# Text-to-Image Generation on ConceptMix k=3

Source: [Text-to-Image Generation on ConceptMix k=3](<https://www.sota2.com/research/sota/text-to-image-generation-on-conceptmix-k-3>)

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

Data updated: 2026-03-20T09:14:52.187Z

Evaluation of Text-to-Image generation models on the ConceptMix k=3 dataset, measured using the Concept Fraction Score.

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) | ConceptMix k=3 |
| Metric | Concept Fraction 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

- [Concept Fraction Score](<https://www.sota2.com/research/sota/text-to-image-generation-on-conceptmix-k-3.md?metric=Concept%20Fraction%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Concept Fraction Score | Result date | Report paper |
| --- | --- | --- | --- |
| CMO | 86.35 | Not recorded | 69bcd4750636e5bf4afc294c |
| Qwen-Image | 84.03 | Not recorded | 69bcd4750636e5bf4afc294c |
| FlowGRPO | 77.26 | Not recorded | 69bcd4750636e5bf4afc294c |
| Pref-GRPO | 73.94 | Not recorded | 69bcd4750636e5bf4afc294c |
| StableDiffusion 3.5 | 73.68 | Not recorded | 69bcd4750636e5bf4afc294c |
| Show-o | 72.6 | Not recorded | 69bcd4750636e5bf4afc294c |
| HermesFlow | 71.93 | Not recorded | 69bcd4750636e5bf4afc294c |
| FLUX.1-dev | 70.93 | Not recorded | 69bcd4750636e5bf4afc294c |
| IterComp | 69.84 | Not recorded | 69bcd4750636e5bf4afc294c |
| Playground V2.5 | 67.01 | Not recorded | 69bcd4750636e5bf4afc294c |
| StableDiffusion XL | 66.57 | Not recorded | 69bcd4750636e5bf4afc294c |
| StableDiffusion XL Turbo | 63.24 | Not recorded | 69bcd4750636e5bf4afc294c |
| Janus | 63.18 | Not recorded | 69bcd4750636e5bf4afc294c |
| PixArt-α | 63.12 | Not recorded | 69bcd4750636e5bf4afc294c |
| Stable Diffusion v2 | 58.22 | Not recorded | 69bcd4750636e5bf4afc294c |
| Stable Diffusion v1.4 | 51.9 | Not recorded | 69bcd4750636e5bf4afc294c |

### CMO

Concept Fraction Score: 86.35. Result ID: 69bd0ffa47f34ce924a75992.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Qwen-Image

Concept Fraction Score: 84.03. Result ID: 69bd0ffa47f34ce924a75991.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

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

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### FlowGRPO

Concept Fraction Score: 77.26. Result ID: 69bd0ffa47f34ce924a7598f.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

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

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

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Pref-GRPO

Concept Fraction Score: 73.94. Result ID: 69bd0ffa47f34ce924a75990.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b011e209131cea862f7.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### StableDiffusion 3.5

Concept Fraction Score: 73.68. Result ID: 69bd0ffa47f34ce924a7598c.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

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

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Show-o

Concept Fraction Score: 72.6. Result ID: 69bd0ffa47f34ce924a75984.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1f1e209131cea86ae5.md>)

[Implementation](<https://github.com/showlab/Show-o>)

Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction.

### HermesFlow

Concept Fraction Score: 71.93. Result ID: 69bd0ffa47f34ce924a75985.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b951e209131cea8943a.md>)

Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction.

### FLUX.1-dev

Concept Fraction Score: 70.93. Result ID: 69bd0ffa47f34ce924a7598d.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### IterComp

Concept Fraction Score: 69.84. Result ID: 69bd0ffa47f34ce924a7598e.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d01e209131cea6f38c.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Playground V2.5

Concept Fraction Score: 67.01. Result ID: 69bd0ffa47f34ce924a7598b.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72521e209131cea559d1.md>)

[Implementation](<https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### StableDiffusion XL

Concept Fraction Score: 66.57. Result ID: 69bd0ffa47f34ce924a7598a.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

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

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### StableDiffusion XL Turbo

Concept Fraction Score: 63.24. Result ID: 69bd0ffa47f34ce924a75988.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50558.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Janus

Concept Fraction Score: 63.18. Result ID: 69bd0ffa47f34ce924a75983.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753c1e209131cea669f4.md>)

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

Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction.

### PixArt-α

Concept Fraction Score: 63.12. Result ID: 69bd0ffa47f34ce924a75989.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Stable Diffusion v2

Concept Fraction Score: 58.22. Result ID: 69bd0ffa47f34ce924a75987.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e4a.md>)

[Implementation](<https://github.com/CompVis/latent-diffusion>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

### Stable Diffusion v1.4

Concept Fraction Score: 51.9. Result ID: 69bd0ffa47f34ce924a75986.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4750636e5bf4afc294c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e4a.md>)

[Implementation](<https://github.com/CompVis/latent-diffusion>)

Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction.

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