Skip to content

benchmark

jev-gateway-bench

Benchmark repository measuring token use, requests, time and correctness of coding-agent sessions with and without Jev routing.

Current clusters

build1 publisher

One ternary in Jev's gateway limits it to hinting inside Claude Code

Jev's own gateway benchmark shows routing raised Opus 5 input tokens 61% on a Claude Code feature task, where the gateway can only hint at tools. Any saving depends on the task and on how many tools Claude Code sends the router each turn.

Publishers:dev.to

Reality

Evidence45
Adoption
Insufficient
Hype gap+40
Incentives
Insufficient
Confidence40