{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:50:14Z","timestamp":1774000214471,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788170","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"595-601","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantifying Capability Boundaries: An Application-Driven Analysis for Large Language Model Selection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8048-5145","authenticated-orcid":false,"given":"Kaikai","family":"Zhao","sequence":"first","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0277","authenticated-orcid":false,"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0237-2265","authenticated-orcid":false,"given":"Shun","family":"Lu","sequence":"additional","affiliation":[{"name":"China Electronics Standardization Institute, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3958-7243","authenticated-orcid":false,"given":"Xuejiao","family":"Lei","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1944-1530","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1040-0293","authenticated-orcid":false,"given":"Wen","family":"Liu","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1171-0281","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-7049","authenticated-orcid":false,"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709069"},{"key":"e_1_3_3_1_3_2","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1 distilled models.https:\/\/huggingface.co\/deepseek-ai\/DeepSeek-R1-Distill-Qwen-1.5B"},{"key":"e_1_3_3_1_4_2","unstructured":"et\u00a0al. DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.19437\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_3_1_5_2","unstructured":"et\u00a0al. DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_1_6_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_7_2","first-page":"10835","volume-title":"International Conference on Machine Learning","author":"Gao Leo","year":"2023","unstructured":"Leo Gao, John Schulman, and Jacob Hilton. 2023. Scaling laws for reward model overoptimization. In International Conference on Machine Learning. PMLR, 10835\u201310866."},{"key":"e_1_3_3_1_8_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.03300 (2020)."},{"key":"e_1_3_3_1_9_2","unstructured":"Yuzhen Huang Yuzhuo Bai Zhihao Zhu Junlei Zhang Jinghan Zhang Tangjun Su Junteng Liu Chuancheng Lv Yikai Zhang Yao Fu et\u00a0al. 2024. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_10_2","unstructured":"Naman Jain King Han Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07974 (2024)."},{"key":"e_1_3_3_1_11_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.08361 (2020)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709050"},{"key":"e_1_3_3_1_13_2","first-page":"67","volume-title":"CCF International Conference on Natural Language Processing and Chinese Computing","author":"Lian Shiguo","year":"2024","unstructured":"Shiguo Lian, Kaikai Zhao, Xinhui Liu, Xuejiao Lei, Bikun Yang, Wenjing Zhang, Kai Wang, and Zhaoxiang Liu. 2024. What is the best model? Application-driven Evaluation for Large Language Models. In CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 67\u201379."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709036"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Wei Liu Jiacheng Xu and Chengxiang Tan. 2025. An AMR-based Model with Role And Relation Information for Document-level Event Argument Extraction(CSAI \u201924). Association for Computing Machinery New York NY USA 361\u2013366. 10.1145\/3709026.3709041","DOI":"10.1145\/3709026.3709041"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709066"},{"key":"e_1_3_3_1_17_2","unstructured":"MetaAI. 2024. Llama instruction-tuned models.https:\/\/huggingface.co\/meta-llama\/Llama-3.3-70B-Instruct"},{"key":"e_1_3_3_1_18_2","unstructured":"ollama. 2024. ollama 4-bit quantized deepseek models.https:\/\/ollama.com\/library\/deepseek-r1"},{"key":"e_1_3_3_1_19_2","unstructured":"OpenAI. 2023. Math-500. https:\/\/github.com\/openai\/prm800k\/tree\/main\/prm800k\/math_splits"},{"key":"e_1_3_3_1_20_2","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_3_1_21_2","unstructured":"OpenAI. 2024. Introducing SimpleQA. https:\/\/openai.com\/index\/introducing-simpleqa\/"},{"key":"e_1_3_3_1_22_2","unstructured":"OpenAI. 2024. Learning to reason with llms. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/"},{"key":"e_1_3_3_1_23_2","unstructured":"Qwen-Team. 2024. Qwen instruction-tuned models.https:\/\/huggingface.co\/Qwen\/Qwen2.5-7B-Instruct"},{"key":"e_1_3_3_1_24_2","unstructured":"Qwen-Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_3_1_25_2","unstructured":"Qwen Team. 2025. QwQ-32B: Embracing the Power of Reinforcement Learning. https:\/\/qwenlm.github.io\/blog\/qwq-32b\/"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:40:11Z","timestamp":1773988811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":24,"alternative-id":["10.1145\/3788149.3788170","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788170","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}