Skip to content
View original post on X: LangChainOfficial· 46/100AI score46/100

NVIDIA's Nemotron 3.5 Super VL runs in LangChain Deep Agents

AISummary

LangChain says NVIDIA's open-weight Nemotron 3.5 Super VL, a 120B-parameter model with 12B active, averaged an 87% pass rate on its Deep Agents behavioral suite. On the Harbor-lite benchmark, the model finished tasks in 55% less total time than DeepSeek V4.1 Flash at similar success, and it is accessible through ChatNVIDIA.

Post on XView on X
LangChainVerified on X
@LangChain

Nemotron 3.5 Super VL from @NVIDIAAI brings vision, reasoning & tool use to Deep Agents via ChatNVIDIA.

Open weights. 120B parameters, 12B active.

Nemotron 3.5 Super VL averaged an 87% pass rate on our Deep Agents behavioral suite.

Speed stood out, too. On our Harbor-lite benchmark: 55% less total task time than DeepSeek V4.1 Flash, with similar success.

https://docs.langchain.com/oss/python/integrations/chat/nvidia_ai_endpoints

Source: LangChain · x.comPublished

Topics

NVIDIAAI agentsMultimodal AIOpen-source ecosystemModel releasesEvals & benchmarks