Total runs:
17.2K
Run Growth:
-2.1K
Growth Rate:
-12.11%
Sponsored by
Agentkit
infly / Infinity-Parser2-Pro
Model's Last Updated: July 20 2026
image-text-to-text
Introduction of Infinity-Parser2-Pro
Model Details of Infinity-Parser2-Pro
Infinity-Parser2-Pro
💻 Github | 📊 Dataset (coming soon...) | 📄 Paper (coming soon...) | 🚀 Demo (coming soon...)
News
- [2026-04-09] We released our latest flagship document parsing model, Infinity-Parser2-Pro. Note that this is still a preview version. Model weights are being uploaded.
Introduction
We are excited to release Infinity-Parser2-Pro, our latest flagship document understanding model that achieves a new state-of-the-art on olmOCR-Bench with a score of 86.7%, surpassing frontier models such as DeepSeek-OCR-2, PaddleOCR-VL-1.5, and dots.mocr. Building on our previous model Infinity-Parser-7B, we have significantly enhanced our data engine and multi-task reinforcement learning approach. This enables the model to consolidate robust multi-modal parsing capabilities into a unified architecture, delivering brand-new zero-shot capabilities for diverse real-world business scenarios.
Key Features
- Upgraded Data Engine : We have comprehensively enhanced our synthetic data engine to support both fixed-layout and flexible-layout document formats. By generating over 1 million diverse full-text samples covering a wide range of document layouts, combined with a dynamic adaptive sampling strategy, we ensure highly balanced and robust multi-task learning across various document types.
- Multi-Task Reinforcement Learning : We designed a novel verifiable reward system to support Joint Reinforcement Learning (RL), enabling seamless and simultaneous co-optimization of multiple complex tasks, including doc2json and doc2markdown.
- Breakthrough Parsing Performance : It substantially outperforms our previous 7B model, achieving 86.7% on olmOCR-Bench, surpassing frontier models such as DeepSeek-OCR-2, PaddleOCR-VL-1.5, and dots.mocr.
- Inference Acceleration : By adopting the highly efficient MoE architecture, our inference throughput has increased by 21% (from 441 to 534 tokens/sec), reducing deployment latency and costs.
Performance
Coming soon...
Citation
Coming soon...
License
This model is licensed under apache-2.0.
Runs of infly Infinity-Parser2-Pro on huggingface.co
349.3K
Total runs
0
24-hour runs
0
3-day runs
-38.5K
7-day runs
311.7K
30-day runs
More Information About Infinity-Parser2-Pro huggingface.co Model
Url of Infinity-Parser2-Pro
Infinity-Parser2-Pro huggingface.co Url
Provider of Infinity-Parser2-Pro huggingface.co
Other API from infly
Updated:July 20 2026
Total runs:
7.4K
Run Growth:
-493
Growth Rate:
-6.71%
Total runs:
3.2K
Run Growth:
2.7K
Growth Rate:
86.23%
Total runs:
1.6K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.3K
Run Growth:
28
Growth Rate:
2.08%
Total runs:
1.1K
Run Growth:
744
Growth Rate:
68.01%
Total runs:
921
Run Growth:
543
Growth Rate:
61.08%
Total runs:
844
Run Growth:
127
Growth Rate:
14.75%
Total runs:
289
Run Growth:
-298
Growth Rate:
-103.11%
Total runs:
250
Run Growth:
-335
Growth Rate:
-134.00%
Total runs:
116
Run Growth:
57
Growth Rate:
49.14%
Total runs:
100
Run Growth:
-88
Growth Rate:
-87.13%
Total runs:
54
Run Growth:
-75
Growth Rate:
-138.89%
Total runs:
39
Run Growth:
-315
Growth Rate:
-807.69%
Total runs:
33
Run Growth:
-38
Growth Rate:
-126.67%
Total runs:
17
Run Growth:
6
Growth Rate:
35.29%
Total runs:
13
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%