# AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale

arXiv: https://arxiv.org/abs/2505.08311 · HTML: https://mlsanity.com/paper/2505.08311/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 59 references that are in the map.
- First posted on arXiv 13 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 7 of 7)

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training](https://mlsanity.com/paper/2503.19633/) (2025)

## Built on by (most cited first, 29 of 29)

- [Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers](https://mlsanity.com/paper/2510.11370/) (2025)
- [No Free Lunch: Rethinking Internal Feedback for LLM Reasoning](https://mlsanity.com/paper/2506.17219/) (2025)
- [MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods](https://mlsanity.com/paper/2601.21821/) (2026)
- [Not All Correct Answers Are Equal: Why Your Distillation Source Matters](https://mlsanity.com/paper/2505.14464/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping](https://mlsanity.com/paper/2510.08457/) (2025)
- [AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent](https://mlsanity.com/paper/2512.20745/) (2025)
- [Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning](https://mlsanity.com/paper/2601.09088/) (2026)
- [MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization](https://mlsanity.com/paper/2507.14683/) (2025)
- [K2-Think: A Parameter-Efficient Reasoning System](https://mlsanity.com/paper/2509.07604/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?](https://mlsanity.com/paper/2510.06410/) (2025)
- [Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models](https://mlsanity.com/paper/2510.21978/) (2025)
- [Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification](https://mlsanity.com/paper/2601.22642/) (2026)
- [OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification](https://mlsanity.com/paper/2512.10756/) (2025)
- [Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets](https://mlsanity.com/paper/2601.09733/) (2025)
- [Best-of-∞ -- Asymptotic Performance of Test-Time LLM Ensembling](https://mlsanity.com/paper/2509.21091/) (2025)
- [How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs](https://mlsanity.com/paper/2601.03662/) (2026)
- [JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2507.19748/) (2025)
- [Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework](https://mlsanity.com/paper/2509.05007/) (2025)
- [Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR](https://mlsanity.com/paper/2511.01937/) (2025)
- [Recursive Think-Answer Process for LLMs and VLMs](https://mlsanity.com/paper/2603.02099/) (2026)
- [Efficient Multilingual Reasoning Transfer via Progressive Code-Switching](https://mlsanity.com/paper/2607.00485/) (2026)
- [PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning](https://mlsanity.com/paper/2601.14716/) (2026)
- [A Primer in Post-Training Reasoning Data: What We Know About How It Works](https://mlsanity.com/paper/2606.02113/) (2026)
- [CausalMix: Data Mixture as Causal Inference for Language Model Training](https://mlsanity.com/paper/2607.01104/) (2026)
- [MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain](https://mlsanity.com/paper/2609.04842/) (2026)
- [Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning](https://mlsanity.com/paper/2609.10445/) (2026)
- [Rufus-Air: An Open LLM Post-Training Recipe](https://mlsanity.com/paper/2609.29421/) (2026)

## Abstract (arXiv)

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 hrefhttps://huggingface.co/a-m-team/AM-Thinking-v1Hugging Face.