Image Generation on TextAtlasEval

Metric: TextVisionBlend OCR (Accuracy) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	TextVisionBlend OCR (Accuracy)▼	Extra Data	Paper	Date↕	Code
1	Grok3	41.54	No	-	-	-
2	SD3.5 Large	14.55	No	-	-	-
3	Dalle3	8.38	No	-	-	-
4	Infinity-2B	2.98	No	Infinity-MM: Scaling Multimodal Performance with...	2024-10-24	Code
5	PixArt-Sigma	2.4	No	PixArt-Σ: Weak-to-Strong Training of Diffusion T...	2024-03-07	Code

#1Grok3
41.54
TextVisionBlend OCR (Accuracy)
No paper
#2SD3.5 Large
14.55
TextVisionBlend OCR (Accuracy)
No paper
#3Dalle3
8.38
TextVisionBlend OCR (Accuracy)
No paper
#4Infinity-2BSOTA
2.98
TextVisionBlend OCR (Accuracy)· 2024-10-24
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data Code
#5PixArt-SigmaSOTA
2.4
TextVisionBlend OCR (Accuracy)· 2024-03-07
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation Code