Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Text-to-Image Generation research benchmarks – Page 38 · SOTA2 Research

Text-to-Image Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ShareGPT4V (val)

0.317FID

2

Mar 31, 2026

54.62Overall Preference (Calibri)

2

Mar 27, 2026

69.57FID

2

Mar 26, 2026

Aesthetic-4K 20 random prompts

4.57Text Alignment

2

Mar 11, 2026

31.5CLIP Score

2

Mar 10, 2026

82.98FID

2

Mar 5, 2026

DanceGRPO FLUX HPS

209Epochs

2

Feb 26, 2026

DanceGRPO HPS SD1.4

188Epochs

2

Feb 26, 2026

191Epochs

2

Feb 26, 2026

DDPO Aesthetics

118Epochs

2

Feb 26, 2026

Pick-a-Pic LPO v1 (val)

0.276HPSv2

2

Feb 26, 2026

Pick-a-Pic SPIN-Diffusion v1 (val)

0.276HPSv2

2

Feb 26, 2026

Pick-a-Pic SSPO v2 (val)

0.272HPSv2

2

Feb 26, 2026

Pick-a-Pic PCPO v1 (val)

0.271HPSv2

2

Feb 26, 2026

Semantic Erasure and Horizontal Injection

92.5Basic Objects & Colors

2

Feb 26, 2026

SDXL LoRA Styles v1.0 (test)

Universal SDXL LoRA

21.96Style 1 Adherence Score

2

Feb 26, 2026

0.049Attack Success Rate

2

Feb 26, 2026

50.53K77 Score

2

Feb 26, 2026

3.08Attack Success Rate

2

Feb 26, 2026

OpenVid 1.0 (test)

Data and Model-based mitigation baseline

62.05SSCD

2

Feb 26, 2026

OpenVid 395 samples 1.0 (test)

Data and Model-based mitigation baseline

0.592SSCD

2

Feb 26, 2026

OpenVid Single-image overfitting 1.0 (test)

Data-based mitigation baseline

0.73SSCD

2

Feb 26, 2026

35.82FID

2

Feb 26, 2026

26.64FID

2

Feb 26, 2026

0.19Normalized FLOPs

2

Feb 26, 2026

Page 38 of 39

Popular datasets

GenEval MS-COCO DrawBench COCO T2I-CompBench

Follow for updates

Join SOTA2 Contact