Commit Graph
3 Commits
Author SHA1 Message Date
Paul Bakaus 27bbf90ede Improve Codex Live architecture benchmark
Compare production-equivalent direct and app-server paths, include annotated UI work, expose first-usable latency, and keep semantic quality gates honest.\n\nAI-assisted: OpenAI Codex.
2026-07-12 20:46:53 -07:00
Paul Bakaus 6d1bd40959 Fix Codex quality benchmark gates
Allow valid CSS-only design work and compare JSX component contracts independent of formatting.\n\nAI-assisted: OpenAI Codex.
2026-07-12 19:53:42 -07:00
Paul Bakaus 92a5589d5d Add Codex Live quality benchmark
Benchmark realistic bolder and polish tasks across fast, full-model, and full-context worker profiles with deterministic and independent quality gates.\n\nAI-assisted: OpenAI Codex.
2026-07-12 19:48:51 -07:00