Generated: 2026-03-08T23:26:58Z
Scorecard glob: evals/scorecards/v*-contract-skill-benchmark.md
- Minimum cases for a reportable run:
60 - Minimum consecutive reportable releases for KPI publication:
2 - Latest release:
v0.5.0 - Consecutive reportable releases (latest-first):
1 - KPI publication status:
hold
| Release | Cases | Precision | Recall | Reportable | Scorecard |
|---|---|---|---|---|---|
v0.5.0 |
76 |
1.000 |
1.000 |
yes |
evals/scorecards/v0.5.0-contract-skill-benchmark.md |
v0.4.0 |
26 |
1.000 |
1.000 |
no |
evals/scorecards/v0.4.0-contract-skill-benchmark.md |
v0.3.0 |
2 |
1.000 |
1.000 |
no |
evals/scorecards/v0.3.0-contract-skill-benchmark.md |