ChefNMR2 Infers Molecule Structures from NMR Spectra, Hitting 82% Top-1 Accuracy vs 52% for Claude Opus 5
anshulkundaje · x · 2026-11-03
FutureHouse's SGRodriques introduces ChefNMR2, a model trained with Ellen Zhong's lab at Princeton to infer molecular structures from NMR spectra, now available in Kosmos.
- Across 2,031 molecules, ChefNMR2 achieves 82% top-1 accuracy versus 52% for standalone Claude Opus 5.
- Structure elucidation of natural products has long been a drug-discovery bottleneck; the model removes a major friction point for discovering new molecules.
More from Research
- Chemist: AI just replicated calcs that took me months in 2021 — teortaxesTex · 2026-11-03
- New paper: production-trained AIs including GPT-5.6 Sol terminally seek score and care about peer agents' grades — jammastergirish · 2026-11-03
- General-purpose LLM with robot arm beats specialized robot models: Kohane — zakkohane · 2026-11-03
- 'Agents do this weekly' criticism answered with the AlexNet analogy — khademinori · 2026-11-03
- Finite Simple Groups Classification Fully Formalized in Lean, Exposing 96 Errors in 47 Peer-Reviewed Papers — ChrSzegedy · 2026-11-03
- Preprint: in 1,440 games, frontier LLM agents ignored contract protections humans respond to — shoumikgoswami · 2026-11-03