---
title: "Distilling Long-CoT Reasoning through Collaborative Step-wise"
description: "The authors propose CoRD (Collaborative Reasoning Decoding), which treats each reasoning step as a decoding unit. 34 references."
authors: ["Taewon Yun", "Jisu Shin", "Jeonghwan Choi", "Seunghwan Bang", "Hwanjun Song"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1867/"
doi: "10.18653/v1/2026.findings-acl.1867"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yun-2026-distilling-long-cot-reasoning-through/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yun-2026-distilling-long-cot-reasoning-through/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/) / Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

# Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

**Authors:** Taewon Yun, [Jisu Shin](https://md.research.elamur.ai/free/en/authors/jisu-shin/), Jeonghwan Choi, Seunghwan Bang and [Hwanjun Song](https://md.research.elamur.ai/free/en/authors/hwanjun-song/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1867/) · [PDF](https://aclanthology.org/2026.findings-acl.1867.pdf) · [DOI 10.18653/v1/2026.findings-acl.1867](https://doi.org/10.18653/v1/2026.findings-acl.1867) · [OpenAlex](https://openalex.org/W7166843365)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Long chain-of-thought (Long-CoT) reasoning from large reasoning models (LRMs) is too expensive to run at full scale, so it is usually distilled into smaller students. Existing curation pipelines such as S1 and LIMO have teachers write complete traces and then keep the best one. This wastes compute on rejected traces and never lets different teachers combine their strengths. The authors propose CoRD (Collaborative Reasoning Decoding), which treats each reasoning step as a decoding unit.

CoRD works in three parts:
- Prompting inserts explicit step markers into the traces.
- Several heterogeneous LRMs each propose a next step.
- Candidates are ranked by predictive perplexity, meaning how well the gold answer follows from the current prefix. Beam search keeps several promising paths alive, including ones that only pay off after later corrections.

Compared with Curation, Integration, S1 and LIMO-v1/v2 across five benchmarks, CoRD yields better distillation data. Its students come close to, or even beat, their teachers. It needs about half the wall-clock time of MCTS and transfers to out-of-domain and open-ended tasks. This makes compact students with strong reasoning more affordable to build.

## Key points
- **Core mechanisms:** splitting steps by prompting, ranking candidates by their predictive perplexity, and searching over paths with a beam. Each beat alternative designs, such as line-break or prefix-based (e.g., "wait") segmentation.
- **Efficiency:** CoRD needs roughly 49.0% of the computation time of MCTS, with negligible meta-prover overhead. It costs only modestly more than Curation while producing clearly better reasoning data.
- **Generalization (heterogeneous teachers):**
  - MATH500: 94.8 for CoRD, versus 93.4 for Curation and 92.1 without distillation.
  - TaTQA (out-of-domain, table-based): 95.2, versus 88.2 and 87.3.
  - PubMedQA (open-ended): 91.8, versus 88.4 and 86.0.
- **PubMedQA setup:** a new distillation set of 456 samples was built, and an R1-Qwen-32B student was trained on it.
- **Resources:** traces were generated with 4 language models, including Hugging Face checkpoints and an OpenAI API model. The dataset and model are released at github.com/DISL-Lab/CoRD.
- **Limitations:** the main evaluation uses monolingual AIME24/AIME25 benchmarks, so multilingual transfer remains untested. Training uses SFT only, without preference learning such as DPO.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Korea Advanced Institute of Science and Technology](https://md.research.elamur.ai/free/en/universities/korea-advanced-institute-of-science-and-technology/) — University, Daejeon, South Korea · 56 works · 3,269 citations
- [Ulsan National Institute of Science and Technology](https://md.research.elamur.ai/free/en/universities/ulsan-national-institute-of-science-and-technology/) — University, Ulsan, South Korea · 3 works

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Taewon Yun, Jisu Shin, Jeonghwan Choi, Seunghwan Bang and Hwanjun Song. 2026. Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yun2026distilling,
  title = {{Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding}},
  author = {Taewon Yun, Jisu Shin, Jeonghwan Choi, Seunghwan Bang and Hwanjun Song},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1867},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1867}
}
```

- [← previous Distilling Large Embeddings via Hyperspherical Householder Quantization](https://md.research.elamur.ai/free/en/papers/wang-2026-distilling-large-embeddings-hyperspherical-householder/)
- [next → Distributional Alignment for Large Language Models under Domain Shift](https://md.research.elamur.ai/free/en/papers/pham-2026-distributional-alignment-large-language-models/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/)

## References

34 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Sahaj Agarwal, Ahmed Awadallah, Vidhisha Balachandran, Harkirat Behl, Lingjiao Chen, Gustavo de Rosa, Suriya Gunasekar, Mojan Javaheripi, Neel Joshi, et al. 2025. [Phi-4-reasoning technical report](https://md.research.elamur.ai/free/en/papers/abdin-2025-phi-4-reasoning-technical-report/). arXiv preprint arXiv:2504.21318.
2. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, et al. 2024. [Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling](https://md.research.elamur.ai/free/en/papers/chen-2024-expanding-performance-boundaries-open/). arXiv preprint arXiv:2412.05271.
3. Xidong Feng, Ziyu Wan, Muning Wen, Stephen Marcus McAleer, Ying Wen, Weinan Zhang, and Jun Wang. 2023. Alphazero-like tree-search can guide large language model decoding and training. arXiv preprint arXiv:2309.17179. [find](https://scholar.google.com/scholar?q=Xidong+Feng%2C+Ziyu+Wan%2C+Muning+Wen%2C+Stephen+Marcus+McAleer%2C+Ying+Wen%2C+Weinan+Zhang%2C+and+Jun+Wang%2E+2023%2E+Alphazero%2Dlike+tree%2Dsearch+can+guide+large+language+model+decoding+and+training%2E+arXiv+preprint+a)
4. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
5. Chengbo He, Bochao Zou, Xin Li, Jiansheng Chen, Junliang Xing, and Huimin Ma. 2024. Enhancing llm reasoning with multi-path collaborative reactive and reflection agents. arXiv preprint arXiv:2501.00430. — [arXiv:2501.00430](https://arxiv.org/abs/2501.00430) [find](https://scholar.google.com/scholar?q=Chengbo+He%2C+Bochao+Zou%2C+Xin+Li%2C+Jiansheng+Chen%2C+Junliang+Xing%2C+and+Huimin+Ma%2E+2024%2E+Enhancing+llm+reasoning+with+multi%2Dpath+collaborative+reactive+and+reflection+agents%2E+arXiv+preprint+arXiv%3A2501%2E0043)
6. Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Zhongyuan Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, et al. 2025. [Can large language models detect errors in long chain-of-thought reasoning?](https://md.research.elamur.ai/free/en/papers/he-2025-can-large-language-models-detect/) In ACL.
7. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). In NeurIPS.
8. Yury Kuratov, Aydar Bulatov, Petr Anokhin, Ivan Rodkin, Dmitry Sorokin, Artyom Sorokin, and Mikhail Burtsev. 2024. [Babilong: Testing the limits of llms with long context reasoning-in-a-haystack](https://md.research.elamur.ai/free/en/papers/kuratov-2024-babilong-testing-limits-llms-long/).
9. Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang, Xiangru Peng, and Jiaya Jia. 2024. [Step-dpo: Stepwise preference optimization for long-chain reasoning of llms](https://md.research.elamur.ai/free/en/papers/lai-2024-step-dpo-step-wise-preference/). arXiv preprint arXiv:2406.18629.
10. Yang Li, Youssef Emad, Karthik Padthe, Jack Lanchantin, Weizhe Yuan, Thao Nguyen, Jason Weston, Shang-Wen Li, Dong Wang, Ilia Kulikov, et al. 2025a. Naturalthoughts: Selecting and distilling reasoning traces for general reasoning tasks. arXiv preprint arXiv:2507.01921. — [arXiv:2507.01921](https://arxiv.org/abs/2507.01921) [find](https://scholar.google.com/scholar?q=Yang+Li%2C+Youssef+Emad%2C+Karthik+Padthe%2C+Jack+Lanchantin%2C+Weizhe+Yuan%2C+Thao+Nguyen%2C+Jason+Weston%2C+Shang%2DWen+Li%2C+Dong+Wang%2C+Ilia+Kulikov%2C+et+al%2E+2025a%2E+Naturalthoughts%3A+Selecting+and+distilling+reasoning)
11. Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, and Radha Poovendran. 2025b. [Small models struggle to learn from strong reasoners](https://md.research.elamur.ai/free/en/papers/li-2025-small-models-struggle-learn-strong/). arXiv preprint arXiv:2502.12143.
12. Zhiyuan Li, Yi Chang, and Yuan Wu. 2025c. Thinkbench: Evaluating thinking efficiency and chain-of-thought quality of large reasoning models. arXiv preprint arXiv:2505.22113. — [arXiv:2505.22113](https://arxiv.org/abs/2505.22113) [find](https://scholar.google.com/scholar?q=Zhiyuan+Li%2C+Yi+Chang%2C+and+Yuan+Wu%2E+2025c%2E+Thinkbench%3A+Evaluating+thinking+efficiency+and+chain%2Dof%2Dthought+quality+of+large+reasoning+models%2E+arXiv+preprint+arXiv%3A2505%2E22113%2E+%E2%80%94+%5BarXiv%3A2505%2E22113%5D%28https)
13. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173.
14. Weicheng Ma, Hefan Zhang, Ivory Yang, Shiyu Ji, Joice Chen, Farnoosh Hashemi, Shubham Mohole, Ethan Gearey, Michael Macy, Saeed Hassanpour, et al. 2025. Communication is all you need: Persuasion dataset construction via multi-llm communication. In NAACL. [find](https://scholar.google.com/scholar?q=Weicheng+Ma%2C+Hefan+Zhang%2C+Ivory+Yang%2C+Shiyu+Ji%2C+Joice+Chen%2C+Farnoosh+Hashemi%2C+Shubham+Mohole%2C+Ethan+Gearey%2C+Michael+Macy%2C+Saeed+Hassanpour%2C+et+al%2E+2025%2E+Communication+is+all+you+need%3A+Persuasion+datas)
15. Sungjin Park, Xiao Liu, Yeyun Gong, and Edward Choi. 2025. Ensembling large language models with process reward-guided tree search for better complex reasoning. In NAACL. [find](https://scholar.google.com/scholar?q=Sungjin+Park%2C+Xiao+Liu%2C+Yeyun+Gong%2C+and+Edward+Choi%2E+2025%2E+Ensembling+large+language+models+with+process+reward%2Dguided+tree+search+for+better+complex+reasoning%2E+In+NAACL%2E)
16. Aske Plaat, Annie Wong, Suzan Verberne, Joost Broekens, Niki van Stein, and Thomas Bäck. 2024. [Reasoning with large language models, a survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). CoRR.
17. Yuxiao Qu, Matthew YR Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, and Aviral Kumar. 2025. Optimizing test-time compute via meta reinforcement fine-tuning. arXiv preprint arXiv:2503.07572. [find](https://scholar.google.com/scholar?q=Yuxiao+Qu%2C+Matthew+YR+Yang%2C+Amrith+Setlur%2C+Lewis+Tunstall%2C+Edward+Emanuel+Beeching%2C+Ruslan+Salakhutdinov%2C+and+Aviral+Kumar%2E+2025%2E+Optimizing+test%2Dtime+compute+via+meta+reinforcement+fine%2Dtuning%2E+arXiv)
18. Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In KDD. [find](https://scholar.google.com/scholar?q=Jeff+Rasley%2C+Samyam+Rajbhandari%2C+Olatunji+Ruwase%2C+and+Yuxiong+He%2E+2020%2E+Deepspeed%3A+System+optimizations+enable+training+deep+learning+models+with+over+100+billion+parameters%2E+In+KDD%2E)
19. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. [Scaling llm test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint arXiv:2408.03314.
20. Hwanjun Song, Jeonghwan Choi, and Minseok Kim. 2025a. Ext2gen: Alignment through unified extraction and generation for robust retrieval-augmented generation. In WSDM. [find](https://scholar.google.com/scholar?q=Hwanjun+Song%2C+Jeonghwan+Choi%2C+and+Minseok+Kim%2E+2025a%2E+Ext2gen%3A+Alignment+through+unified+extraction+and+generation+for+robust+retrieval%2Daugmented+generation%2E+In+WSDM%2E)
21. Hwanjun Song, Taewon Yun, Yuho Lee, Jihwan Oh, Gihun Lee, Jason Cai, and Hang Su. 2025b. Learning to summarize from llm-generated feedback. In NAACL. [find](https://scholar.google.com/scholar?q=Hwanjun+Song%2C+Taewon+Yun%2C+Yuho+Lee%2C+Jihwan+Oh%2C+Gihun+Lee%2C+Jason+Cai%2C+and+Hang+Su%2E+2025b%2E+Learning+to+summarize+from+llm%2Dgenerated+feedback%2E+In+NAACL%2E)
22. Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, and James Zou. 2024. [Mixture-of-agents enhances large language model capabilities](https://md.research.elamur.ai/free/en/papers/wang-2024-mixture-agents-enhances-large/). arXiv preprint arXiv:2406.04692.
23. Wang Yang, Hongye Jin, Jingfeng Yang, Vipin Chaudhary, and Xiaotian Han. 2025. Thinking preference optimization. arXiv preprint arXiv:2502.13173. — [arXiv:2502.13173](https://arxiv.org/abs/2502.13173) [find](https://scholar.google.com/scholar?q=Wang+Yang%2C+Hongye+Jin%2C+Jingfeng+Yang%2C+Vipin+Chaudhary%2C+and+Xiaotian+Han%2E+2025%2E+Thinking+preference+optimization%2E+arXiv+preprint+arXiv%3A2502%2E13173%2E+%E2%80%94+%5BarXiv%3A2502%2E13173%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E13173%29)
24. Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, Yuxin Song, Haocheng Feng, Li Shen, et al. 2025. Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search. In NeurIPS. [find](https://scholar.google.com/scholar?q=Huanjin+Yao%2C+Jiaxing+Huang%2C+Wenhao+Wu%2C+Jingyi+Zhang%2C+Yibo+Wang%2C+Shunyu+Liu%2C+Yingjie+Wang%2C+Yuxin+Song%2C+Haocheng+Feng%2C+Li+Shen%2C+et+al%2E+2025%2E+Mulberry%3A+Empowering+mllm+with+o1%2Dlike+reasoning+and+reflecti)
25. Yixin Ye, Zhen Huang, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu. 2025. [Limo: Less is more for reasoning](https://md.research.elamur.ai/free/en/papers/ye-2025-limo-less-more-reasoning/). In COLM.
26. Edward Yeo, Yuxuan Tong, Morry Niu, Graham Neubig, and Xiang Yue. 2025. [Demystifying long chain-of-thought reasoning in llms](https://md.research.elamur.ai/free/en/papers/yeo-2025-demystifying-long-chain-thought-reasoning/). In ICML.
27. Huifeng Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Bo Zeng, Hao Wang, Tianqi Shi, Liangying Shao, Chenyang Lyu, Longyue Wang, et al. 2025. Towards widening the distillation bottleneck for reasoning models. CoRR. [find](https://scholar.google.com/scholar?q=Huifeng+Yin%2C+Yu+Zhao%2C+Minghao+Wu%2C+Xuanfan+Ni%2C+Bo+Zeng%2C+Hao+Wang%2C+Tianqi+Shi%2C+Liangying+Shao%2C+Chenyang+Lyu%2C+Longyue+Wang%2C+et+al%2E+2025%2E+Towards+widening+the+distillation+bottleneck+for+reasoning+models%2E)
28. Wenyuan Zhang, Shuaiyi Nie, Xinghua Zhang, Zefeng Zhang, and Tingwen Liu. 2025. S1-bench: A simple benchmark for evaluating system 1 thinking capability of large reasoning models. arXiv preprint arXiv:2504.10368. — [arXiv:2504.10368](https://arxiv.org/abs/2504.10368) [find](https://scholar.google.com/scholar?q=Wenyuan+Zhang%2C+Shuaiyi+Nie%2C+Xinghua+Zhang%2C+Zefeng+Zhang%2C+and+Tingwen+Liu%2E+2025%2E+S1%2Dbench%3A+A+simple+benchmark+for+evaluating+system+1+thinking+capability+of+large+reasoning+models%2E+arXiv+preprint+arXiv)
29. Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, and Tat-Seng Chua. 2021. [Tat-qa: A question answering benchmark on a hybrid of tabular and textual content in finance](https://md.research.elamur.ai/free/en/papers/zhu-2021-tat-qa-question-answering-benchmark/). In ACL.
30. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In NeurIPS.
31. Linjuan Wu, Hao-Ran Wei, Baosong Yang, and Weiming Lu. 2025a. From english to second language mastery: Enhancing llms with cross-lingual continued instruction tuning. In ACL. [find](https://scholar.google.com/scholar?q=Linjuan+Wu%2C+Hao%2DRan+Wei%2C+Baosong+Yang%2C+and+Weiming+Lu%2E+2025a%2E+From+english+to+second+language+mastery%3A+Enhancing+llms+with+cross%2Dlingual+continued+instruction+tuning%2E+In+ACL%2E)
32. Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, and Meng Jiang. 2025b. [Enhancing mathematical reasoning in llms by stepwise correction](https://md.research.elamur.ai/free/en/papers/wu-2025-enhancing-mathematical-reasoning-llms-stepwise/). In ACL.
33. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yang%2C+Jin)
34. Model Name Checkpoints R1-Qwen-32B (Guo et al., 2025) QwQ-32B (Yang et al., 2024) Phi4-Reasoning-Plus (Abdin et al., 2025) GPT5o-mini deepseek-ai/DeepSeek-R1-Distill-Qwen-32B Qwen/QwQ-32B microsoft/Phi-4-reasoning-plus gpt5o-mini (OpenAI) *Table 8: Checkpoints of the 4 reasoning generation models. F… [find](https://scholar.google.com/scholar?q=Model+Name+Checkpoints+R1%2DQwen%2D32B+%28Guo+et+al%2E%2C+2025%29+QwQ%2D32B+%28Yang+et+al%2E%2C+2024%29+Phi4%2DReasoning%2DPlus+%28Abdin+et+al%2E%2C+2025%29+GPT5o%2Dmini+deepseek%2Dai%2FDeepSeek%2DR1%2DDistill%2DQwen%2D32B+Qwen%2FQwQ%2D32B+microsoft%2FPh)

*Updated 2 November 2026*