# NVIDIA Says Nemotron 3 Ultra Leads Open Models on LangChain's Agent Suite

Tuned inside LangChain's Deep Agents harness, the model scores an aggregate 0.86 at $4.48 per run against $43.48 for the closest closed model.

- Published: 2026-07-09T05:49:21.519Z
- Canonical: https://polylog.news/ai/2026-07-09/nvidia-says-nemotron-3-ultra-leads-open-models-on-langchain
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [NVIDIA Blog](https://blogs.nvidia.com/blog/nemotron-langchain-agents-open-stack/), [LangChain](https://www.langchain.com/blog/langchain-and-nvidia-launch-the-nemoclaw-deep-agents-blueprint)

NVIDIA and LangChain reported that Nemotron 3 Ultra, tuned inside LangChain's Deep Agents harness, reached the highest accuracy among open models on LangChain's internal agent evaluation while running at roughly one-tenth the inference cost…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-09/nvidia-says-nemotron-3-ultra-leads-open-models-on-langchain (subscription information: https://polylog.news/pricing).