Quant-Arena benchmarks LLM agents on sealed A-share trading research
Original title: Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research
Nine frontier models were scored on 2024 after 2022–2023 feedback; GPT-6 Astra led, and none beat equal-weight.
Quant-Arena is a public leaderboard for end-to-end quantitative research on real A-share market data. A model builds features and stock-scoring code, receives feedback only for 2022–2023, and freezes one strategy for assessment in 2024. A cash-account evaluator applies trading constraints, costs, and market impact from a simulated order book. Scores emphasize realized excess return, with signal quality and feature diversity as complements.
Unconfirmed: Rankings reflect the authors' Quant-Arena evaluation, not independent replication.
- No evaluated model beat the equal-weight market in the sealed 2024 year.
- GPT-6 Astra scored highest among the nine frontier models.
- Submissions are open to any model or agent harness.
- Products
- Quant-Arena
- AI models
- GPT-6 Astra
From the original article
1 min read at arxiv.orgQuantitative 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.
By Houde Qian · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.