The runs of this benchmark
One row per CLI run: the audit writes one second statement per question per run, so a prediction file is a run. Every benchmark is indexed a level up.
| run | date | engine | question set | question set digest |
|---|---|---|---|---|
| demo | 2026-09-08T04:11:01.285823+00:00 | sqlite | demo/questions.json | sha256:7ad58addc070b425cabfc9d67bbd9c95840253160cf3b73d672e9aeb4897f5ff |