All evaluations
API diagnosticsRun it yourself
API quality check
A private, one-time check for protocol shape, response integrity, model claims, and bounded timing signals.
- Category
- API diagnostics
- Status
- Run it yourself
- Method version
- user-tests.v1
- Scope
- One authorized API endpoint
01 / METHOD
What this suite is designed to observe.
The method is the boundary of the claim. Read it before comparing any result or treating a signal as a verdict.
A private, one-time check for protocol shape, response integrity, model claims, and bounded timing signals.
- Method version
- user-tests.v1
- Scope
- One authorized API endpoint
02 / PUBLISHED RESULTS
Evidence from this evaluation.
Only released snapshots with a named window, sample, and method version belong here.
Results not published yet
No Folkbench result snapshot has been published for this suite yet.
03 / RELATED WRITING
Read the thinking behind the test.
Articles explain the task design, review decisions, and what the evidence can or cannot support.
04 / RUN IT YOURSELF
Make one authorized observation of your own.
A user run is private and bounded. It does not create a public score or change a ranking.
Start a private test05 / EVIDENCE LIMITS
What this test cannot prove.
A single suite is one signal. It does not certify a model, station, security posture, or future availability by itself.