LLMs can generate plausible trading code and features, but current models fail to produce strategies that generalize beyond their training period—a critical gap between research-phase performance and real-world deployment.
Quant-Arena is a benchmark that tests whether LLMs can complete the full quantitative trading research loop—from hypothesis to strategy—on real market data. Models develop trading strategies using 2022-2023 data, then their frozen strategies are evaluated on unseen 2024 data with realistic trading costs and market impact.