Event ·Multi-source

Quant-Arena 发布：评测 LLM 端到端量化研究能力

Quant-Arena 是一个面向量化研究的基准与公开排行榜，基于真实 A 股数据。模型需要构建特征和股票打分代码，仅在 2022-2023 年数据上获得反馈，并冻结策略接受 2024 年封存数据的检验。评估采用现金账户模拟，计入交易成本和基于模拟订单簿估算的市场冲击，得分以实际超额收益为主。共评测九个前沿模型，GPT-6 Astra 得分最高，但没有模型在 2024 年跑赢等权市场基准。

Current read

arXiv 上这个 Quant-Arena 基准挺有意思：让 GPT-6 Astra 等 9 个模型做真实 A 股量化策略，结果没有一个跑赢等权市场，排行榜对外开放提交。

9 sources31° AI heatLast updated 2026/10/21 17:54:01

Evidence

9 sources

Primary sourcearXiv cs.AI

2026/10/21 17:54:01View source

Related source 1Decoder

2026/10/21 12:34:57View source

Related source 2theverge

2026/10/21 13:57:43View source

Related source 3rohanpaul_ai

2026/10/22 05:56:00View source

Related source 4elvis

2026/10/19 18:54:22View source

Related source 5AIGCLINK

2026/10/20 01:44:28View source

Related source 6PolymarketMoney

2026/10/21 15:49:50View source

Related source 7Artificial Analysis

2026/10/21 15:53:56View source

Related source 8TestingCatalog

2026/10/22 08:23:08View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story