Back to evaluations
Public evaluation
cad_dfm_evaluation
Validate agent's capability to read parametric CAD metadata and accurately flag manufacturing risks and tolerance violations.
Evaluation type
task based
Challenge
Engineering Intelligence CAD Analysis Pipeline with Claude Agents SDK and Google Jules
Difficulty
Advanced
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
cad_dfm_evaluation
Evaluate DFM check output from raw CAD parametric summary
Input format
JSON object describing wall thickness, material, and geometric constraints
Output format
JSON report listing detected_defects, risk_score, and recommended_design_change