Benchmark

MedChemBench (Internal)

MedChemBench is an internal OpenAI evaluation of medicinal-chemistry reasoning, testing whether models can support drug-discovery-relevant chemistry…

Modality
text
Categories
reasoning, science, healthcare
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GPT-5.6 LunaOpenAI0.3042026-07-09evidence
GPT-5.6 SolOpenAI0.4832026-07-09evidence
GPT-5.6 TerraOpenAI0.352026-07-09evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.