Saved in:
Bibliographic Details
Main Authors: Guo, Jiacheng, Huang, Suozhi, Yao, Zixin, Zhang, Yifan, Lu, Yifu, Liu, Jiashuo, Li, Zihao, Deng, Nicholas, Xiao, Qixin, Tian, Jia, Zhan, Kanghong, Li, Tianyi, Liu, Xiaochen, Ge, Jason, He, Chaoyang, Huang, Kaixuan, Yang, Lin, Huang, Wenhao, Wang, Mengdi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00417
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in the uniquely demanding and fast-paced cryptocurrency domain. Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges: \emph{extreme time-sensitivity}, \emph{a highly adversarial information environment}, and the critical need to synthesize data from \emph{diverse, specialized sources}, such as on-chain intelligence platforms and real-time Decentralized Finance (DeFi) dashboards. CryptoBench thus serves as a much more challenging and valuable scenario for LLM agent assessment. To address these challenges, we constructed a live, dynamic benchmark featuring 50 questions per month, expertly designed by crypto-native professionals to mirror actual analyst workflows. These tasks are rigorously categorized within a four-quadrant system: Simple Retrieval, Complex Retrieval, Simple Prediction, and Complex Prediction. This granular categorization enables a precise assessment of an LLM agent's foundational data-gathering capabilities alongside its advanced analytical and forecasting skills. Our evaluation of ten LLMs, both directly and within an agentic framework, reveals a performance hierarchy and uncovers a failure mode. We observe a \textit{retrieval-prediction imbalance}, where many leading models, despite being proficient at data retrieval, demonstrate a pronounced weakness in tasks requiring predictive analysis. This highlights a problematic tendency for agents to appear factually grounded while lacking the deeper analytical capabilities to synthesize information.