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

LLM Personality Compass: Literal Trait Probe

Run: 617d2ed984e68d3c

Instances for Run Label: 617d2ed984e68d3c (Blueprint: LLM Personality Compass: Literal Trait Probe)

This blueprint tests for the 'Literal' trait. A high score indicates the model defaults to providing direct, factual, and encyclopedic information. It avoids using analogies, metaphors, or creative interpretations.

TAGS:

COMPASS:LITERAL

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Creative Writing

General Knowledge

Science Communication

Back to All Runs for Blueprint: LLM Personality Compass: Literal Trait Probe

Showing all recorded executions for Run Label 617d2ed984e68d3c.

Executed:

Filename: 617d2ed984e68d3c_2025-08-14T12-38-58-378Z_comparison.json

Avg. Hybrid Score

60.5%

Model Variants

125

Test Cases

6