Benchmarking AI models for end-to-end stock trading strategy creation
Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research
Computation and LanguageArtificial IntelligenceComputational Engineering, Finance, and Science
Summary
Building successful stock trading strategies usually requires many steps and testing on past stock data. The authors created Quant-Arena, a system that challenges AI models to do all these steps: from making predictions and writing code to testing strategies on real market data. They tested various advanced AI models and found none yet outperforms a simple equal-weighted market strategy for 2024. This benchmark helps show how well AI can handle the complete process of quantitative trading research.
What this means in practice
- •For quantitative trading teams: Compare AI methods for building and testing complete trading strategies on real stock market data with realistic constraints.
- •For financial software engineers: Develop automated tools that generate and validate stock trading strategies end-to-end using large language models and historical market feedback.
Authors
Houde Qian, Zheng Jiang, Wenyi Li, Chenxi Xu, Xinjie Lin, Yuzhao Peng, Ruoyu Han, Youjie Zheng, Kaisen Yang, Qinhuai Na, You Fu, Calvin Xiao
Abstract
Quantitative research is an iterative loop: a researcher proposes a market hypothesis, implements it as an executable signal, tests it on historical data, and decides what to keep. Existing benchmarks score formulas, code, or individual trading decisions, leaving open whether large language models (LLMs) can complete this loop and produce strategies that work beyond the research period. We introduce Quant-Arena, a benchmark and public leaderboard for end-to-end quantitative research on real A-share market data. A model constructs features and stock-scoring code, receives feedback only on 2022--2023, and freezes one strategy for assessment on the sealed year 2024. A cash-account evaluator applies trading constraints and costs, including market impact estimated from a simulated order book. Scores are dominated by realized excess return and complemented by signal quality and the diversity of features used by the strategy. We evaluate nine frontier models, among which GPT-6 Astra scores highest; yet no model beats the equal-weight market in 2024. Quant-Arena is open to submissions from any model or agent harness.