Join us in building the evaluation infrastructure for scientific AI
Collaborate on benchmark development, contribute evaluation tasks, or conduct joint research on scientific AI evaluation.
zhangwenlong@pjlab.org.cnJoin our open-source community to contribute code, report issues, or discuss the future of scientific AI evaluation.
github.com/InternScienceWe are building a network of domain experts to help design and validate our scientific benchmarks. Members of our expert panel have the opportunity to become co-authors on our publications.
Apply to Join
Scan to join our WeChat community
Follow us on Xiaohongshu