pr-391-b3-cand Completed
Eval Tasks
| eval | phase | rate | 95% CI (0-1 axis) | n | method | log path | |
|---|---|---|---|---|---|---|---|
| docs/readme_comprehension_blind | Completed | 0.40 | [0.12, 0.77] | 2/5 (samples 17-24) | wilson | gs://gkelabs-evalrunner-dev-eval-runner/runs/184dfbc73f5a4c073be67666fc2bde04710a9e07/docs/readme_comprehension_blind/2026-10-27T15-48-02-00-00_readme-comprehension-blind_ButJNdghhNQ484KxvxCwaX.json ↗ | |