Expand description
The eval report types: one CaseOutcome per case and the aggregate EvalReport with a
readable Display summary table.
Structs§
- Case
Outcome - The result of running one eval case.
- Eval
Report - The aggregate report over a set of cases, plus latency/token statistics.
- RunRecord
- One persisted eval run: an
EvalReportplus the run metadata the HTML report needs to label, sort, and group runs across models and over time. Serialized toresults/{model}_{timestamp_file}.json.