Training-method researcherBenchmark creator

Karl Cobbe

ORCID lookup ↗DBLP lookup ↗Scholar lookup ↗Semantic Scholar ↗arXiv ↗

Built GSM8K and process-supervision verifiers, establishing step-level reward signals for training model reasoning.

Works in the archive (2) · lead author on 2

LeadGSM8K / MATH (mathematical reasoning) · 2021
LeadVerifiers & Process Supervision (GSM8K / Let's Verify Step by Step) · 2023

“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.

Co-authors in the archive

John Schulman (2), Vineet Kosaraju, Dan Hendrycks, Jacob Steinhardt, Hunter Lightman, Ilya Sutskever, Jan Leike

View co-author network (8 people)

Loading graph…