Dev48
Language
  • About
  • Services
  • Industries
  • Technologies
  • Articles
  • Contacts
Book a call
    Home/Articles/Can ai help scientists identify promising drug candidates
Dev48
info@dev48.org+375 29 320-40-96WhatsApp@isky_by

© 2026 · All rights reserved.

Can AI help scientists identify promising drug candidates?

Source: OpenAI•November 20, 2026 at 07:52 PM

Can AI help scientists identify promising drug candidates?

MedChemBench evaluates how well AI models interpret molecular structures, reason from experimental evidence, and select compounds in early drug discovery.

We’re introducing MedChemBench, a benchmark that evaluates AI models on reasoning tasks drawn from medicinal chemistry research. It tests whether models can connect a molecule’s structure with experimental evidence to explain results, compare compounds, and predict their properties. Building AI that can reliably support this work is one step towards helping scientists develop better medicines.

One of the hardest parts of this work is that improving one property of a molecule can make another worse. A compound might act strongly against a disease related protein but be poorly absorbed or break down too quickly in the body. Medicinal chemists work through these tradeoffs by designing, making, and testing related compounds, then deciding what to try next. For AI to help, it needs to connect changes in molecular structure with experimental evidence and reason about what compounds are worth pursuing.

MedChemBench measures these abilities through 99 problems drawn from published research. At the xhigh reasoning setting, GPT‑6.2 Astra earned 84.5% of the available credit, compared with 83.3% for GPT‑6 Astra, 82.0% for GPT‑6.1 Sol, and 58.2% for GPT‑5.6 Sol. GPT‑6 Astra was strongest at reconstructing molecular structures and explaining experimental evidence. Selecting compounds and predicting their numerical properties proved harder for that model.

What MedChemBench grades

MedChemBench draws on 117 papers and patents and includes 761 distinct molecular structures. For most problems, models receive the context available at a chosen point in a research program: the biological target, the researchers’ goals, the compounds studied so far, and selected experimental findings.

The benchmark evaluates four components:

  • Molecular structures. Correct atom connections and specified stereochemistry in molecules assembled from the drawings and chemical groups provided.

Molecular structures. Correct atom connections and specified stereochemistry in molecules assembled from the drawings and chemical groups provided.

  • Scientific reasoning. Explanations supported by the supplied evidence, such as the reasons for choosing one compound over another.

Scientific reasoning. Explanations supported by the supplied evidence, such as the reasons for choosing one compound over another.

  • Ranking and selection. Compound rankings and choices that meet the stated requirements.

Ranking and selection. Compound rankings and choices that meet the stated requirements.

  • Property predictions. Agreement with the numerical values and categories reported in the source material, including measured and calculated molecular properties.

Property predictions. Agreement with the numerical values and categories reported in the source material, including measured and calculated molecular properties.

Prediction across competing properties

One MedChemBench problem draws on research into inhibitors of PRMT5, a protein studied in cancer drug discovery. The model receives molecular structures and results from earlier experiments. It must predict how three related compounds will behave: how strongly they block PRMT5 in cells, how readily they cross a cell barrier, and how quickly liver enzymes break them down in a laboratory assay.

Later experiments, withheld from the model, showed a tradeoff. Compound 23 blocked PRMT5 in cells at a lower concentration, while compound 24 crossed the cell barrier more readily and broke down more slowly in the liver-enzyme assay.

Predicting these properties together tests whether a model can connect molecular structures with several aspects of compound behavior. This reflects a central challenge in medicinal chemistry: stronger activity against a target does not necessarily come with better permeability or slower breakdown.

The benchmark checks whether the model reconstructs the molecular structures correctly and how closely its predictions match experimental measurements. Predictions receive partial credit based on their closeness to the measured values. Measurements already supplied in the prompt must also be reproduced correctly.

Small chemical changes can produce different property profiles. The task asks models to connect the structures with evidence about their behavior.

Testing spatial reasoning in medicinal chemistry

Before a model can reason about a compound’s properties, it needs to identify the molecule correctly. Chemical drawings encode atom connections, ring structures, and stereochemistry.

MedChemBench tests whether models preserve this information when reconstructing molecules from the drawings and chemical groups provided.

One problem asks models to assemble a molecule from a central structure and two attached groups while preserving an 18-atom ring. At the highest reasoning setting shared by all eleven models (xhigh), GPT‑6 Astra reconstructed this compound correctly in all ten responses. GPT‑5.6 Sol and GPT‑5.6 Luna failed across all ten responses.

In the illustrated answers, GPT‑5.6 Sol produced a 15-atom ring, while GPT‑5.6 Luna split the molecule into two disconnected fragments.

These errors change the identity of the molecule being analyzed. This example tests a foundation of medicinal chemistry reasoning: whether the model can accurately represent the compound before interpreting its behavior.

Figure 1. The same input, different molecules

These selected answers for compound 17 show a correct reconstruction, a smaller ring, and disconnected fragments.

While measuring the benchmark for structure components, Astra earned 95.4% of the available credit at xhigh. This result shows strong performance on reconstructing the molecular structures supplied in the tasks.

We evaluated eleven GPT models at different reasoning-effort settings. Across the full benchmark, Astra earned 83.3% of the available credit at the shared xhigh setting, compared with 82.0% for GPT‑6.1 Sol, 75.1% for GPT‑6.1 Terra, and 58.2% for GPT‑5.6 Sol. At max effort, GPT‑6 Astra reached 83.8%. Higher reasoning settings improved scores, while large differences between models remained. The figure below plots performance against output tokens.

Figure 2. Performance versus token usage

Each point represents a model at one reasoning setting, showing 51 combinations across nine models from GPT‑5.6 onward. Scores are averaged across 99 problems; bars show 95% uncertainty intervals. Tokens include reasoning and the final answer.

The component results separate four abilities: reconstructing molecules, explaining findings, selecting compounds, and predicting measurements. This shows where models are strongest and where errors remain.

Figure 3. Component performance versus token usage

Astra’s clearest strengths were in reconstructing molecular structures and explaining the scientific evidence. In selected reasoning examples from our preprint, Astra correctly identified structural changes and weighed their possible effects on protein binding, absorption, and metabolism.

Where selection and prediction remain difficult, Astra earned 95.4% of the available structure credit at xhigh, but only about half the credit for selecting compounds and predicting numerical properties. These categories use different tasks and scoring rules, but the results show substantial room to improve predictions and compound choices.

Where we go from here

These results do not establish whether models can discover new drugs or improve laboratory decisions. Prior exposure to the published sources cannot be ruled out, and each response was a single attempt without tools, feedback, or new experiments. While the benchmark evaluates reasoning from historical evidence rather than real-world drug discovery, its results help identify where models are advancing and where challenges remain. We believe MedChemBench will support continued progress and look forward to sharing updates as our models advance to serve the field.

← All articles

What this article says

More in AI & Machine Learning

All →
Introducing Inkling 2 Mini
Thinking Machines Lab

Introducing Inkling 2 Mini

Combatting adversarial distillation
OpenAI

Combatting adversarial distillation

ElevenAgents for Healthcare: Build an outbound appointment reminder agent with Architect
ElevenLabs

ElevenAgents for Healthcare: Build an outbound appointment reminder agent with Architect

How to Scale Marketing Expertise with AI Agents
Jasper

How to Scale Marketing Expertise with AI Agents

How we secure 100+ clusters across 20+ clouds
Baseten

How we secure 100+ clusters across 20+ clouds

Improved controls for the new era of cyberattacks
Baseten

Improved controls for the new era of cyberattacks

More from OpenAI

Combatting adversarial distillation
OpenAI

Combatting adversarial distillation

How OpenAI’s Performance Factory keeps ChatGPT fast
OpenAI

How OpenAI’s Performance Factory keeps ChatGPT fast

Research acceleration: The jagged frontier
OpenAI

Research acceleration: The jagged frontier

OpenAI CEO Sam Altman says it’s ‘hard to imagine the AI industry without Jensen’Пресса
OpenAI

OpenAI CEO Sam Altman says it’s ‘hard to imagine the AI industry without Jensen’

Advancing chip design with OpenAI models
OpenAI

Advancing chip design with OpenAI models

Le Groupe Figaro and OpenAI partner to bring Le Figaro journalism to ChatGPT
OpenAI

Le Groupe Figaro and OpenAI partner to bring Le Figaro journalism to ChatGPT