# Text-to-Image Generation on ConceptMix k = 3 1.0 Source: [Text-to-Image Generation on ConceptMix k = 3 1.0]() Collection index: [llms.txt]() Data updated: 2026-03-20T09:14:52.456Z Evaluation of Text-to-Image generation models on the ConceptMix k = 3 1.0 dataset, measured using the Full Mark 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 1.0 | | Metric | Full Mark 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 - [Full Mark Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Full Mark Score | Result date | Report paper | | --- | --- | --- | --- | | CMO | 57 | Not recorded | 69bcd4750636e5bf4afc294c | | Qwen-Image | 50.6 | Not recorded | 69bcd4750636e5bf4afc294c | | FlowGRPO | 35.17 | Not recorded | 69bcd4750636e5bf4afc294c | | PrefGRPO | 30.23 | Not recorded | 69bcd4750636e5bf4afc294c | | StableDiffusion 3.5 | 30.1 | Not recorded | 69bcd4750636e5bf4afc294c | | Show-o | 27.47 | Not recorded | 69bcd4750636e5bf4afc294c | | HermesFlow | 26.9 | Not recorded | 69bcd4750636e5bf4afc294c | | FLUX.1-dev | 26.8 | Not recorded | 69bcd4750636e5bf4afc294c | | IterComp | 21.43 | Not recorded | 69bcd4750636e5bf4afc294c | | Playground V2.5 | 19.17 | Not recorded | 69bcd4750636e5bf4afc294c | | Janus | 17.1 | Not recorded | 69bcd4750636e5bf4afc294c | | StableDiffusion XL | 16.7 | Not recorded | 69bcd4750636e5bf4afc294c | | PixArt-α | 13.53 | Not recorded | 69bcd4750636e5bf4afc294c | | StableDiffusion XL Turbo | 13.43 | Not recorded | 69bcd4750636e5bf4afc294c | | StableDiffusion v2 | 10.1 | Not recorded | 69bcd4750636e5bf4afc294c | | StableDiffusion v1.4 | 7.17 | Not recorded | 69bcd4750636e5bf4afc294c | ### CMO Full Mark Score: 57. Result ID: 69bd0ffa47f34ce924a75a1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### Qwen-Image Full Mark Score: 50.6. Result ID: 69bd0ffa47f34ce924a75a1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### FlowGRPO Full Mark Score: 35.17. Result ID: 69bd0ffa47f34ce924a75a18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### PrefGRPO Full Mark Score: 30.23. Result ID: 69bd0ffa47f34ce924a75a19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### StableDiffusion 3.5 Full Mark Score: 30.1. Result ID: 69bd0ffa47f34ce924a75a15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### Show-o Full Mark Score: 27.47. Result ID: 69bd0ffa47f34ce924a75a0d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction. ### HermesFlow Full Mark Score: 26.9. Result ID: 69bd0ffa47f34ce924a75a0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction. ### FLUX.1-dev Full Mark Score: 26.8. Result ID: 69bd0ffa47f34ce924a75a16. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### IterComp Full Mark Score: 21.43. Result ID: 69bd0ffa47f34ce924a75a17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### Playground V2.5 Full Mark Score: 19.17. Result ID: 69bd0ffa47f34ce924a75a14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### Janus Full Mark Score: 17.1. Result ID: 69bd0ffa47f34ce924a75a0c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Autoregressive Models"}. This record does not assert independent reproduction. ### StableDiffusion XL Full Mark Score: 16.7. Result ID: 69bd0ffa47f34ce924a75a13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### PixArt-α Full Mark Score: 13.53. Result ID: 69bd0ffa47f34ce924a75a12. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### StableDiffusion XL Turbo Full Mark Score: 13.43. Result ID: 69bd0ffa47f34ce924a75a11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### StableDiffusion v2 Full Mark Score: 10.1. Result ID: 69bd0ffa47f34ce924a75a10. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non-Autoregressive Models"}. This record does not assert independent reproduction. ### StableDiffusion v1.4 Full Mark Score: 7.17. Result ID: 69bd0ffa47f34ce924a75a0f. [Reporting paper]() [Method origin paper]() [Implementation]() 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.