Optimize correct kernels for OpenAI first-party hardware.
On this page
AI-system improvement
What this measure tells us
Targets a specific AI-development task.
Internal suite; no cross-lab percentage comparison.
Not a demonstration of recursive improvement.
Results by version
GPT-6.1 Sol card snapshot, September 29, 2026
2026-09-29
Separate disclosure snapshot. The addendum refers to the Astra card methods but does not positively establish identical task snapshot or budgets. Do not treat later source date as a new best score.
Metric definitions
Mean kernel optimization reward (percent): Mean score on the kernel-optimization rubric, displayed as a percentage. It is not a percentage reduction in runtime or a task-success rate.
Published results · GPT-6.1 Sol card snapshot, September 29, 2026
Version identity is this disclosure snapshot, not an invented upstream version.
Metric definitions
Mean kernel optimization reward (percent): Mean score on the kernel-optimization rubric, displayed as a percentage. It is not a percentage reduction in runtime or a task-success rate.
Published results · Astra card snapshot, September 2026