Anthropic medicinal-chemistry evaluation (Medicinal chemistry)
We show this table for reference; we do not rank on it.
Selects compounds with the highest or lowest measured ADME-related property from molecular structures and reference values.
Benchmark score on Medicinal chemistry — September 27, 2026
We compile the Medicinal chemistry rows from provider self-reports. Claude Opus 5.5 leads the table at 63.5%. We do not use these results to rank models overall.
1 modelKnowledgeCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (1 model)
ScoreAbout Medicinal chemistry
Year
2026
Tasks
504 molecular-property questions
Format
Accuracy
Difficulty
Medicinal chemistry reasoning
Section 8.17.4 reports a provider-run five-attempt average across 504 questions without tools. It is display-only evidence.
Freshness and provenance
Version
Medicinal chemistry 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Medicinal chemistry measure?
Selects compounds with the highest or lowest measured ADME-related property from molecular structures and reference values.
Which model scores highest on Medicinal chemistry?
Claude Opus 5.5 by Anthropic currently leads with a score of 63.5% on Medicinal chemistry.
How many models are evaluated on Medicinal chemistry?
1 AI models have been evaluated on Medicinal chemistry on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.