Back to evaluations
Public evaluation

LifeSG Claim Parsing Task

Evaluates parsing accuracy and latency of the AI SDK claim processing API endpoint.

Evaluation type
task based
Challenge
AI SDK & Bolt.new Citizen LifeSG Workflow Automation
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

LifeSG Claim Parsing Task

Extracts document fields and validates citizen benefit eligibility

Input format

JSON containing base64 string or plain text of a child birth certificate / grant application

Output format

JSON matching expected citizen attributes with execution_time_ms