GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
youngzhong
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
youngzhong
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
SOD-GRPO_teacher-4B is a 4B agentic reasoning model trained with GRPO (Group Relative Policy Optimization), serving as the teacher model in the SOD distillation framework.
This model is used to distill smaller student models (SOD-0.6B and SOD-1.7B) via the SOD method, which introduces adaptive step-level weighting to handle cascading error propagation in tool-integrated reasoning.
| Attribute | Value |
|---|---|
| Base Model | Qwen3-4B |
| Training Pipeline | Cold-Start SFT → GRPO |
| Parameters | 4B |
| Model | Description |
|---|---|
| SOD-0.6B | SOD-distilled 0.6B student |
| SOD-1.7B | SOD-distilled 1.7B student |
| SOD-GRPO_teacher-4B | GRPO-trained 4B teacher model (this model) |
We report average@32 over 5 runs on challenging math, science, and code benchmarks.
| Method | AIME 2024 | AIME 2025 | GPQA-Diamond | LiveCodeBench-v6 | Average |
|---|---|---|---|---|---|
| GRPO (This Model) | 67.60 | 60.42 | 55.19 | 63.13 | 61.59 |
| Model | AIME 2024 | AIME 2025 | GPQA-Diamond | LiveCodeBench-v6 | Average |
|---|---|---|---|---|---|
| SOD-0.6B | 20.84 | 26.13 | 22.19 | 27.72 | 24.22 |
| SOD-1.7B | 50.83 | 41.72 | 38.72 | 40.63 | 42.98 |
We sincerely thank the authors of DemyAgent-4B and the paper "Demystifying Reinforcement Learning in Agentic Reasoning" (arXiv:2510.11701) for their contribution.
bibtex
@article{zhong2026sod,title={SOD: Step-wise On-policy Distillation for Small Language Model Agents},author={Zhong, Qiyong and Zheng, Mao and Song, Mingyang and Lin, Xin and Sun, Jie and Jiang, Houcheng and Wang, Xiang and Fang, Junfeng},journal={arXiv preprint arXiv:2605.07725},year={2026}}