# Benchmark run 20261015T171350Z-suite-tool_selection-scripted-900f27

Status `success`, agent `scripted`, commit `2925aeab2262`.

| suite | tasks | pass rate | 95% CI | incidents as fail | incident rate | tokens in / out | cost |
|---|---|---|---|---|---|---|---|
| tool_selection | 70 | 1.000 | [0.948, 1.000] (wilson) | 1.000 | 0.000 | 0 / 0 | — |

Rendered from summary.json; every number there is recomputable from results.jsonl.