typesafe-ai-benchmark

A gateway-shaped benchmark rig that speaks structured System One, useful when you need apples-to-apples latency stories.

by @iamMrDuncan

What it does

Benchmark harness material that mimics gateway-style structured output so you can stress Jev-like paths without wiring every vendor by hand. Treat it as lab equipment: reproduce numbers on your hardware before you quote blog-post latencies in a roadmap deck.

Gateway-shaped benchmark rig for structured System One paths. Reproduce latency and calibration on your box before you quote blog numbers in a deck.

Related products

Hand-picked neighbors with rich profiles or overlapping tags.

IntegrationsTypeScript5,253

DemoFeatured

eve

Vercel's agent framework with Jev wired into the experimental evaluate path, so scoring stays typed.

integrationsagentseval

Details Demo

BenchmarksPython4,785

DemoFeatured

SemIf

Semantic ifs on a home 3090: open models doing structured branches without pretending to be TypeSafe.

benchmarksopen-sourceself-hosted

Details Demo

BenchmarksPython851

Featured

jevlike

Train a small model that chooses among a changing list of text options, one probability per option in a single pass.

by @hhkkmon

benchmarksgame

Details

IntegrationsTypeScript796

DemoFeatured

ai-cli

Vercel Labs terminal CLI that can point evaluate at Jev instead of another vibes-based judge.

integrationseval

Details Demo

typesafe-ai-benchmark

What it does

Tags

Related products