urn:uuid:78fa9f48-af39-5018-98a7-73cd7d238962 SocioLens — RO-LD06-01: Do benchmark scores predict what models achieve in real deployments? New versions of this research opportunity and changes to the claims it rests on. 2026-10-15T00:00:00Z SocioLens urn:uuid:18ed36e2-8cb2-5459-bed4-4747c265f9de New research opportunity: RO-LD06-01 — Do benchmark scores predict what models achieve in real deployments? 2026-10-15T00:00:00Z Across many language models, do scores on public benchmarks predict measured outcomes when the same models are used in real work, such as code that maintainers merge in live repositories, support tickets resolved or error rates in use, and are the benchmarks calibrated to those outcomes or only correct in rank?