inference-benchmarks
iammrduncan/inference-benchmarks
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
TypeScript
- Stars
- 38
- Forks
- 5
Why it is listed
A synthetic-workload benchmark compares TypeSafe Jev with a constrained Qwen structured-output path and a local tool-calling model; its results are author-reported.