# Benchmark run 20261015T124100Z-suite-paper_repro-gemini-c5ea8f

Status `success`, agent `gemini`, commit `38e979372a0f`.

| suite | tasks | pass rate | 95% CI | incidents as fail | incident rate | tokens in / out | cost |
|---|---|---|---|---|---|---|---|
| paper_repro | 3 | 1.000 | [1.000, 1.000] (cluster_bootstrap) | 1.000 | 0.000 | 250461 / 8141 | 0.241107 |

- paper_repro: by kind agent 1.000 (n=2), design 1.000 (n=1); accuracy given t1 0/0; tool coverage 56/56 (by_construction); agent coverage 55/56 (by_construction)

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