Insilico Medicine launches DDD Benchmark as a Service
Analysis based on 6 articles · First reported Jul 30, 2026 · Last updated Aug 01, 2026
The launch positions Insilico Medicine as a standard-setter in AI drug discovery evaluation, potentially increasing its credibility and attracting partnerships. It may also influence the competitive landscape by providing a transparent benchmark for AI models in pharma, affecting companies developing such models.
Insilico Medicine, a clinical-stage generative AI-driven drug discovery company listed on the Hong Kong Stock Exchange, announced the launch of the Drug Discovery and Development (DDD) Benchmark as a Service (BaaS) on July 30, 2026. The DDD Benchmark is a standardized evaluation framework designed to measure whether frontier AI and foundation models can perform real-world drug discovery tasks, addressing the problem of data contamination in existing AI benchmarks. It comprises two suites: Drug Discovery Foundations, with over 300 evaluations covering disease biology, molecular property prediction, retrosynthesis, and clinical development; and Drug Candidate Essentials, which tests end-to-end drug discovery program navigation from hit identification to preclinical candidate nomination. The benchmark uses decontaminated public data and proprietary out-of-distribution test sets, anchored in Insilico's validated programs. Models are evaluated via standard chat-completions APIs, with results provided as scorecards and an optional public leaderboard. Insilico's CEO Alex Zhavoronkov emphasized the need to measure genuine capability rather than memorized answers. The company has nominated 31 preclinical candidates, received over 10 IND clearances, and advanced its lead program Rentosertib to Phase III for IPF.
Set up alerts, explore entity relationships, search across thousands of events, and build custom intelligence feeds.
Open Dashboard