Frontier LLMs suddenly got good at NMR since Claude Opus 4.8, large-scale benchmark shows
ZhongingAlong · x · 2026-11-03
The author observes that since Claude Opus 4.8 in June, chatbots have suddenly become good at NMR spectroscopy interpretation, signaling that LLMs are now generally intelligent enough for scientific tasks performed much like a chemist would.
The team partnered with EdisonSci to run a large-scale benchmark of ChefNMR2 with frontier reasoning LLMs, and to explore its integration with Kosmos, EdisonSci's AI scientist platform. ChefNMR2 takes 1D proton and carbon NMR peak lists plus a molecular formula (e.g., from mass spec) to generate candidate structures, and its generative model carries calibrated uncertainties that help guide interpretation of the outputs.
More from Models
- Olmo 3 ships with Nextcloud's llm2 backend for centrally managed local AI features — allen_ai · 2026-11-03
- Nextcloud picked Olmo 3 partly because it runs on consumer-grade hardware — allen_ai · 2026-11-03
- Olmo 3 earns Nextcloud's top green Ethical AI rating: open code, weights, and data — allen_ai · 2026-11-03
- Nextcloud picks Ai2's fully open Olmo 3, earning its highest Ethical AI green rating — allen_ai · 2026-11-03
- Qwen 3.8 27B spontaneously uses Blender MCP to code its way through a physics problem — Balloon_Fan · 2026-11-03
- AA-PersonalityBench goes live: build your own AI personality rankings across 41 models — ArtificialAnlys · 2026-11-03