pr-391-b3-cand Completed
Eval Tasks
| eval | phase | latency (p50/p95) | n | log path |
|---|---|---|---|---|
| docs/readme_comprehension_blind | Completed | 2.40s / 2.95s | 2/5 (samples 17-24) | gs://gkelabs-evalrunner-dev-eval-runner/runs/184dfbc73f5a4c073be67666fc2bde04710a9e07/docs/readme_comprehension_blind/2026-10-27T15-48-02-00-00_readme-comprehension-blind_ButJNdghhNQ484KxvxCwaX.json ↗ |