{"name":"baoyan-agent-benchmark","repo":"yeyuxin777/baoyan-agent-benchmark","url":"https://midorreal.com/project/yeyuxin777-baoyan-agent-benchmark","repository":"https://github.com/yeyuxin777/baoyan-agent-benchmark","description":"Sprix AI at 屿智同行 × 保研岛 — an open-source benchmark for AI agents in Baoyan advising and application planning.","facts":{"license":{"value":"MIT","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark/releases","checked":"19 Nov 2026"},"contributors":{"value":"7","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark","checked":"22 Nov 2026"}},"stars":701.0,"writeup":{"what_it_is":"An open-source benchmark for evaluating AI agent configurations on graduate admissions advising, application planning, and updating advice when student information changes. It contains 70 Chinese-language tasks with per-task rubrics, and it reports mean scores and completion rates for agent configurations.","audience":"Researchers and developers evaluating AI agents for Baoyan (graduate admissions) advising","claims":[{"kind":"specific","claim":"The benchmark contains 70 Chinese-language tasks, 23 cases and 83 answer stages.","excerpt":"The benchmark contains 70 Chinese-language tasks, 23 cases and 83 answer stages","status":"not_checked"},{"kind":"specific","claim":"Each task is worth 100 points, with full recommendation tasks allocating 70 points to reference-program matching and 30 to recommendation quality.","excerpt":"Each task is worth 100 points. Full recommendation tasks allocate 70 points to reference-program matching and 30 to recommendation quality.","status":"not_checked"},{"kind":"specific","claim":"The framework uses only the standard library and needs no pip install.","excerpt":"The framework uses only the standard library; no `pip install` is needed.","status":"not_checked"},{"kind":"specific","claim":"Automated native execution requires macOS Seatbelt and Python 3.10+.","excerpt":"Automated native execution requires macOS Seatbelt and Python 3.10+","status":"not_checked"},{"kind":"specific","claim":"The dataset is licensed under CC BY 4.0 and the code under MIT.","excerpt":"Code and software documentation are licensed under [MIT](LICENSE).","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-17"},"why_now":null,"owner_supplied":null,"score":{"verdict":"sleeper","hype":1,"reality":45,"gap":-44,"momentum":0.0,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T09:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-12T09:15:11+00:00","text":"Repository created","source":"https://github.com/yeyuxin777/baoyan-agent-benchmark"}],"cite":"baoyan-agent-benchmark is a GitHub project at https://github.com/yeyuxin777/baoyan-agent-benchmark written mainly in Python, described there as \"Sprix AI at 屿智同行 × 保研岛 - an open-source benchmark for AI agents in Baoyan advising and application planning\".","attribution":"Data from Mid or Real, https://midorreal.com/project/yeyuxin777-baoyan-agent-benchmark, checked 22 November 2026. Attribution with a link is required.","still_real":null}