# Benchmark run 20261015T171234Z-suite-nist_anova-baseline-71784e

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

| suite | tasks | pass rate | 95% CI | incidents as fail | incident rate | tokens in / out | cost |
|---|---|---|---|---|---|---|---|
| nist_anova | 22 | 0.364 | [0.227, 0.500] (cluster_bootstrap) | 0.364 | 0.000 | 0 / 0 | — |

- nist_anova: by kind tool 0.727 (n=11), agent 0.000 (n=11); reference path agreement 8/11; tool coverage 11/11 (source_split); agent coverage 11/11 (source_split); failures no_estimate_cited 11, out_of_tolerance 3

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