Skip to content

Evaluation

AIME

advanced math competition problem solving

Core capabilities Anthropic

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Claude 3.5 Haiku, Upgraded Claude 3.5 Sonnet
Anthropic

partial detail 15 method fields published

See how this test was run
Claude Opus 4, Claude Sonnet 4
Anthropic

rich detail 20 method fields published

See how this test was run