On the Bench · AI tool benchmarks

Reproducible, honest benchmarks for the AI tooling you actually run.

Every entrant is measured the same way, on neutral hardware: same box, same mock upstream, same load, same CPU pin.

Every number regenerates from committed JSON. Fully open source, re-runnable by anyone.

Built and operated by the Busbar team, who are also one of the entrants. Same harness for everyone. A failure is our bug until proven the gateway's.

Published OpenAI → OpenAI measurements

Gateway overhead against a local mock. Independent runs; compare configurations before drawing ratios.

GatewayAdded p99 (µs)StateMeasured at
agentgateway251Valid
AISIX (api7)174Valid
APISIX340Valid
Bifrost1,057Valid
Busbar89Valid
GoModel565Valid
Helicone274Valid
Higress943Valid
Kong410Valid
LiteLLM · Python9,522Valid
LiteLLM · Rust279Valid
One-API589,609Valid
Plano205,966Valid
Portkey3,902Valid
TensorZero41,966Valid