# Text-to-Image Generation on text-to-image 2M Source: [Text-to-Image Generation on text-to-image 2M]() Collection index: [llms.txt]() Data updated: 2026-05-22T07:32:53.381Z Evaluation of Text-to-Image generation models using the text-to-image 2M dataset, primarily assessed via CLIP 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) | text-to-image 2M | | Metric | CLIP Score | | 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 - [CLIP Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | CLIP Score | Result date | Report paper | | --- | --- | --- | --- | | P-POTS+Mirror | 35.27 | Not recorded | 69253863d6b0dd334292f7b9 | | Mirror | 34.88 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS+Mirror | 34.59 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS+Mirror | 34.39 | Not recorded | 69253863d6b0dd334292f7b9 | | Standard | 34.28 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS+Mirror | 34.1 | Not recorded | 69253863d6b0dd334292f7b9 | | Mirror | 34.07 | Not recorded | 69253863d6b0dd334292f7b9 | | Mirror | 33.77 | Not recorded | 69253863d6b0dd334292f7b9 | | Mirror | 33.57 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS | 33.41 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS | 31.65 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS | 31.51 | Not recorded | 69253863d6b0dd334292f7b9 | | Standard | 31.36 | Not recorded | 69253863d6b0dd334292f7b9 | | Standard | 31.19 | Not recorded | 69253863d6b0dd334292f7b9 | | P-POTS | 30.02 | Not recorded | 69253863d6b0dd334292f7b9 | | Standard | 28.61 | Not recorded | 69253863d6b0dd334292f7b9 | ### P-POTS+Mirror CLIP Score: 35.27. Result ID: 6a1006a2fbc373592c08a007. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"42"}. This record does not assert independent reproduction. ### Mirror CLIP Score: 34.88. Result ID: 6a1006a2fbc373592c08a013. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"42"}. This record does not assert independent reproduction. ### P-POTS+Mirror CLIP Score: 34.59. Result ID: 6a1006a2fbc373592c08a00a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"Avg"}. This record does not assert independent reproduction. ### P-POTS+Mirror CLIP Score: 34.39. Result ID: 6a1006a2fbc373592c08a009. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"20231"}. This record does not assert independent reproduction. ### Standard CLIP Score: 34.28. Result ID: 6a1006a2fbc373592c08a00c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"731"}. This record does not assert independent reproduction. ### P-POTS+Mirror CLIP Score: 34.1. Result ID: 6a1006a2fbc373592c08a008. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"731"}. This record does not assert independent reproduction. ### Mirror CLIP Score: 34.07. Result ID: 6a1006a2fbc373592c08a016. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"Avg"}. This record does not assert independent reproduction. ### Mirror CLIP Score: 33.77. Result ID: 6a1006a2fbc373592c08a014. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"731"}. This record does not assert independent reproduction. ### Mirror CLIP Score: 33.57. Result ID: 6a1006a2fbc373592c08a015. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"20231"}. This record does not assert independent reproduction. ### P-POTS CLIP Score: 33.41. Result ID: 6a1006a2fbc373592c08a011. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"20231"}. This record does not assert independent reproduction. ### P-POTS CLIP Score: 31.65. Result ID: 6a1006a2fbc373592c08a012. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"Avg"}. This record does not assert independent reproduction. ### P-POTS CLIP Score: 31.51. Result ID: 6a1006a2fbc373592c08a00f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"42"}. This record does not assert independent reproduction. ### Standard CLIP Score: 31.36. Result ID: 6a1006a2fbc373592c08a00e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"Avg"}. This record does not assert independent reproduction. ### Standard CLIP Score: 31.19. Result ID: 6a1006a2fbc373592c08a00d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"20231"}. This record does not assert independent reproduction. ### P-POTS CLIP Score: 30.02. Result ID: 6a1006a2fbc373592c08a010. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"731"}. This record does not assert independent reproduction. ### Standard CLIP Score: 28.61. Result ID: 6a1006a2fbc373592c08a00b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seed":"42"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.