跳到正文
𝕏 Rohan Paul(x.com)·· 2 天前品質評分58
重點導讀

藥物化學研究需要根據實驗結果決定下一步該做什麼,但模型答對化學題目,不代表也能做出對的研究判斷。

  • OpenAI 發布 MedChemBench,題目取自 117 篇論文和專利,涵蓋 761 種有評分的分子結構,並隱藏研究者後來公佈的結果。
  • 每題會提供生物標靶、已製作的化合物和部分實驗結果,停在需要做決定的地方。
  • 表現最好的 GPT-6.2 Astra 整體得分約 84%,讀懂化學內容幾乎沒問題,但真正重要的決策只有約一半答對。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·2 天前
𝕏

OpenAI has now published MedChemBench, its medicinal chemistry benchmark.

Its problems come from 117 papers and patents, span 761 graded molecular structures, and withhold the results researchers reported later.

Each prompt stops at a real decision point, supplying the biological target, the compounds made so far and selected assay results.

the best model GPT-6.2 Astra gets about 84% overall, is near perfect at reading the chemistry, and is right about half the time on the decision that actually matters.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論