# Text-to-Image on PartiPrompts 42 (test)

Source: [Text-to-Image on PartiPrompts 42 (test)](<https://www.sota2.com/research/sota/text-to-image-on-partiprompts-42-test>)

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

Data updated: 2026-02-26T06:08:04.320Z

Evaluation of Text-to-Image models using the PartiPrompts 42 test set, assessed using VQAScore, MPS, and VILA 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 | Text-to-Image |
| Dataset (including any stated split) | PartiPrompts 42 (test) |
| Metric | VQAScore |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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-partiprompts-42-test.md?metric=VQAScore>): Higher is better; unit: PERCENT.

- [MPS](<https://www.sota2.com/research/sota/text-to-image-on-partiprompts-42-test.md?metric=MPS>): Higher is better; unit: SCALAR.

- [VILA](<https://www.sota2.com/research/sota/text-to-image-on-partiprompts-42-test.md?metric=VILA>): Higher is better; unit: SCALAR.

## Recorded results

| Method | VQAScore | Result date | Report paper |
| --- | --- | --- | --- |
| SD 3 M + CaPO | 91.4 | Not recorded | 692689c5d6b0dd3342930642 |
| SD 3 M | 90.8 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA | 88.5 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-D | 88.1 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 88 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 87.9 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA + RaTE | 87.7 | Not recorded | 692689c5d6b0dd3342930642 |
| Rewarded Soup | 87.5 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 87.5 | Not recorded | 692689c5d6b0dd3342930642 |
| MapReduce LoRA | 87.5 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 86.3 | Not recorded | 692689c5d6b0dd3342930642 |
| Rewarded Soup | 86.2 | Not recorded | 692689c5d6b0dd3342930642 |
| SD 3.5 M | 86.1 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-DR | 86 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 85.4 | Not recorded | 692689c5d6b0dd3342930642 |
| Individual Expert (Flow-GRPO) | 84.1 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-DR | 84 | Not recorded | 692689c5d6b0dd3342930642 |
| MORL-D | 83.4 | Not recorded | 692689c5d6b0dd3342930642 |
| FLUX.1-dev | 83 | Not recorded | 692689c5d6b0dd3342930642 |

### SD 3 M + CaPO

VQAScore: 91.4. Result ID: 699a3c8b5698665ec4c30e5c.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b9f1e209131cea89667.md>)

Recorded evaluation configuration: {"Backbone":"SD 3 M"}. This record does not assert independent reproduction.

### SD 3 M

VQAScore: 90.8. Result ID: 699a3c8b5698665ec4c30e5b.

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

Recorded evaluation configuration: {"Backbone":"SD 3 M"}. This record does not assert independent reproduction.

### MapReduce LoRA

VQAScore: 88.5. Result ID: 699a3c8b5698665ec4c30e64.

[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: 88.1. Result ID: 699a3c8b5698665ec4c30e62.

[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.

### Individual Expert (Flow-GRPO)

VQAScore: 88. Result ID: 699a3c8b5698665ec4c30e5f.

[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.

### Individual Expert (Flow-GRPO)

VQAScore: 87.9. Result ID: 699a3c8b5698665ec4c30e5e.

[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 + RaTE

VQAScore: 87.7. Result ID: 699a3c8b5698665ec4c30e65.

[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.

### Rewarded Soup

VQAScore: 87.5. Result ID: 699a3c8b5698665ec4c30e61.

[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: 87.5. Result ID: 699a3c8b5698665ec4c30e68.

[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.

### MapReduce LoRA

VQAScore: 87.5. Result ID: 699a3c8b5698665ec4c30e6d.

[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: 86.3. Result ID: 699a3c8b5698665ec4c30e60.

[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.

### Rewarded Soup

VQAScore: 86.2. Result ID: 699a3c8b5698665ec4c30e6a.

[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.

### SD 3.5 M

VQAScore: 86.1. Result ID: 699a3c8b5698665ec4c30e5d.

[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: 86. Result ID: 699a3c8b5698665ec4c30e63.

[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.

### Individual Expert (Flow-GRPO)

VQAScore: 85.4. Result ID: 699a3c8b5698665ec4c30e67.

[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: 84.1. Result ID: 699a3c8b5698665ec4c30e69.

[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: 84. Result ID: 699a3c8b5698665ec4c30e6c.

[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: 83.4. Result ID: 699a3c8b5698665ec4c30e6b.

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

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

### FLUX.1-dev

VQAScore: 83. Result ID: 699a3c8b5698665ec4c30e66.

[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.