Sign in

Compare Evaluations

Compare two session evaluations and return a detailed comparison report.

This endpoint evaluates both sessions (using cache if available) and generates a comprehensive comparison across 5 dimensions with AI-generated justifications.

post/compare_evaluations

Request body

session_a_idstring required

First session ID to compare

session_b_idstring required

Second session ID to compare

evaluation_typestring nullable

Evaluation type to use. If not provided, auto-detects from existing evaluations.

skip_cacheboolean

Whether to skip cached evaluations

num_runsinteger

Number of judgment runs per dimension for stability (1-50, recommend 3-5)

Response

Successful Response

Changes