Image Generation on TextAtlasEval

Metric: TextVisionBlend OCR (Cer) (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	TextVisionBlend OCR (Cer)▲	Extra Data	Paper	Date↕	Code
1	Grok3	0.57	No	-	-	-
2	Infinity-2B	0.83	No	Infinity-MM: Scaling Multimodal Performance with...	2024-10-24	Code
3	PixArt-Sigma	0.83	No	PixArt-Σ: Weak-to-Strong Training of Diffusion T...	2024-03-07	Code
4	SD3.5 Large	0.88	No	-	-	-
5	Dalle3	0.93	No	-	-	-

#1Grok3
0.57
TextVisionBlend OCR (Cer)
No paper
#2Infinity-2B
0.83
TextVisionBlend OCR (Cer)· 2024-10-24
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data Code
#3PixArt-SigmaSOTA
0.83
TextVisionBlend OCR (Cer)· 2024-03-07
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation Code
#4SD3.5 Large
0.88
TextVisionBlend OCR (Cer)
No paper
#5Dalle3
0.93
TextVisionBlend OCR (Cer)
No paper