Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.08311 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908377867616256 |
|---|---|
| author | Ji, Yunjie Tian, Xiaoyu Zhao, Sitong Wang, Haotian Chen, Shuaiting Peng, Yiping Zhao, Han Li, Xiangang |
| author_facet | Ji, Yunjie Tian, Xiaoyu Zhao, Sitong Wang, Haotian Chen, Shuaiting Peng, Yiping Zhao, Han Li, Xiangang |
| contents | We present AM-Thinking-v1, a 32B dense language model that advances the frontier of reasoning, embodying the collaborative spirit of open-source innovation. Outperforming DeepSeek-R1 and rivaling leading Mixture-of-Experts (MoE) models like Qwen3-235B-A22B and Seed1.5-Thinking, AM-Thinking-v1 achieves impressive scores of 85.3 on AIME 2024, 74.4 on AIME 2025, and 70.3 on LiveCodeBench, showcasing state-of-the-art mathematical and coding capabilities among open-source models of similar scale.
Built entirely from the open-source Qwen2.5-32B base model and publicly available queries, AM-Thinking-v1 leverages a meticulously crafted post-training pipeline - combining supervised fine-tuning and reinforcement learning - to deliver exceptional reasoning capabilities. This work demonstrates that the open-source community can achieve high performance at the 32B scale, a practical sweet spot for deployment and fine-tuning. By striking a balance between top-tier performance and real-world usability, we hope AM-Thinking-v1 inspires further collaborative efforts to harness mid-scale models, pushing reasoning boundaries while keeping accessibility at the core of innovation. We have open-sourced our model on \href{https://huggingface.co/a-m-team/AM-Thinking-v1}{Hugging Face}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale Ji, Yunjie Tian, Xiaoyu Zhao, Sitong Wang, Haotian Chen, Shuaiting Peng, Yiping Zhao, Han Li, Xiangang Computation and Language We present AM-Thinking-v1, a 32B dense language model that advances the frontier of reasoning, embodying the collaborative spirit of open-source innovation. Outperforming DeepSeek-R1 and rivaling leading Mixture-of-Experts (MoE) models like Qwen3-235B-A22B and Seed1.5-Thinking, AM-Thinking-v1 achieves impressive scores of 85.3 on AIME 2024, 74.4 on AIME 2025, and 70.3 on LiveCodeBench, showcasing state-of-the-art mathematical and coding capabilities among open-source models of similar scale. Built entirely from the open-source Qwen2.5-32B base model and publicly available queries, AM-Thinking-v1 leverages a meticulously crafted post-training pipeline - combining supervised fine-tuning and reinforcement learning - to deliver exceptional reasoning capabilities. This work demonstrates that the open-source community can achieve high performance at the 32B scale, a practical sweet spot for deployment and fine-tuning. By striking a balance between top-tier performance and real-world usability, we hope AM-Thinking-v1 inspires further collaborative efforts to harness mid-scale models, pushing reasoning boundaries while keeping accessibility at the core of innovation. We have open-sourced our model on \href{https://huggingface.co/a-m-team/AM-Thinking-v1}{Hugging Face}. |
| title | AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.08311 |