Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Lin Shi, Haowei Lin, Zixuan Zhu, Xiaoyue Zhou, Xiang Li, Xiangning Lin, Yaxuan Deng, Han Xu, Yuangang Li, Shanda Li, Zizhao Chen, Hanwen Xing, Harsh Raj, Bo Chen, Quan Shi, Steven Dillmann, Yipeng Gao, Puneesh Khanna, Ruofan Lu, Chao Zhou, Michael Yang, Robert Zhang, Siyuan Chai, Jiayu Chang, Yizhao Chen, Xiaokun Chen, Yiwei Dai, Wenting Yang, Hange Liu, Minghao Liu, Zihan Wang, Adnan E Assadi, Benedikt Stroebl, Estefany Kelly Buchanan, Han Meng, Junwei He, Longxuan YU, Radin Shayanfar, Yukyung Lee, Zhikang Dong, Allen G Hart, Anjiang Wei, Anurag Kashyap, Arpandeep Khatua, Audrey J Zheng, Chengrui Ma, David Heineman, dubing, Hai-Anh Trinh, Haishuo Fang, Hefan Zhang, Hui Shen, Issa Sugiura, Jiankai Sun, Jiechao Gao, Junhong Lin, Junnan Li, Kai Yang, Lei Hsiung, Maoyu Wang, Mengze Tang, Nabil Omi, Negin Raoof, Nicholas Edwards, Ruohao Guo, Orfeas Menis Mastromichalakis, Ryan Ji, Przemysław Hejman, Qi Qi, Qunshu Lin, Richard Zhuang, Rui Yang, Ruichen Zheng, Ryan Marten, Shaghayegh Fazliani, Shizheng Hou, Sicong Jiang, Sijie Li, Song Bian, Terry Yue Zhuo, Tianqing Wu, Tom Tang, Wanjia Zhao, Weihao Xuan, Wenhua Liang, Xian Liu, Xin Lan, Ruby Zhang, Xuandong Zhao, Yanchuan Tang, Yifan Jiang, Yijiang Li, Yitong Guan, Yizhi Li, YONGHUI LIU, Yuheng Tang, Yujun Mao, Yunfei Zhao, Yuxin Wang, Yuxuan Tang, Zhenheng Tang, Zhifei Li, Ziruo Wang, Ziyu She, Kaiyuan Liu, Iheb Chaabane, Yuxin Tang, Xiangyi Li, Soroush Vosoughi, Sanmi Koyejo, Di He, Etash Guha, Benjamin Feuer, Andy Konwinski, Boxuan Li, Leon L Chen, Alex Dimakis, Nicholas Carlini, Mike Merrill, Ludwig Schmidt, Alex Shaw
Abstract
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of frontier models across 54 benchmarks, enabling a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Mix, a curated set of 100 difficult, diverse, and high-quality tasks refined from the adapted benchmarks. Harbor-Mix preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; the strongest model resolves only 15.6% of its tasks. We release the adapters, evaluation results, in-depth analysis, and Harbor-Mix as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.