All benchmark types
GenAI (similarity · introspection)
Generative-AI-adjacent micro-benchmarks — embedding similarity and graph introspection helpers.
Latest commit a40cf2a1 · every metric smaller-is-better · each group header shows a competitive summary computed live from real same-box competitor numbers (or an honest placeholder where none exist yet).
No metrics are reported for this benchmark type yet. The CI benchmark workflow will populate it as soon as it emits — this section is kept visible so coverage is honest, never fabricated.