39f47f34ce924e59f57.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-Gemini 3.1 Pro-ARR"}. This record does not assert independent reproduction.

### ARR-RPO

Score (Short): 65.36. Result ID: 6a02e39f47f34ce924e59f55.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-GPT-5-ARR"}. This record does not assert independent reproduction.

### ARR-RPO

Score (Short): 64.76. Result ID: 6a02e39f47f34ce924e59f56.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-Gemini 3.1 Pro"}. This record does not assert independent reproduction.

### ARR-RPO

Score (Short): 64.22. Result ID: 6a02e39f47f34ce924e59f54.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-GPT-5"}. This record does not assert independent reproduction.

### ARR-RPO

Score (Short): 64.17. Result ID: 6a02e39f47f34ce924e59f53.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-Qwen3vl-8B-ARR"}. This record does not assert independent reproduction.

### ARR-RPO

Score (Short): 63.28. Result ID: 6a02e39f47f34ce924e59f52.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Implementation](<https://github.com/OpenEnvision/AutoRubric-as-Reward>)

Recorded evaluation configuration: {"Variant":"w/ RPO-Qwen3vl-8B"}. This record does not assert independent reproduction.

### OmniGen2

Score (Short): 63.09. Result ID: 6a02e39f47f34ce924e59f50.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba31e209131cea89864.md>)

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

### Show-o2

Score (Short): 61.9. Result ID: 6a02e39f47f34ce924e59f4f.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b761e209131cea88a1f.md>)

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

### Janus-Pro-7B

Score (Short): 61.36. Result ID: 6a02e39f47f34ce924e59f4e.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76cc1e209131cea6f20a.md>)

[Implementation](<https://github.com/deepseek-ai/Janus>)

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

### FLUX.1-Dev

Score (Short): 60.97. Result ID: 6a02e39f47f34ce924e59f4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a81e209131cea7eb79.md>)

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

### BAGEL

Score (Short): 59.91. Result ID: 6a02e39f47f34ce924e59f51.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

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

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

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

### BLIP3o-4B

Score (Short): 59.57. Result ID: 6a02e39f47f34ce924e59f4d.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78841e209131cea78c86.md>)

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

### JanusFlow

Score (Short): 47.1. Result ID: 6a02e39f47f34ce924e59f4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77981e209131cea743dd.md>)

[Implementation](<https://github.com/deepseek-ai/Janus>)

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

### Emu3

Score (Short): 45.42. Result ID: 6a02e39f47f34ce924e59f49.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f61e209131cea64daa.md>)

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

### SDXL

Score (Short): 40.22. Result ID: 6a02e39f47f34ce924e59f48.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b424dbc836b87d8246e4.md>)

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