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 15 · SOTA2 Research

Text-to-Image Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Chefer prompts (Object-Object)

65.95BLIP-VQA

12

Mar 17, 2026

Chefer Prompts Animal-Object

0.888BLIP-VQA

12

Mar 17, 2026

Chefer prompts Animal-Animal

74.41BLIP-VQA Score

12

Mar 17, 2026

User Study Human Evaluation

60VisualPrompter Preference

12

Mar 31, 2026

Qwen-Image Evaluation Set

22.4Latency (s)

12

Feb 26, 2026

MSCOCO 30K 2014 (val)

10.65FID

12

Feb 26, 2026

IG-NeurIPS’24

1.389Density

12

Feb 26, 2026

8.847VS

12

Feb 26, 2026

FLUX.1 1.0 (dev)

388.27FLOPs (T)

12

Feb 26, 2026

Pick-a-Pic, HPSv2, and PartiPrompts (test)

24.9PickScore

12

Feb 26, 2026

0.81Cultural Score

12

Feb 26, 2026

8.54Attribute Shift

12

Feb 26, 2026

Text-to-image generation (test)

14.78FID

12

Feb 26, 2026

95OCR Accuracy

12

Feb 26, 2026

92OCR Accuracy

12

Feb 26, 2026

24.05PickScore

12

Feb 26, 2026

Affordance Pairs Automatic Evaluation (test)

3.99Faithfulness

12

Feb 26, 2026

0.461CompBench Score

12

Feb 26, 2026

Text-to-Image Generation Evaluation Set

1.54Mismatch Rate (M/F)

12

Feb 26, 2026

Evaluation Agent

5Evaluation Time (min)

12

Feb 26, 2026

Qwen-Image native (test)

10.3Speedup

11

Jul 3, 2026

0.859ID

11

May 26, 2026

Aesthetic-4K zero-shot 4096 x 4096

1.58IR

11

May 22, 2026

SD3 Generated Images 1024x1024

27.67FID

11

May 22, 2026

87.23Color Score

11

Jun 30, 2026

Page 15 of 39

Popular datasets

GenEval MS-COCO DrawBench COCO T2I-CompBench

Follow for updates

Join SOTA2 Contact