Grading Needs a Rubric, Not Intelligence

Excerpt

arXiv:2608.17938v1 Announce Type: new Abstract: Small language models can grade open-ended examination answers as reliably as substantially more expensive models when they grade against an explicit rubric. We test this claim as the design principle behind any-to-bench: a frontier model reads source documents once, at ingestion, to extract each question and its rubric; lower-cost models then perform all repeated grading work. We evaluate six cost-efficient model configurations from two model fami