Summary of METR's predeployment evaluation of Claude Opus 5.5

Research question

Does stronger task performance establish full research automation?

Design & assumptions

Combines verifiable tasks, conceptual evaluations, interviews and a separate preliminary internal assessment.

Findings

Authors judge capability gains incremental and full automation unlikely.

Research judgment and feedback-loop weaknesses remain.

Limits & counterevidence

Some supporting evidence was unavailable to this assessment team; the time period of a separate acceleration estimate is unspecified.

Source evidence

No structured numerical extraction is available in this reading package.