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

pr-391-f3fda21 Completed

← Back to Runs
Repository
https://github.com/codebot-robot/eval-runner.git
Commit
f3fda21
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
$0.0303
Tokens Consumed
92838
Latency (mean of per-task p50 / p95)
3.05s / 4.12s

Eval Tasks

eval phase cost n log path
docs/readme_comprehension Completed $0.0278 8/8 (samples 1-8) gs://gkelabs-evalrunner-dev-eval-runner/runs/f3fda211d85123b41f9b4126845a4ab74e82923b/docs/readme_comprehension/2026-10-27T16-36-25-00-00_readme-comprehension_EfFeooE8oG5278Mpq6tZgG.json ↗
docs/readme_comprehension_blind Completed $0.0025 1/8 (samples 1-8) gs://gkelabs-evalrunner-dev-eval-runner/runs/f3fda211d85123b41f9b4126845a4ab74e82923b/docs/readme_comprehension_blind/2026-10-27T16-35-41-00-00_readme-comprehension-blind_Ws3yaPoS9zT22diKzhtwmN.json ↗