Back to evaluations
Public evaluation
ai_sdk_routing_task
Evaluates routing choices across diverse prompt types and edge thermal states.
Evaluation type
task based
Challenge
Dynamic Hybrid Inference Router with Vercel AI SDK
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
ai_sdk_routing_task
Tests middleware routing logic given incoming user prompt and current edge temperature.
Input format
JSON containing prompt_text, prompt_token_count, edge_temp_c, and latency_sla_ms
Output format
JSON returning chosen_route (edge|cloud), estimated_latency_ms, and routing_rationale