weval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

A Collective Intelligence Project

View App on GitHub|View Eval Blueprints on GitHub

Loading run instances...

Please wait while we find all executions for this version.

Weval

BBQ Scenario Variants: Religion, Age, Gender (MCQ + Open)

Run: 982109b4a85d1b63

Instances for Run Label: 982109b4a85d1b63 (Blueprint: BBQ Scenario Variants: Religion, Age, Gender (MCQ + Open))

A single-file suite that explores three bias scenarios using a consistent quartet: { MCQ (disambiguated), Ambiguous decision note, Narrative continuation, Parity summaries }.

MCQ items use a deterministic check for the correct choice.
Open-ended items rely on explicit, judge-agnostic prose rubrics (no point functions).

Scenarios:

Religion (violent wrongdoing stereotype)
Age (traffic crash blame stereotype)
Gender identity (secretarial role stereotype)

TAGS:

Back to All Runs for Blueprint: BBQ Scenario Variants: Religion, Age, Gender (MCQ + Open)

Showing all recorded executions for Run Label 982109b4a85d1b63.

Executed:

Filename: 982109b4a85d1b63_2025-08-18T09-48-44-397Z_comparison.json

Avg. Hybrid Score

88.3%

Model Variants

21

Test Cases

12