GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MiniMaxAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MiniMaxAI
Model Tree
Qwen/Qwen2.5-32B
Input Modalities
Output Modalities
Supported Functionality
Zero-Mix-3 is an advanced multi-domain reasoning model trained using Zero-RL (reinforcement learning from scratch) on a diverse mixture of logical reasoning, mathematical, and coding data. Built on Qwen2.5-32B-Base, this model demonstrates the power of combining diverse verifiable reasoning tasks in a unified training framework.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_name = "MiniMaxAI/SynLogic-Mix-3-32B"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto") prompt = "What is 2 + 2?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=20)print(tokenizer.decode(outputs[0], skip_special_tokens=True))| Model | BBEH | KOR-Bench | LiveCodeBench | AIME 2024 | GPQA Diamond |
|---|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-32B | 19.2 | 66.6 | 57.2 | 72.6 | 63.1 |
| DeepSeek-R1-Zero-Qwen-32B | - | - | 40.2 | 47.0 | 55.0 |
| Zero-Mix-2 (Math+Coding) | 18.5 | 58.6 | 39.5 | 34.5 | 55.2 |
| Zero-Mix-3 (SynLogic+Math+Coding) | 28.6 | 65.0 | 40.7 | 35.8 | 57.5 |
Key Achievements:
Comparison with Zero-Mix-2 (Math+Coding only) demonstrates that adding SynLogic logical reasoning data:
bibtex
@misc{liu2025synlogic, title={SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond}, author={Junteng Liu and Yuanxiang Fan and Zhuo Jiang and Han Ding and Yongyi Hu and Chi Zhang and Yiqi Shi and Shitong Weng and Aili Chen and Shiqi Chen and Yunan Huang and Mozhi Zhang and Pengyu Zhao and Junjie Yan and Junxian He}, year={2025}, eprint={2505.19641}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2505.19641}, }from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_name = "MiniMaxAI/SynLogic-Mix-3-32B"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto") prompt = "What is 2 + 2?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=20)print(tokenizer.decode(outputs[0], skip_special_tokens=True))@misc{liu2025synlogic, title={SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond}, author={Junteng Liu and Yuanxiang Fan and Zhuo Jiang and Han Ding and Yongyi Hu and Chi Zhang and Yiqi Shi and Shitong Weng and Aili Chen and Shiqi Chen and Yunan Huang and Mozhi Zhang and Pengyu Zhao and Junjie Yan and Junxian He}, year={2025}, eprint={2505.19641}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2505.19641}, }