Metrics of Agent Ability - METR
metr.org · 4,076 words · saved by 2 readers
Tom Cunningham surveys metrics for comparing AI agent capability as performance changes with expenditure and relative to human performance.
Metrics of Agent Ability - METR Our Work Research Notes Updates Risk Assessment About Donate Careers Search --> Our Work Research Notes Updates Risk Assessment About Donate Careers Menu × Research note: Metrics of Agent Ability CONTRIBUTORS Tom Cunningham DATE July 24, 2026 SHARE Copy Link Citation BibTeX Citation × @misc { metr-2026-metrics-of-model-ability , title = {Metrics of Agent Ability} , author = {Tom Cunningham} , howpublished = {\url{https://metr.org/notes/2026-07-24-metrics-of-model-ability/}} , year = {2026} , month = {07} , } Copy Tom Cunningham **Goals of this post**
saved by
related reading
- Measuring AI Ability to Complete Long Tasks - METRmetr.org
- An Apple-Picking Model of AI R&D | Tom Cunningham – Tom Cunninghamtecunningham.github.io
- [1911.01547] On the Measure of Intelligencearxiv.org
- Economics and Transformative AI | Tom Cunningham – Tom Cunninghamtecunningham.github.io
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- We spent 2 hours working in the future - METRmetr.org
- More compute, more capability: Why AI agent evaluations need to account for test-time compute | AISI Workaisi.gov.uk
- Early work on monitorability evaluations - METRmetr.org
- Measuring AI Ability to Complete Long Software Tasksarxiv.org
- Demystifying evals for AI agents \ Anthropicanthropic.com
- METRmetr.org