Back to evaluations
Public evaluation

trial_matching_task

Evaluates Pydantic output validation compliance, inclusion decision precision, and criterion checks.

Evaluation type
task based
Challenge
Trial Eligibility Engine for Anti-Inflammatory Drugs using Pydantic AI
Difficulty
Intermediate
Rigor
Unspecified

Evaluation overview

How the linked challenge is judged: tasks, benchmarks, and criteria count.

Tasks
1
Benchmarks
0
Criteria
0

Task templates

Inputs and expected outputs.

Task 1

trial_matching_task

Evaluates patient eligibility for IL-6 inhibitor cardiovascular trial.

Input format

JSON containing OMOP patient clinical record.

Output format

JSON strictly matching Pydantic schema for TrialEligibilityResult.