NVIDIA launches Nemotron for Science with Nemotron 3.5 Super VL and a chemistry dataset of nearly 50,000 questions
NVIDIA introduced Nemotron for Science on November 16, 2026. It pairs the open Nemotron 3.5 Super VL model with scientific evaluations, post-training recipes and LitmusBench v0.2, a chemistry dataset of nearly 50,000 questions.
NVIDIA introduced Nemotron for Science on November 16, 2026, a package that pairs its open Nemotron 3.5 Super VL model with scientific evaluations, post-training recipes and LitmusBench v0.2, a chemistry dataset containing nearly 50,000 questions for training and evaluating research agents.
What is in the package
- Model: Nemotron 3.5 Super VL, described as an open model.
- Evaluations and recipes: scientific evaluations and post-training recipes.
- Dataset: LitmusBench v0.2, a chemistry dataset with nearly 50,000 questions, intended for both training and evaluating research agents.
Intended use
The package is intended for agents that interpret scientific information, generate code and call computational tools, including CUDA-X accelerated software. Researchers can post-train the model with domain-specific data.
Context window, parameter count, pricing and benchmark scores were not part of the information available at publication.
What this means
NVIDIA is offering the model, the evaluations, the post-training recipes and a chemistry dataset together, rather than the model alone. For teams building scientific agents, that gives a starting point for domain-specific post-training and a dataset of nearly 50,000 questions for measuring chemistry performance. The stated focus on calling computational tools, including CUDA-X accelerated software, places the package in agent workflows that combine reasoning with code and simulation tools.
Related Articles
NVIDIA recipe: RL post-training lifts Nemotron 3.5 Super VL accuracy a further 17% on drug-metabolism task
NVIDIA has published a recipe for post-training Nemotron 3.5 Super VL on scientific tasks using NeMo Gym and NeMo RL. In a drug-metabolism example, supervised fine-tuning improved accuracy by 12% and RL post-training lifted it a further 17% at a 16,384-token output budget.
NVIDIA releases two synthetic Japanese datasets, Nemotron-Personas-Finance-Japan and Nemotron-PII-Japan
At NVIDIA Agentic AI Day Japan 2026 in Tokyo on November 10, NVIDIA presented two synthetic datasets for Japanese AI development. Nemotron-Personas-Finance-Japan targets financial AI and user simulation, and Nemotron-PII-Japan covers PII detection and masking across 8 domains. Both are published on Hugging Face.
NVIDIA Vera Rubin NVL72 posts over 10x GB300 NVL72 throughput per kW on MLPerf Endpoints v1.0
Provisional MLPerf Endpoints v1.0 results show NVIDIA Vera Rubin NVL72 delivering over 10x the throughput per kilowatt of GB300 NVL72 at a shared minimum interactivity of 50 tokens per second per user. The Vera Rubin results are pending MLCommons verification; the GB300 results are verified.
NVIDIA Vera Rubin NVL72 posts fastest time to train on six of seven MLPerf Training v6.1 benchmarks
In its first MLPerf Training appearance, NVIDIA's Vera Rubin NVL72 delivered the fastest time to train on six of seven benchmarks, with up to 2x the per-GPU performance of an optimized GB300 NVL72 baseline, according to NVIDIA. On DeepSeek-V3 671B it trained in 4.14 minutes on 1,024 GPUs versus 8.03 minutes for GB300 NVL72.
Comments
Loading...