GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nvidia
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nvidia
Model Tree
Qwen/Qwen3-235B-A22B-Thinking-2507
Input Modalities
Output Modalities
Supported Functionality
Qwen3-Nemotron-235B-A22B-GenRM is a Generative Reward Model (GenRM) that leverages Qwen3-235B-A22B-Thinking-2507 as the foundation and is fine-tuned to evaluate the quality of assistant's responses.
Given a conversation history, a new user request, and two candidate assistant responses, it produces an individual helpfulness score for each response and a ranking score.
This GenRM is used in the Reinforcement Learning from Human Feedback training of NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.
For training details, see the Nemotron 3 Nano technical report.
This model is ready for commercial/non-commercial use.
The model is licensed with Apache 2.0.
Global
HuggingFace 2025-12-15 via https://huggingface.co/nvidia/Qwen3-Nemotron-235B-A22B-GenRM
| Chat | Math | Code | Safety | Easy | Normal | Hard | Overall |
|---|---|---|---|---|---|---|---|
| 76.5 | 96.9 | 81.4 | 94.4 | 94.0 | 90.5 | 77.4 | 87.3 |
| Knowledge | Reasoning | Math | Code | Overall |
|---|---|---|---|---|
| 78.6 | 95.9 | 91.1 | 95.2 | 87.4 |
Architecture Type: Transformer Network Architecture: Qwen3
We developed this model using Qwen/Qwen3-235B-A22B-Thinking-2507 as its foundation. This model contains 235 billion parameters.
Input Type(s): Text Input Format: String Input Parameters: One Dimensional (1D) Other Properties Related to Input: Max of 128k tokens
Output Type(s): Text Output Format: String Output Parameters: One-Dimensional (1D)
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Runtime Engine(s):
Supported Hardware Microarchitecture Compatibility:
Supported Operating System(s): Linux
The model shares the same architecture as Qwen3-235B-A22B-Thinking-2507. It can be served with vLLM.
text
python3 -m vllm.entrypoints.openai.api_server \ --model "nvidia/Qwen3-Nemotron-235B-A22B-GenRM" \ --trust-remote-code \ --seed=1 \ --host="0.0.0.0" \ --port=5000 \ --served-model-name "nvidia/Qwen3-Nemotron-235B-A22B-GenRM" \ --tensor-parallel-size=8 \ --max-model-len=40000 \ --gpu-memory-utilization=0.95Now you can query the model, here is an example:
python
from openai import OpenAIclient = OpenAI(base_url="http://127.0.0.1:5000/v1", api_key="dummy") msg = [ {"role": "user", "content": "What is 1+1?"}, {"role": "assistant", "content": "1+1=2"}, {"role": "user", "content": "What about 1+2?"}, {"role": "response_1", "content": "1+2=4"}, {"role": "response_2", "content": "1+2=3"}] completion = client.chat.completions.create( model="nvidia/Qwen3-Nemotron-235B-A22B-GenRM", messages=msg, temperature=0.6, top_p=0.95, max_tokens=16384, stream=False)output = completion.choices[0].message.contentprint(output.split("</think>")[-1].strip())Note that the conversation history should be presented in "user" and "assistant" roles, where the last turn is user turn. The responses to be judged should be in "response_1" and "response_2" roles.
For individual helpfulness score, it ranges from 1 to 5, where higher means better.
For ranking score, it ranges from 1 to 6, where:
v1.0
Dataset Name: Subset of Nemotron dataset-3 containing samples from HelpSteer3, lmarena-ai/arena-human-preference-140k (commercial-friendly models only) and additional safety preference data.
Datasets Links: To be released (Nemotron dataset-3)
Data Collection Method
Labeling Method
Dataset Name: RM-Bench Dataset Link: https://huggingface.co/datasets/THU-KEG/RM-Bench
Data Collection Method by dataset
Labeling Method by dataset
Properties:
Dataset Name: JudgeBench Dataset Link: https://huggingface.co/datasets/ScalerLab/JudgeBench
Data Collection Method by dataset
Labeling Method by dataset
Properties:
Engine: PyTorch Test Hardware: H100
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety and Security, and Privacy Subcards.
Please report security vulnerabilities or NVIDIA AI Concerns here.
If you find this model useful, please cite the following work:
bibtex
@misc{wang2025helpsteer3preferenceopenhumanannotatedpreference, title={Help{S}teer3-{P}reference: Open Human-Annotated Preference Data across Diverse Tasks and Languages}, author={Zhilin Wang and Jiaqi Zeng and Olivier Delalleau and Hoo-Chang Shin and Felipe Soares and Alexander Bukharin and Ellie Evans and Yi Dong and Oleksii Kuchaiev}, year={2025}, eprint={2505.11475}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.11475}, }python3 -m vllm.entrypoints.openai.api_server \ --model "nvidia/Qwen3-Nemotron-235B-A22B-GenRM" \ --trust-remote-code \ --seed=1 \ --host="0.0.0.0" \ --port=5000 \ --served-model-name "nvidia/Qwen3-Nemotron-235B-A22B-GenRM" \ --tensor-parallel-size=8 \ --max-model-len=40000 \ --gpu-memory-utilization=0.95from openai import OpenAIclient = OpenAI(base_url="http://127.0.0.1:5000/v1", api_key="dummy") msg = [ {"role": "user", "content": "What is 1+1?"}, {"role": "assistant", "content": "1+1=2"}, {"role": "user", "content": "What about 1+2?"}, {"role": "response_1", "content": "1+2=4"}, {"role": "response_2", "content": "1+2=3"}] completion = client.chat.completions.create( model="nvidia/Qwen3-Nemotron-235B-A22B-GenRM", messages=msg, temperature=0.6, top_p=0.95, max_tokens=16384, stream=False)output = completion.choices[0].message.contentprint(output.split("</think>")[-1].strip())@misc{wang2025helpsteer3preferenceopenhumanannotatedpreference, title={Help{S}teer3-{P}reference: Open Human-Annotated Preference Data across Diverse Tasks and Languages}, author={Zhilin Wang and Jiaqi Zeng and Olivier Delalleau and Hoo-Chang Shin and Felipe Soares and Alexander Bukharin and Ellie Evans and Yi Dong and Oleksii Kuchaiev}, year={2025}, eprint={2505.11475}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.11475}, }