# Text-to-Image on GenAI-Bench 19 (test)

Source: [Text-to-Image on GenAI-Bench 19 (test)](<https://www.sota2.com/research/sota/text-to-image-on-genai-bench-19-test>)

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

Data updated: 2026-02-26T06:08:04.338Z

Evaluation of Text-to-Image generation performance on the test split of the GenAI-Bench 19 dataset, measured using VQAScore.

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 |
| Dataset (including any stated split) | GenAI-Bench 19 (test) |
| Metric | VQAScore |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [VQAScore](<https://www.sota2.com/research/sota/text-to-image-on-genai-bench-19-test.md?metric=VQAScore>): Higher is better; unit: PERCENT.

## Recorded results

| Method | VQAScore | Result date | Report paper |
| --- | --- | --- | --- |
| Individual Expert (Flow-GRPO) | 78.2 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA | 78.2 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-D | 77.7 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA + RaTE | 77.7 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA | 77.5 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 77.4 | Not recorded | 692689c5d6b0dd3342930642 |
| Rewarded Soup | 77.2 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 77.2 | Not recorded | 692689c5d6b0dd3342930642 |
| Rewarded Soup | 76.7 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 76.4 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 75 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 74.9 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-DR | 74.6 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-DR | 74.5 | Not recorded | 692689c5d6b0dd3342930642 |
| SD 3.5 M | 74.4 | Not recorded | 692689c5d6b0dd3342930642 |
| FLUX.1-dev | 73.7 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-D | 73.3 | Not recorded | 692689c5d6b0dd3342930642 |

### Individual Expert (Flow-GRPO)

VQAScore: 78.2. Result ID: 699a3c8b5698665ec4c30e6f.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M","Reward":"GenEval"}. This record does not assert independent reproduction.

### MapReduce LoRA

VQAScore: 78.2. Result ID: 699a3c8b5698665ec4c30e75.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### MORL-D

VQAScore: 77.7. Result ID: 699a3c8b5698665ec4c30e73.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### MapReduce LoRA + RaTE

VQAScore: 77.7. Result ID: 699a3c8b5698665ec4c30e76.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### MapReduce LoRA

VQAScore: 77.5. Result ID: 699a3c8b5698665ec4c30e7e.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev"}. This record does not assert independent reproduction.

### Individual Expert (Flow-GRPO)

VQAScore: 77.4. Result ID: 699a3c8b5698665ec4c30e70.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M","Reward":"PickScore"}. This record does not assert independent reproduction.

### Rewarded Soup

VQAScore: 77.2. Result ID: 699a3c8b5698665ec4c30e72.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dcbb.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### Individual Expert (Flow-GRPO)

VQAScore: 77.2. Result ID: 699a3c8b5698665ec4c30e79.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev","Reward":"PickScore"}. This record does not assert independent reproduction.

### Rewarded Soup

VQAScore: 76.7. Result ID: 699a3c8b5698665ec4c30e7b.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dcbb.md>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev"}. This record does not assert independent reproduction.

### Individual Expert (Flow-GRPO)

VQAScore: 76.4. Result ID: 699a3c8b5698665ec4c30e78.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev","Reward":"GenEval"}. This record does not assert independent reproduction.

### Individual Expert (Flow-GRPO)

VQAScore: 75. Result ID: 699a3c8b5698665ec4c30e71.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M","Reward":"OCR"}. This record does not assert independent reproduction.

### Individual Expert (Flow-GRPO)

VQAScore: 74.9. Result ID: 699a3c8b5698665ec4c30e7a.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a061e209131cea8093f.md>)

[Implementation](<https://github.com/yifan123/flow_grpo>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev","Reward":"OCR"}. This record does not assert independent reproduction.

### MORL-DR

VQAScore: 74.6. Result ID: 699a3c8b5698665ec4c30e74.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### MORL-DR

VQAScore: 74.5. Result ID: 699a3c8b5698665ec4c30e7d.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev"}. This record does not assert independent reproduction.

### SD 3.5 M

VQAScore: 74.4. Result ID: 699a3c8b5698665ec4c30e6e.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"SD 3.5 M"}. This record does not assert independent reproduction.

### FLUX.1-dev

VQAScore: 73.7. Result ID: 699a3c8b5698665ec4c30e77.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev"}. This record does not assert independent reproduction.

### MORL-D

VQAScore: 73.3. Result ID: 699a3c8b5698665ec4c30e7c.

[Reporting paper](<https://www.sota2.com/research/paper/692689c5d6b0dd3342930642.md>)

Recorded evaluation configuration: {"Backbone":"FLUX.1-dev"}. This record does not assert independent reproduction.

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