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 26 · SOTA2 Research

Text-to-Image Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Malicious Prompts

ESD(Erasing Concept)

372.38FID-Censored

6

Mar 18, 2026

1.044IR

6

Apr 21, 2026

0.274CLIP Score

6

Mar 16, 2026

Pick-a-Pic 10,000 prompts

2.34Inference Time

6

Mar 16, 2026

83.93Relevance

6

Mar 9, 2026

InterActing (entire)

4.57Qwen2.5 Score

6

Mar 5, 2026

InterActing Compositional Relation scenario sampled

4.283Human Likert Score

6

Mar 5, 2026

InterActing Multi-subject Interaction scenario sampled

3.8Human Likert Score

6

Mar 5, 2026

InterActing Functional Relation scenario, sampled

4.28Human Likert Scale

6

Mar 5, 2026

CC12M 50K (val)

4.25FID

6

Mar 4, 2026

GenEval and MS-COCO 10K subset

Flux-Schnell + GAG

0.739GE

6

Mar 4, 2026

COCO captions 2017 (test)

5.58Latency (s)

6

Mar 4, 2026

Webster 2023 SD v1.4 (500 Memorized Prompts)

0.633SSCD Target Score

6

Mar 4, 2026

Webster 70 Unseen Prompts 2023 v1.4 (val)

57.3SSCD (Seeds)

6

Mar 4, 2026

prompts 10 randomly sampled

2.232Inference Time (s)

6

Mar 4, 2026

0.353HPSv2.1

6

Feb 26, 2026

1.91Rank

6

Feb 26, 2026

75B-VQA

6

Feb 26, 2026

evaluation benchmarks one-to-one

31.6CLIP Score

6

Feb 26, 2026

One-to-one evaluation benchmarks Text-to-Image

17.39FID

6

Feb 26, 2026

0.938ImageReward

6

Feb 26, 2026

Human Preference Evaluation Set

4.39DEQA

6

Feb 26, 2026

noise optimization strategy

0.477DreamSim Score

6

Feb 26, 2026

Car Garage Prompts (test)

51.4HPS

6

Feb 26, 2026

Car Insurance Prompts (test)

53.4HPS

6

Feb 26, 2026

Page 26 of 39

Popular datasets

GenEval MS-COCO DrawBench COCO T2I-CompBench

Follow for updates

Join SOTA2 Contact