All people
Jean-Stanislas Denain portrait

Researcher

Jean-Stanislas Denain

METRMember of Technical Staff

At a glance

Denain helps make AI progress measurable. He co-authored FrontierMath, a test built from difficult original mathematics problems, and A Rosetta Stone for AI Benchmarks, which links results across different tests to compare model capabilities more consistently.[1][2]

More

His earlier research examined how language models can copy false examples from a prompt, even when their intermediate calculations initially point toward the correct answer.

Career & education

Current role
Oct 2026-present
Member of Technical Staff
Previously
2024-2026
Senior Researcher; Insights Team Lead
Jan 2024-May 2024
AI Policy
Education

Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.

Citation Trend

Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
1 snapshots
Citation snapshot on Oct 25, '26817Oct 25, '26
citations817As of Oct 25, '26
For today’s citation count and per work, visit Google Scholar.

Updates 1

MoveJean-Stanislas Denain joins METR from Epoch AI

After two years at Epoch AI, Denain joins METR to assess how much AI is accelerating AI research and development.

October 23, 2026

References

  1. FrontierMatharxiv.org

    Named coauthor; benchmark of original expert-written advanced mathematics problems.

  2. A Rosetta Stone for AI Benchmarksarxiv.org

    Named coauthor; linking benchmark performance and comparing AI capabilities across tests.

About this profile

Based on public sources. If accuracy is important, verify details using the links or references.

For corrections, updates, or requests to remove information, contact us.

Sharing card

Related people