Benchmark Radar™
Star —

AI gateway reproducible benchmark

Explore score history ↗

Compares four open-source AI gateway proxies (GoModel, LiteLLM, Portkey, Bifrost) for routing overhead on a fixed AWS c7i.large instance with a mock backend. Measures latency percentiles, throughput, memory, cold start, and image size across streaming and non-streaming workloads.

Released
2026-08-20
Evaluates
Language & Knowledge, Software & AI Compute, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
ai-name-audit-deferred

AI gateway reproducible benchmark code

No reported scores are on record for this benchmark yet.

Which sources cite AI gateway reproducible benchmark?

Related Language & Knowledge, Software & AI Compute, cs.AI benchmarks