Evaluation
Kernels task (ML kernel optimization)
performance engineering kernel optimization challenge (proxy for accelerating frontier model capability)
Autonomy & self-improvement
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 Opus 4, Claude Sonnet 4
Anthropic
rich detail
22 method fields published
See how this test was run