Runs a suite of cases against one or more models through an adapter the consumer writes, scores each reply with a scorer the consumer writes, and prints leaderboards, per-case breakdowns and Braintrust experiments. The gem knows nothing about what is being evaluated: it owns discovery, the model lineup, providers, parallel execution, reporting and the command line.

Required Ruby Version

>= 3.4.0

Authors

Konstantin Gredeskoul

Versions

  1. 0.2.0

    1. source

      1. 0.2.0 source October 15, 2026 (54.5 KB)
  2. 0.1.1

    1. source

      1. 0.1.1 source October 15, 2026 (54 KB)

Pushed by

kigster

SHA 256 checksum

← Previous version