aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

OpenAI publishes medicinal chemistry benchmark MedChemBenchMachine translation

AI introduction

MedChemBench draws problems from 117 papers and patents and covers 761 graded molecular structures. Each prompt stops at a real research decision point, provides the biological target, compounds made so far and selected assay results, and withholds results reported later. The source says GPT-6.2 Astra scores about 84% overall but gets the consequential decision right about half the time.

Original post · AI translation

@rohanpaul_ai
Translation · refer to the original

OpenAI 现已发布其药物化学基准测试 MedChemBench。

其题目来自 117 篇论文和专利,涵盖 761 个经过评分的分子结构,并隐藏了研究人员后来报告的结果。

每道题都停在一个真实的决策节点,提供生物学靶点、迄今合成的化合物以及部分实验测定结果。

表现最好的模型 GPT-6.2 Astra 总体得分约为 84%,在解读化学信息方面近乎完美,但在真正重要的决策上,正确率约为一半。

Source: Rohan Paul · x.com

Research
Found an error? Send a correction