Back to evaluations
Public evaluation

Phishing Payload Classification Task

Evaluates detection precision of scam messages and container response latency on Modal execution.

Evaluation type
task based
Challenge
Google ADK & Modal Anti-Scam Verification Service
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

Phishing Payload Classification Task

Classifies SMS text and accompanying web screenshot into SCAM or LEGITIMATE

Input format

JSON containing message text and image URL

Output format

JSON containing label, confidence, indicators, and latency_ms