References

本文为论文《s1：用简单方法实现测试时计算扩展》「论文原文」板块的对应章节，按 arXiv 官方全文逐字保留，层级与「中文全文翻译」板块一一对应。

  • Ankner et al. (2024)

Ankner, Z., Paul, M., Cui, B., Chang, J. D., and Ammanabrolu, P.

Critique-out-loud reward models, 2024.

URL https://arxiv.org/abs/2408.11791.

  • Arora et al. (2023)

Arora, D., Singh, H. G., and Mausam.

Have llms advanced enough? a challenging problem solving benchmark for large language models, 2023.

URL https://arxiv.org/abs/2305.15074.

  • Azerbayev et al. (2023)

Azerbayev, Z., Schoelkopf, H., Paster, K., Santos, M. D., McAleer, S., Jiang, A. Q., Deng, J., Biderman, S., and Welleck, S.

Llemma: An open language model for mathematics, 2023.

  • Bi et al. (2023)

Bi, Z., Zhang, N., Jiang, Y., Deng, S., Zheng, G., and Chen, H.

When do program-of-thoughts work for reasoning?, 2023.

URL https://arxiv.org/abs/2308.15452.

  • Biderman et al. (2024)

Biderman, S., Schoelkopf, H., Sutawika, L., Gao, L., Tow, J., Abbasi, B., Aji, A. F., Ammanamanchi, P. S., Black, S., Clive, J., DiPofi, A., Etxaniz, J., Fattori, B., Forde, J. Z., Foster, C., Hsu, J., Jaiswal, M., Lee, W. Y., Li, H., Lovering, C., Muennighoff, N., Pavlick, E., Phang, J., Skowron, A., Tan, S., Tang, X., Wang, K. A., Winata, G. I., Yvon, F., and Zou, A.

Lessons from the trenches on reproducible evaluation of language models, 2024.

  • Brown et al. (2024)

Brown, B., Juravsky, J., Ehrlich, R., Clark, R., Le, Q. V., Ré, C., and Mirhoseini, A.

Large language monkeys: Scaling inference compute with repeated sampling, 2024.

URL https://arxiv.org/abs/2407.21787.

  • Chen et al. (2023)

Chen, W., Yin, M., Ku, M., Lu, P., Wan, Y., Ma, X., Xu, J., Wang, X., and Xia, T.

Theoremqa: A theorem-driven question answering dataset, 2023.

URL https://arxiv.org/abs/2305.12524.

  • Choi et al. (2023)

Choi, S., Fang, T., Wang, Z., and Song, Y.

Kcts: Knowledge-constrained tree search decoding with token-level hallucination detection, 2023.

URL https://arxiv.org/abs/2310.09044.

  • DeepSeek-AI et al. (2025)

DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., Zhang, X., Yu, X., Wu, Y., Wu, Z. F., Gou, Z., Shao, Z., Li, Z., Gao, Z., Liu, A., Xue, B., Wang, B., Wu, B., Feng, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., Dai, D., Chen, D., Ji, D., Li, E., Lin, F., Dai, F., Luo, F., Hao, G., Chen, G., Li, G., Zhang, H., Bao, H., Xu, H., Wang, H., Ding, H., Xin, H., Gao, H., Qu, H., Li, H., Guo, J., Li, J., Wang, J., Chen, J., Yuan, J., Qiu, J., Li, J., Cai, J. L., Ni, J., Liang, J., Chen, J., Dong, K., Hu, K., Gao, K., Guan, K., Huang, K., Yu, K., Wang, L., Zhang, L., Zhao, L., Wang, L., Zhang, L., Xu, L., Xia, L., Zhang, M., Zhang, M., Tang, M., Li, M., Wang, M., Li, M., Tian, N., Huang, P., Zhang, P., Wang, Q., Chen, Q., Du, Q., Ge, R., Zhang, R., Pan, R., Wang, R., Chen, R. J., Jin, R. L., Chen, R., Lu, S., Zhou, S., Chen, S., Ye, S., Wang, S., Yu, S., Zhou, S., Pan, S., Li, S. S., Zhou, S., Wu, S., Ye, S., Yun, T., Pei, T., Sun, T., Wang, T., Zeng, W., Zhao, W., Liu, W., Liang, W., Gao, W., Yu, W., Zhang, W., Xiao, W. L., An, W., Liu, X., Wang, X., Chen, X., Nie, X., Cheng, X., Liu, X., Xie, X., Liu, X., Yang, X., Li, X., Su, X., Lin, X., Li, X. Q., Jin, X., Shen, X., Chen, X., Sun, X., Wang, X., Song, X., Zhou, X., Wang, X., Shan, X., Li, Y. K., Wang, Y. Q., Wei, Y. X., Zhang, Y., Xu, Y., Li, Y., Zhao, Y., Sun, Y., Wang, Y., Yu, Y., Zhang, Y., Shi, Y., Xiong, Y., He, Y., Piao, Y., Wang, Y., Tan, Y., Ma, Y., Liu, Y., Guo, Y., Ou, Y., Wang, Y., Gong, Y., Zou, Y., He, Y., Xiong, Y., Luo, Y., You, Y., Liu, Y., Zhou, Y., Zhu, Y. X., Xu, Y., Huang, Y., Li, Y., Zheng, Y., Zhu, Y., Ma, Y., Tang, Y., Zha, Y., Yan, Y., Ren, Z. Z., Ren, Z., Sha, Z., Fu, Z., Xu, Z., Xie, Z., Zhang, Z., Hao, Z., Ma, Z., Yan, Z., Wu, Z., Gu, Z., Zhu, Z., Liu, Z., Li, Z., Xie, Z., Song, Z., Pan, Z., Huang, Z., Xu, Z., Zhang, Z., and Zhang, Z.

Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

URL https://arxiv.org/abs/2501.12948.

  • Fu et al. (2023)

Fu, Y., Peng, H., Sabharwal, A., Clark, P., and Khot, T.

Complexity-based prompting for multi-step reasoning, 2023.

URL https://arxiv.org/abs/2210.00720.

  • Gandhi et al. (2024)

Gandhi, K., Lee, D., Grand, G., Liu, M., Cheng, W., Sharma, A., and Goodman, N. D.

Stream of search (sos): Learning to search in language, 2024.

URL https://arxiv.org/abs/2404.03683.

  • Gao et al. (2024a)

Gao, B., Song, F., Yang, Z., Cai, Z., Miao, Y., Dong, Q., Li, L., Ma, C., Chen, L., Xu, R., Tang, Z., Wang, B., Zan, D., Quan, S., Zhang, G., Sha, L., Zhang, Y., Ren, X., Liu, T., and Chang, B.

Omni-math: A universal olympiad level mathematic benchmark for large language models, 2024a.

URL https://arxiv.org/abs/2410.07985.

  • Gao et al. (2021)

Gao, L., Tow, J., Biderman, S., Black, S., DiPofi, A., Foster, C., Golding, L., Hsu, J., McDonell, K., Muennighoff, N., Phang, J., Reynolds, L., Tang, E., Thite, A., Wang, B., Wang, K., and Zou, A.

A framework for few-shot language model evaluation, September 2021.

URL https://doi.org/10.5281/zenodo.5371628.

  • Gao et al. (2024b)

Gao, Z., Niu, B., He, X., Xu, H., Liu, H., Liu, A., Hu, X., and Wen, L.

Interpretable contrastive monte carlo tree search reasoning, 2024b.

URL https://arxiv.org/abs/2410.01707.

  • Glazer et al. (2024)

Glazer, E., Erdil, E., Besiroglu, T., Chicharro, D., Chen, E., Gunning, A., Olsson, C. F., Denain, J.-S., Ho, A., de Oliveira Santos, E., Järviniemi, O., Barnett, M., Sandler, R., Vrzala, M., Sevilla, J., Ren, Q., Pratt, E., Levine, L., Barkley, G., Stewart, N., Grechuk, B., Grechuk, T., Enugandla, S. V., and Wildon, M.

Frontiermath: A benchmark for evaluating advanced mathematical reasoning in ai, 2024.

URL https://arxiv.org/abs/2411.04872.

  • Google (2024)

Google.

Gemini 2.0 flash thinking mode (gemini-2.0-flash-thinking-exp-1219), December 2024.

URL https://cloud.google.com/vertex-ai/generative-ai/docs/thinking-mode.

  • He et al. (2024a)

He, C., Luo, R., Bai, Y., Hu, S., Thai, Z. L., Shen, J., Hu, J., Han, X., Huang, Y., Zhang, Y., Liu, J., Qi, L., Liu, Z., and Sun, M.

Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024a.

URL https://arxiv.org/abs/2402.14008.

  • He et al. (2024b)

He, C., Luo, R., Bai, Y., Hu, S., Thai, Z. L., Shen, J., Hu, J., Han, X., Huang, Y., Zhang, Y., Liu, J., Qi, L., Liu, Z., and Sun, M.

Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024b.

URL https://arxiv.org/abs/2402.14008.

  • Hendrycks et al. (2021)

Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J.

Measuring mathematical problem solving with the math dataset, 2021.

URL https://arxiv.org/abs/2103.03874.

  • Hoffmann et al. (2022)

Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., de Las Casas, D., Hendricks, L. A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Rae, J. W., Vinyals, O., and Sifre, L.

Training compute-optimal large language models, 2022.

URL https://arxiv.org/abs/2203.15556.

  • Hou et al. (2025)

Hou, Z., Lv, X., Lu, R., Zhang, J., Li, Y., Yao, Z., Li, J., Tang, J., and Dong, Y.

Advancing language model reasoning through reinforcement learning and inference scaling, 2025.

URL https://arxiv.org/abs/2501.11651.

  • Hu et al. (2024)

Hu, Y., Shi, W., Fu, X., Roth, D., Ostendorf, M., Zettlemoyer, L., Smith, N. A., and Krishna, R.

Visual sketchpad: Sketching as a visual chain of thought for multimodal language models, 2024.

URL https://arxiv.org/abs/2406.09403.

  • Huang et al. (2024a)

Huang, Z., Wang, Z., Xia, S., Li, X., Zou, H., Xu, R., Fan, R.-Z., Ye, L., Chern, E., Ye, Y., Zhang, Y., Yang, Y., Wu, T., Wang, B., Sun, S., Xiao, Y., Li, Y., Zhou, F., Chern, S., Qin, Y., Ma, Y., Su, J., Liu, Y., Zheng, Y., Zhang, S., Lin, D., Qiao, Y., and Liu, P.

Olympicarena: Benchmarking multi-discipline cognitive reasoning for superintelligent ai, 2024a.

URL https://arxiv.org/abs/2406.12753.

  • Huang et al. (2024b)

Huang, Z., Zou, H., Li, X., Liu, Y., Zheng, Y., Chern, E., Xia, S., Qin, Y., Yuan, W., and Liu, P.

O1 replication journey – part 2: Surpassing o1-preview through simple distillation, big progress or bitter lesson?, 2024b.

URL https://arxiv.org/abs/2411.16489.

  • Irvine et al. (2023)

Irvine, R., Boubert, D., Raina, V., Liusie, A., Zhu, Z., Mudupalli, V., Korshuk, A., Liu, Z., Cremer, F., Assassi, V., Beauchamp, C.-C., Lu, X., Rialan, T., and Beauchamp, W.

Rewarding chatbots for real-world engagement with millions of users, 2023.

URL https://arxiv.org/abs/2303.06135.

  • Jain et al. (2024a)

Jain, N., Han, K., Gu, A., Li, W.-D., Yan, F., Zhang, T., Wang, S., Solar-Lezama, A., Sen, K., and Stoica, I.

Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024a.

URL https://arxiv.org/abs/2403.07974.

  • Jain et al. (2024b)

Jain, N., Han, K., Gu, A., Li, W.-D., Yan, F., Zhang, T., Wang, S., Solar-Lezama, A., Sen, K., and Stoica, I.

Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024b.

URL https://arxiv.org/abs/2403.07974.

  • Kapfer et al. (2025)

Kapfer, C., Stine, K., Narasimhan, B., Mentzel, C., and Candes, E.

Marlowe: Stanford’s gpu-based computational instrument, January 2025.

URL https://doi.org/10.5281/zenodo.14751899.

  • Kaplan et al. (2020)

Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D.

Scaling laws for neural language models, 2020.

URL https://arxiv.org/abs/2001.08361.

  • Kim et al. (2024)

Kim, E., Suk, J., Kim, S., Muennighoff, N., Kim, D., and Oh, A.

Llm-as-an-interviewer: Beyond static testing through dynamic llm evaluation, 2024.

URL https://arxiv.org/abs/2412.10424.

  • Kwon et al. (2023)

Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., and Stoica, I.

Efficient memory management for large language model serving with pagedattention, 2023.

URL https://arxiv.org/abs/2309.06180.

  • Labs (2025)

Labs, B.

Bespoke-stratos: The unreasonable effectiveness of reasoning distillation, 2025.

URL https://hf.co/bespokelabs/Bespoke-Stratos-32B.

Accessed: 2025-01-22.

  • Lee et al. (2025)

Lee, K.-H., Fischer, I., Wu, Y.-H., Marwood, D., Baluja, S., Schuurmans, D., and Chen, X.

Evolving deeper llm thinking, 2025.

URL https://arxiv.org/abs/2501.09891.

  • LI et al. (2024)

LI, J., Beeching, E., Tunstall, L., Lipkin, B., Soletskyi, R., Huang, S. C., Rasul, K., Yu, L., Jiang, A., Shen, Z., Qin, Z., Dong, B., Zhou, L., Fleureau, Y., Lample, G., and Polu, S.

Numinamath, 2024.

URL https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf.

  • Lightman et al. (2023)

Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., and Cobbe, K.

Let’s verify step by step, 2023.

URL https://arxiv.org/abs/2305.20050.

  • Ling et al. (2017)

Ling, W., Yogatama, D., Dyer, C., and Blunsom, P.

Program induction by rationale generation : Learning to solve and explain algebraic word problems, 2017.

URL https://arxiv.org/abs/1705.04146.

  • Liu et al. (2020)

Liu, J., Cui, L., Liu, H., Huang, D., Wang, Y., and Zhang, Y.

Logiqa: A challenge dataset for machine reading comprehension with logical reasoning, 2020.

URL https://arxiv.org/abs/2007.08124.

  • Liu et al. (2024)

Liu, J., Cohen, A., Pasunuru, R., Choi, Y., Hajishirzi, H., and Celikyilmaz, A.

Don’t throw away your value model! generating more preferable text with value-guided monte-carlo tree search decoding, 2024.

URL https://arxiv.org/abs/2309.15028.

  • Loshchilov & Hutter (2019)

Loshchilov, I. and Hutter, F.

Decoupled weight decay regularization, 2019.

  • Luo et al. (2025)

Luo, H., Sun, Q., Xu, C., Zhao, P., Lou, J., Tao, C., Geng, X., Lin, Q., Chen, S., Tang, Y., and Zhang, D.

Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct, 2025.

URL https://arxiv.org/abs/2308.09583.

  • of America (2024)

of America, M. A.

Aime, February 2024.

URL https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions/.

  • OpenAI (2024)

OpenAI.

Learning to reason with llms, September 2024.

URL https://openai.com/index/learning-to-reason-with-llms/.

  • Phan et al. (2025)

Phan, L., Gatti, A., Han, Z., Li, N., Hu, J., Zhang, H., Shi, S., Choi, M., Agrawal, A., Chopra, A., Khoja, A., Kim, R., Hausenloy, J., Zhang, O., Mazeika, M., Anderson, D., Nguyen, T., Mahmood, M., Feng, F., Feng, S. Y., Zhao, H., Yu, M., Gangal, V., Zou, C., Wang, Z., Wang, J. P., Kumar, P., Pokutnyi, O., Gerbicz, R., Popov, S., Levin, J.-C., Kazakov, M., Schmitt, J., Galgon, G., Sanchez, A., Lee, Y., Yeadon, W., Sauers, S., Roth, M., Agu, C., Riis, S., Giska, F., Utpala, S., Giboney, Z., Goshu, G. M., of Arc Xavier, J., Crowson, S.-J., Naiya, M. M., Burns, N., Finke, L., Cheng, Z., Park, H., Fournier-Facio, F., Wydallis, J., Nandor, M., Singh, A., Gehrunger, T., Cai, J., McCarty, B., Duclosel, D., Nam, J., Zampese, J., Hoerr, R. G., Bacho, A., Loume, G. A., Galal, A., Cao, H., Garretson, A. C., Sileo, D., Ren, Q., Cojoc, D., Arkhipov, P., Qazi, U., Li, L., Motwani, S., de Witt, C. S., Taylor, E., Veith, J., Singer, E., Hartman, T. D., Rissone, P., Jin, J., Shi, J. W. L., Willcocks, C. G., Robinson, J., Mikov, A., Prabhu, A., Tang, L., Alapont, X., Uro, J. L., Zhou, K., de Oliveira Santos, E., Maksimov, A. P., Vendrow, E., Zenitani, K., Guillod, J., Li, Y., Vendrow, J., Kuchkin, V., Ze-An, N., Marion, P., Efremov, D., Lynch, J., Liang, K., Gritsevskiy, A., Martinez, D., Pageler, B., Crispino, N., Zvonkine, D., Fraga, N. W., Soori, S., Press, O., Tang, H., Salazar, J., Green, S. R., Brüssel, L., Twayana, M., Dieuleveut, A., Rogers, T. R., Zhang, W., Li, B., Yang, J., Rao, A., Loiseau, G., Kalinin, M., Lukas, M., Manolescu, C., Mishra, S., Kamdoum, A. G. K., Kreiman, T., Hogg, T., Jin, A., Bosio, C., Sun, G., Coppola, B. P., Tarver, T., Heidinger, H., Sayous, R., Ivanov, S., Cavanagh, J. M., Shen, J., Imperial, J. M., Schwaller, P., Senthilkuma, S., Bran, A. M., Dehghan, A., Algaba, A., Verbeken, B., Noever, D., V, R. P., Schut, L., Sucholutsky, I., Zheltonozhskii, E., Lim, D., Stanley, R., Sivarajan, S., Yang, T., Maar, J., Wykowski, J., Oller, M., Sandlin, J., Sahu, A., Hu, Y., Fish, S., Heydari, N., Apronti, A., Rawal, K., Vilchis, T. G., Zu, Y., Lackner, M., Koppel, J., Nguyen, J., Antonenko, D. S., Chern, S., Zhao, B., Arsene, P., Goldfarb, A., Ivanov, S., Poświata, R., Wang, C., Li, D., Crisostomi, D., Achilleos, A., Myklebust, B., Sen, A., Perrella, D., Kaparov, N., Inlow, M. H., Zang, A., Thornley, E., Orel, D., Poritski, V., Ben-David, S., Berger, Z., Whitfill, P., Foster, M., Munro, D., Ho, L., Hava, D. B., Kuchkin, A., Lauff, R., Holmes, D., Sommerhage, F., Schneider, K., Kazibwe, Z., Stambaugh, N., Singh, M., Magoulas, I., Clarke, D., Kim, D. H., Dias, F. M., Elser, V., Agarwal, K. P., Vilchis, V. E. G., Klose, I., Demian, C., Anantheswaran, U., Zweiger, A., Albani, G., Li, J., Daans, N., Radionov, M., Rozhoň, V., Ma, Z., Stump, C., Berkani, M., Platnick, J., Nevirkovets, V., Basler, L., Piccardo, M., Jeanplong, F., Cohen, N., Tkadlec, J., Rosu, P., Padlewski, P., Barzowski, S., Montgomery, K., Menezes, A., Patel, A., Wang, Z., Tucker-Foltz, J., Stade, J., Goertzen, T., Kazemi, F., Milbauer, J., Ambay, J. A., Shukla, A., Labrador, Y. C. L., Givré, A., Wolff, H., Rossbach, V., Aziz, M. F., Kaddar, Y., Chen, Y., Zhang, R., Pan, J., Terpin, A., Muennighoff, N., Schoelkopf, H., Zheng, E., Carmi, A., Jones, A., Shah, J., Brown, E. D. L., Zhu, K., Bartolo, M., Wheeler, R., Ho, A., Barkan, S., Wang, J., Stehberger, M., Kretov, E., Sridhar, K., EL-Wasif, Z., Zhang, A., Pyda, D., Tam, J., Cunningham, D. M., Goryachev, V., Patramanis, D., Krause, M., Redenti, A., Bugas, D., Aldous, D., Lai, J., Coleman, S., Bahaloo, M., Xu, J., Lee, S., Zhao, S., Tang, N., Cohen, M. K., Carroll, M., Paradise, O., Kirchner, J. H., Steinerberger, S., Ovchynnikov, M., Matos, J. O., Shenoy, A., de Oliveira Junior, B. A., Wang, M., Nie, Y., Giordano, P., Petersen, P., Sztyber-Betley, A., Shukla, P., Crozier, J., Pinto, A., Verma, S., Joshi, P., Yong, Z.-X., Tee, A., Andréoletti, J., Weller, O., Singhal, R., Zhang, G., Ivanov, A., Khoury, S., Mostaghimi, H., Thaman, K., Chen, Q., Khánh, T. Q., Loader, J., Cavalleri, S., Szlyk, H., Brown, Z., Roberts, J., Alley, W., Sun, K., Stendall, R., Lamparth, M., Reuel, A., Wang, T., Xu, H., Raparthi, S. G., Hernández-Cámara, P., Martin, F., Malishev, D., Preu, T., Korbak, T., Abramovitch, M., Williamson, D., Chen, Z., Bálint, B., Bari, M. S., Kassani, P., Wang, Z., Ansarinejad, B., Goswami, L. P., Sun, Y., Elgnainy, H., Tordera, D., Balabanian, G., Anderson, E., Kvistad, L., Moyano, A. J., Maheshwari, R., Sakor, A., Eron, M., McAlister, I. C., Gimenez, J., Enyekwe, I., O., A. F. D., Shah, S., Zhou, X., Kamalov, F., Clark, R., Abdoli, S., Santens, T., Meer, K., Wang, H. K., Ramakrishnan, K., Chen, E., Tomasiello, A., Luca, G. B. D., Looi, S.-Z., Le, V.-K., Kolt, N., Mündler, N., Semler, A., Rodman, E., Drori, J., Fossum, C. J., Jagota, M., Pradeep, R., Fan, H., Shah, T., Eicher, J., Chen, M., Thaman, K., Merrill, W., Harris, C., Gross, J., Gusev, I., Sharma, A., Agnihotri, S., Zhelnov, P., Usawasutsakorn, S., Mofayezi, M., Bogdanov, S., Piperski, A., Carauleanu, M., Zhang, D. K., Ler, D., Leventov, R., Soroko, I., Jansen, T., Lauer, P., Duersch, J., Taamazyan, V., Morak, W., Ma, W., Held, W., Đuc Huy, T., Xian, R., Zebaze, A. R., Mohamed, M., Leser, J. N., Yuan, M. X., Yacar, L., Lengler, J., Shahrtash, H., Oliveira, E., Jackson, J. W., Gonzalez, D. E., Zou, A., Chidambaram, M., Manik, T., Haffenden, H., Stander, D., Dasouqi, A., Shen, A., Duc, E., Golshani, B., Stap, D., Uzhou, M., Zhidkovskaya, A. B., Lewark, L., Vincze, M., Wehr, D., Tang, C., Hossain, Z., Phillips, S., Muzhen, J., Ekström, F., Hammon, A., Patel, O., Remy, N., Farhidi, F., Medley, G., Mohammadzadeh, F., Peñaflor, M., Kassahun, H., Friedrich, A., Sparrow, C., Sakal, T., Dhamane, O., Mirabadi, A. K., Hallman, E., Battaglia, M., Maghsoudimehrabani, M., Hoang, H., Amit, A., Hulbert, D., Pereira, R., Weber, S., Mensah, S., Andre, N., Peristyy, A., Harjadi, C., Gupta, H., Malina, S., Albanie, S., Cai, W., Mehkary, M., Reidegeld, F., Dick, A.-K., Friday, C., Sidhu, J., Kim, W., Costa, M., Gurdogan, H., Weber, B., Kumar, H., Jiang, T., Agarwal, A., Ceconello, C., Vaz, W. S., Zhuang, C., Park, H., Tawfeek, A. R., Aggarwal, D., Kirchhof, M., Dai, L., Kim, E., Ferret, J., Wang, Y., Yan, M., Burdzy, K., Zhang, L., Franca, A., Pham, D. T., Loh, K. Y., Robinson, J., Gul, S., Chhablani, G., Du, Z., Cosma, A., White, C., Riblet, R., Saxena, P., Votava, J., Vinnikov, V., Delaney, E., Halasyamani, S., Shahid, S. M., Mourrat, J.-C., Vetoshkin, L., Bacho, R., Ginis, V., Maksapetyan, A., de la Rosa, F., Li, X., Malod, G., Lang, L., Laurendeau, J., Adesanya, F., Portier, J., Hollom, L., Souza, V., Zhou, Y. A., Yalın, Y., Obikoya, G. D., Arnaboldi, L., Rai, Bigi, F., Bacho, K., Clavier, P., Recchia, G., Popescu, M., Shulga, N., Tanwie, N. M., Lux, T. C. H., Rank, B., Ni, C., Yakimchyk, A., Huanxu, Liu, Häggström, O., Verkama, E., Narayan, H., Gundlach, H., Brito-Santana, L., Amaro, B., Vajipey, V., Grover, R., Fan, Y., e Silva, G. P. R., Xin, L., Kratish, Y., Łucki, J., Li, W.-D., Xu, J., Scaria, K. J., Vargus, F., Habibi, F., Long, Lian, Rodolà, E., Robins, J., Cheng, V., Grabb, D., Bosio, I., Fruhauff, T., Akov, I., Lo, E. J. Y., Qi, H., Jiang, X., Segev, B., Fan, J., Martinson, S., Wang, E. Y., Hausknecht, K., Brenner, M. P., Mao, M., Jiang, Y., Zhang, X., Avagian, D., Scipio, E. J., Siddiqi, M. R., Ragoler, A., Tan, J., Patil, D., Plecnik, R., Kirtland, A., Montecillo, R. G., Durand, S., Bodur, O. F., Adoul, Z., Zekry, M., Douville, G., Karakoc, A., Santos, T. C. B., Shamseldeen, S., Karim, L., Liakhovitskaia, A., Resman, N., Farina, N., Gonzalez, J. C., Maayan, G., Hoback, S., Pena, R. D. O., Sherman, G., Mariji, H., Pouriamanesh, R., Wu, W., Demir, G., Mendoza, S., Alarab, I., Cole, J., Ferreira, D., Johnson, B., Milliron, H., Safdari, M., Dai, L., Arthornthurasuk, S., Pronin, A., Fan, J., Ramirez-Trinidad, A., Cartwright, A., Pottmaier, D., Taheri, O., Outevsky, D., Stepanic, S., Perry, S., Askew, L., Rodríguez, R. A. H., Dendane, A., Ali, S., Lorena, R., Iyer, K., Salauddin, S. M., Islam, M., Gonzalez, J., Ducey, J., Campbell, R., Somrak, M., Mavroudis, V., Vergo, E., Qin, J., Borbás, B., Chu, E., Lindsey, J., Radhakrishnan, A., Jallon, A., McInnis, I. M. J., Hoover, A., Möller, S., Bian, S., Lai, J., Patwardhan, T., Yue, S., Wang, A., and Hendrycks, D.

Humanity’s last exam, 2025.

URL https://arxiv.org/abs/2501.14249.

  • Qwen et al. (2024)

Qwen, :, Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Wei, H., Lin, H., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Lin, J., Dang, K., Lu, K., Bao, K., Yang, K., Yu, L., Li, M., Xue, M., Zhang, P., Zhu, Q., Men, R., Lin, R., Li, T., Xia, T., Ren, X., Ren, X., Fan, Y., Su, Y., Zhang, Y., Wan, Y., Liu, Y., Cui, Z., Zhang, Z., and Qiu, Z.

Qwen2.5 technical report, 2024.

URL https://arxiv.org/abs/2412.15115.

  • Rein et al. (2023)

Rein, D., Hou, B. L., Stickland, A. C., Petty, J., Pang, R. Y., Dirani, J., Michael, J., and Bowman, S. R.

Gpqa: A graduate-level google-proof q&a benchmark, 2023.

URL https://arxiv.org/abs/2311.12022.

  • Shi et al. (2024)

Shi, Q., Tang, M., Narasimhan, K., and Yao, S.

Can language models solve olympiad programming?, 2024.

URL https://arxiv.org/abs/2404.10952.

  • Snell et al. (2024)

Snell, C., Lee, J., Xu, K., and Kumar, A.

Scaling llm test-time compute optimally can be more effective than scaling model parameters, 2024.

URL https://arxiv.org/abs/2408.03314.

  • Srivastava et al. (2023)

Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al.

Beyond the imitation game: Quantifying and extrapolating the capabilities of language models, 2023.

  • Su et al. (2024)

Su, H., Yen, H., Xia, M., Shi, W., Muennighoff, N., yu Wang, H., Liu, H., Shi, Q., Siegel, Z. S., Tang, M., Sun, R., Yoon, J., Arik, S. O., Chen, D., and Yu, T.

Bright: A realistic and challenging benchmark for reasoning-intensive retrieval, 2024.

URL https://arxiv.org/abs/2407.12883.

  • Sun et al. (2024)

Sun, L., Han, Y., Zhao, Z., Ma, D., Shen, Z., Chen, B., Chen, L., and Yu, K.

Scieval: A multi-level large language model evaluation benchmark for scientific research, 2024.

URL https://arxiv.org/abs/2308.13149.

  • Team (2024a)

Team, D.

Deepseek r1, November 2024a.

URL https://x.com/deepseek_ai/status/1859200141355536422.

  • Team et al. (2025)

Team, K., Du, A., Gao, B., Xing, B., Jiang, C., Chen, C., Li, C., Xiao, C., Du, C., Liao, C., Tang, C., Wang, C., Zhang, D., Yuan, E., Lu, E., Tang, F., Sung, F., Wei, G., Lai, G., Guo, H., Zhu, H., Ding, H., Hu, H., Yang, H., Zhang, H., Yao, H., Zhao, H., Lu, H., Li, H., Yu, H., Gao, H., Zheng, H., Yuan, H., Chen, J., Guo, J., Su, J., Wang, J., Zhao, J., Zhang, J., Liu, J., Yan, J., Wu, J., Shi, L., Ye, L., Yu, L., Dong, M., Zhang, N., Ma, N., Pan, Q., Gong, Q., Liu, S., Ma, S., Wei, S., Cao, S., Huang, S., Jiang, T., Gao, W., Xiong, W., He, W., Huang, W., Wu, W., He, W., Wei, X., Jia, X., Wu, X., Xu, X., Zu, X., Zhou, X., Pan, X., Charles, Y., Li, Y., Hu, Y., Liu, Y., Chen, Y., Wang, Y., Liu, Y., Qin, Y., Liu, Y., Yang, Y., Bao, Y., Du, Y., Wu, Y., Wang, Y., Zhou, Z., Wang, Z., Li, Z., Zhu, Z., Zhang, Z., Wang, Z., Yang, Z., Huang, Z., Huang, Z., Xu, Z., and Yang, Z.

Kimi k1.5: Scaling reinforcement learning with llms, 2025.

URL https://arxiv.org/abs/2501.12599.

  • Team (2025)

Team, N.

Sky-t1: Fully open-source reasoning model with o1-preview performance in $450 budget, 2025.

URL https://novasky-ai.github.io/posts/sky-t1.

Accessed: 2025-01-09.

  • Team (2024b)

Team, Q.

Qwq: Reflect deeply on the boundaries of the unknown, November 2024b.

URL https://qwenlm.github.io/blog/qwq-32b-preview/.

  • Wang et al. (2024a)

Wang, J., Meng, F., Liang, Y., and Zhou, J.

Drt-o1: Optimized deep reasoning translation via long chain-of-thought, 2024a.

URL https://arxiv.org/abs/2412.17498.

  • Wang et al. (2024b)

Wang, P., Li, L., Shao, Z., Xu, R. X., Dai, D., Li, Y., Chen, D., Wu, Y., and Sui, Z.

Math-shepherd: Verify and reinforce llms step-by-step without human annotations, 2024b.

URL https://arxiv.org/abs/2312.08935.

  • Wang et al. (2021)

Wang, S., Liu, Z., Zhong, W., Zhou, M., Wei, Z., Chen, Z., and Duan, N.

From lsat: The progress and challenges of complex reasoning, 2021.

URL https://arxiv.org/abs/2108.00648.

  • Wang et al. (2024c)

Wang, Z., Dong, Y., Delalleau, O., Zeng, J., Shen, G., Egert, D., Zhang, J. J., Sreedhar, M. N., and Kuchaiev, O.

Helpsteer2: Open-source dataset for training top-performing reward models, 2024c.

URL https://arxiv.org/abs/2406.08673.

  • Wei et al. (2023)

Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D.

Chain-of-thought prompting elicits reasoning in large language models, 2023.

URL https://arxiv.org/abs/2201.11903.

  • Welleck et al. (2024)

Welleck, S., Bertsch, A., Finlayson, M., Schoelkopf, H., Xie, A., Neubig, G., Kulikov, I., and Harchaoui, Z.

From decoding to meta-generation: Inference-time algorithms for large language models, 2024.

URL https://arxiv.org/abs/2406.16838.

  • Wu et al. (2024a)

Wu, Y., Sun, Z., Li, S., Welleck, S., and Yang, Y.

Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models, 2024a.

URL https://arxiv.org/abs/2408.00724.

  • Wu et al. (2024b)

Wu, Y., Sun, Z., Li, S., Welleck, S., and Yang, Y.

Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models, 2024b.

URL https://arxiv.org/abs/2408.00724.

  • Xie et al. (2023)

Xie, Y., Kawaguchi, K., Zhao, Y., Zhao, X., Kan, M.-Y., He, J., and Xie, Q.

Self-evaluation guided beam search for reasoning, 2023.

URL https://arxiv.org/abs/2305.00633.

  • Xin et al. (2024)

Xin, H., Guo, D., Shao, Z., Ren, Z., Zhu, Q., Liu, B., Ruan, C., Li, W., and Liang, X.

Deepseek-prover: Advancing theorem proving in llms through large-scale synthetic data, 2024.

URL https://arxiv.org/abs/2405.14333.

  • Xu et al. (2025)

Xu, H., Wu, X., Wang, W., Li, Z., Zheng, D., Chen, B., Hu, Y., Kang, S., Ji, J., Zhang, Y., Guo, Z., Yang, Y., Zhang, M., and Zhang, D.

Redstar: Does scaling long-cot data unlock better slow-reasoning systems?, 2025.

URL https://arxiv.org/abs/2501.11284.

  • Yang et al. (2024)

Yang, Z., Band, N., Li, S., Candès, E., and Hashimoto, T.

Synthetic continued pretraining, 2024.

URL https://arxiv.org/abs/2409.07431.

  • Yao et al. (2023a)

Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., and Narasimhan, K.

Tree of thoughts: Deliberate problem solving with large language models, 2023a.

URL https://arxiv.org/abs/2305.10601.

  • Yao et al. (2023b)

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y.

React: Synergizing reasoning and acting in language models, 2023b.

URL https://arxiv.org/abs/2210.03629.

  • Yu et al. (2024)

Yu, L., Jiang, W., Shi, H., Yu, J., Liu, Z., Zhang, Y., Kwok, J. T., Li, Z., Weller, A., and Liu, W.

Metamath: Bootstrap your own mathematical questions for large language models, 2024.

URL https://arxiv.org/abs/2309.12284.

  • Yuan et al. (2025)

Yuan, S., Chen, Z., Xi, Z., Ye, J., Du, Z., and Chen, J.

Agent-r: Training language model agents to reflect via iterative self-training, 2025.

URL https://arxiv.org/abs/2501.11425.

  • Zelikman et al. (2022)

Zelikman, E., Wu, Y., Mu, J., and Goodman, N. D.

Star: Bootstrapping reasoning with reasoning, 2022.

URL https://arxiv.org/abs/2203.14465.

  • Zelikman et al. (2024)

Zelikman, E., Harik, G., Shao, Y., Jayasiri, V., Haber, N., and Goodman, N. D.

Quiet-star: Language models can teach themselves to think before speaking, 2024.

URL https://arxiv.org/abs/2403.09629.

  • Zhang & Chen (2024)

Zhang, H. and Chen, C.

Test-time compute scaling laws, 2024.

URL https://github.com/hughbzhang/o1_inference_scaling_laws.

  • Zhang et al. (2023)

Zhang, S., Chen, Z., Shen, Y., Ding, M., Tenenbaum, J. B., and Gan, C.

Planning with large language models for code generation, 2023.

URL https://arxiv.org/abs/2303.05510.

  • Zhang et al. (2024a)

Zhang, Y., Wu, S., Yang, Y., Shu, J., Xiao, J., Kong, C., and Sang, J.

o1-coder: an o1 replication for coding, 2024a.

URL https://arxiv.org/abs/2412.00154.

  • Zhang et al. (2024b)

Zhang, Y., Yang, J., Yuan, Y., and Yao, A. C.-C.

Cumulative reasoning with large language models, 2024b.

URL https://arxiv.org/abs/2308.04371.

  • Zhong et al. (2019)

Zhong, H., Xiao, C., Tu, C., Zhang, T., Liu, Z., and Sun, M.

Jec-qa: A legal-domain question answering dataset, 2019.

URL https://arxiv.org/abs/1911.12011.

  • Zhong et al. (2023)

Zhong, W., Cui, R., Guo, Y., Liang, Y., Lu, S., Wang, Y., Saied, A., Chen, W., and Duan, N.

Agieval: A human-centric benchmark for evaluating foundation models, 2023.

URL https://arxiv.org/abs/2304.06364.

  • Zhou et al. (2024)

Zhou, A., Yan, K., Shlapentokh-Rothman, M., Wang, H., and Wang, Y.-X.

Language agent tree search unifies reasoning acting and planning in language models, 2024.

URL https://arxiv.org/abs/2310.04406.

  • Zhou et al. (2023)

Zhou, C., Liu, P., Xu, P., Iyer, S., Sun, J., Mao, Y., Ma, X., Efrat, A., Yu, P., Yu, L., Zhang, S., Ghosh, G., Lewis, M., Zettlemoyer, L., and Levy, O.

Lima: Less is more for alignment, 2023.

Contents

  • 1 Introduction

  • 2 Reasoning data curation to create s1K

  • 2.1 Initial collection of 59K samples

  • 2.2 Final selection of 1K samples

  • 3 Test-time scaling

  • 3.1 Method

  • 3.2 Metrics

  • 4 Results

  • 4.1 Setup

  • 4.2 Performance

  • 5 Ablations

  • 5.1 Data Quantity, Diversity, and Difficulty

  • 5.2 Test-time scaling methods

  • 6 Discussion and related work

  • 6.1 Sample-efficient reasoning

  • 6.2 Test-time scaling

  • References

  • A Evaluation determinism

  • B s1K details

  • B.1 s1K summary

  • B.2 Dataset composition for full 59K questions

  • B.3 s1K grading prompt

  • B.4 s1K diversity selection

  • B.5 Decontamination

  • C Training details

  • C.1 Training Ablations: Sequence length

  • C.2 Training Samples

  • D Test-time scaling details

  • D.1 Sequential scaling ablations

  • D.2 Examples for rejection sampling ablation