Model Releases
Congrats to @nvidia for creating the best open-weight model on document parsing so far. Nemotron 3.5 Parse takes the #1 spot on ParseBench, …
Congrats to @nvidia for creating the best open-weight model on document parsing so far. Nemotron 3.5 Parse takes the #1 spot on ParseBench, our comprehensive real-world benchmark for document understa
Congrats to @nvidia for creating the best open-weight model on document parsing so far. Nemotron 3.5 Parse takes the #1 spot on ParseBench, our comprehensive real-world benchmark for document understanding. The full list consists of 150+ frontier models, open-weight models, and specialized solutions. It does this while remaining sub-1B parameters so it's also blazing fast ⚡️ Big thanks to @JensenHuang for the shoutout at GTC Berlin! Nemotron release: https://huggingface.co/blog/nvidia/nemotron-retriever-world-class-agentic-retrieval ParseBench: https://www.parsebench.ai/
Related
- Ocr benchmark
- We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent t…
- ParseBench is here!📊 We’ve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale. It includes: • 2…
- If you want to stack rank LLMs/VLMs on document understanding 📄, you can through ParseBench, now live on @kaggle 📊 ParseBench is the most …
- ParseBench is the most comprehensive OCR benchmark for real-world enterprise documents: financial filings, contracts, insurance documents, a…
Source: Jerry Liu (X) | 2026-10-21