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

(main)

← Back to Series
showing last 0 of 4 commits
Cohorts Task: docs/readme_comprehension docs/readme_comprehension_blind
Cohorts
Mean score per cohort over commits · 95% CI shaded · pooled Wilson
default (2 evals)
0.00 0.50 1.00 0a3e6b0 2a0e7b7 884fa75 369fe00
Cohort Evals First Seen Commit Latest Mean 95% CI
default 2 0a3e6b0 0.69 [0.44, 0.86]