Agent routing intelligence

Benchmark explorer

Explore a transparent example, or import your own results into a private workspace.

Example data. All example models, endpoints and results are synthetic. They demonstrate the workflow and are not recommendations or measured benchmarks.

Execution paths

SYNTHETIC SUITE

Execution path	Success / attempts	Cost / success	Successful time	Evidence
Balanced path Example model A Example endpoint A	33/36 (91.7%) 12 example tasks × 3	$0.276Includes failed attempts	172sSuccess-only median	Example only Inspect →
Economy path Example model B Example endpoint B	29/36 (80.6%) 12 example tasks × 3	$0.107Includes failed attempts	225sSuccess-only median	Example only Inspect →
Fast path Example model C Unknown upstream	25/36 (69.4%) 12 example tasks × 3	UnknownMissing usage	109sSuccess-only median	Example only Inspect →

Metrics here are arithmetic on synthetic records. No inferential confidence interval or real model ranking is implied.