---
id: 20260524-T0-07
title: "SMDD-Bench：评估LLM药物设计能力"
title_en: "SMDD-Bench: Evaluates LLM Drug Design Capabilities"
url: https://ai.daily.yangsir.net/daily/20260524-T0-07
issue_date: 2026-05-24
publish_date: 2026-05-23T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2605.21740
---

# SMDD-Bench：评估LLM药物设计能力

研究人员推出SMDD-Bench基准测试，专门评估大语言模型在真实世界小分子药物设计任务中的表现。该基准覆盖多样化化学物质和靶点，填补了现有评估方法的空白。测试结果将为AI在药物发现领域的应用提供重要参考。

## English Version

**SMDD-Bench: Evaluates LLM Drug Design Capabilities**

SMDD-Bench benchmark evaluates LLM performance on real-world small molecule drug design tasks across diverse chemistries and targets. The new benchmark addresses evaluation gaps and provides critical insights for AI applications in drug discovery.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2605.21740)

**详情页**：https://ai.daily.yangsir.net/daily/20260524-T0-07

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*