We introduce Look-Ahead-Bench, a standardized benchmark measuring look-ahead bias in Point-in-Time (PiT) Large Language Models (LLMs) within realistic and practical financial workflows. Unlike most existing approaches that primarily test inner lookahead knowledge via Q\\&A, our benchmark evaluates model behavior in practical scenarios. To distinguish genuine predictive capability from memorization-based performance, we analyze performance decay across temporally distinct market regimes, incorporating several quantitative baselines to establish performance thresholds. We evaluate prominent open-source LLMs -- Llama 3.1 (8B and 70B) and DeepSeek 3.2 -- against a family of Point-in-Time LLMs (Pitinf-Small, Pitinf-Medium, and frontier-level model Pitinf-Large) from PiT-Inference. Results reveal significant lookahead bias in standard LLMs, as measured with alpha decay, unlike Pitinf models, which demonstrate improved generalization and reasoning abilities as they scale in size. This work establishes a foundation for the standardized evaluation of temporal bias in financial LLMs and provides a practical framework for identifying models suitable for real-world deployment. Code is available on GitHub: https://github.com/benstaf/lookaheadbench

翻译：我们提出了前瞻性偏差基准（Look-Ahead-Bench），这是一个用于在现实且实用的金融工作流程中，衡量点时间（Point-in-Time, PiT）大语言模型（LLMs）前瞻性偏差的标准化评测基准。与大多数主要通过问答测试内部前瞻知识的现有方法不同，我们的基准评估模型在实际场景中的行为。为了区分真正的预测能力与基于记忆的性能，我们分析了模型在不同时间市场机制下的性能衰减，并引入了多个量化基线来建立性能阈值。我们评估了主流的开源LLMs——Llama 3.1（8B和70B）和DeepSeek 3.2——与来自PiT-Inference的点时间LLMs系列模型（Pitinf-Small、Pitinf-Medium以及前沿模型Pitinf-Large）进行对比。结果显示，标准LLMs存在显著的前瞻性偏差（通过alpha衰减衡量），而Pitinf模型则不同，随着模型规模的扩大，它们展现出更强的泛化能力和推理能力。这项工作为金融LLMs中时间偏差的标准化评估奠定了基础，并为识别适合实际部署的模型提供了一个实用框架。代码已在GitHub上开源：https://github.com/benstaf/lookaheadbench