/ github.com / gke-labs / eval-runner

base-0a3e6b0 Completed

← Back to Runs
Repository
https://github.com/gke-labs/eval-runner.git
Commit
0a3e6b0
Model
google/gemini-3.5-flash-lite
Age
4h
Tasks
2/2 (2 ok, 0 fail)
Total Samples
16 (samples 1-8)
Mean Success Rate
0.56
Total Cost
$0.0475
Tokens Consumed
152642
Latency (mean of per-task p50 / p95)
2.68s / 3.36s

Eval Tasks

eval phase tokens input output reasoning cached n log path
docs/readme_comprehension Completed 151003 150905 98 — — 8/8 (samples 1-8) gs://gkelabs-evalrunner-dev-eval-runner/runs/0a3e6b01043cf8c6eaebcb676001a692ab71c350/docs/readme_comprehension/2026-10-27T15-23-26-00-00_readme-comprehension_GXznZnuNHdkaBBB5v93Qgu.json ↗
docs/readme_comprehension_blind Completed 1639 961 678 — — 1/8 (samples 1-8) gs://gkelabs-evalrunner-dev-eval-runner/runs/0a3e6b01043cf8c6eaebcb676001a692ab71c350/docs/readme_comprehension_blind/2026-10-27T15-22-58-00-00_readme-comprehension-blind_h7rctuXVfkYc7yKHeDt6tw.json ↗