Jev as an LLM router: a mostly negative result

Benchmarks Jev as a router across 13 flagship models on LLMRouterBench and a RouterArena pilot.

Notes

62.4% versus 60.3% for the best single model at 33% lower cost; the gain came from retrieval evidence rather than the difficulty signal. Total spend under $0.006.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Try a walkthrough

• Connect Jev to your app →

  Set up the Python SDK, make a typed routing decision and keep the result under your application's control.

• Route the next step of an agent →

  Let Jev choose a proposed next step, then apply an explicit allow, review or fallback policy before any tool runs.

Verification levels

Report a problem →

Filed under

• #routing
• #benchmark
• #github

In collections

• Benchmarks & independent tests →
• Agent harnesses →