Model Releases
Super proud of this release, please try this model out
Super proud of this release, please try this model out 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 c
Super proud of this release, please try this model out 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 s…
Related
- it's a good benchmark sir
- Benchmarks so good that even Jensen wants to holla’
- 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, …
- We benchmarked Mistral OCR against other frontier and open-weight models on ParseBench 📊 For a model at its price point, it is quite compet…
- ParseBench is here!📊 We’ve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale. It includes: • 2…
Source: Jerry Liu (X) | 2026-10-21