▌system-one

~ / benchmarks / suites-harnesses / evals-typesafe-ai

evals.typesafe.ai

TypeSafe's workflow evals: four production-shaped workflows scored against frontier LLM reference probabilities.

section
Benchmarks
group
Suites & harnesses
source
evals.typesafe.ai
added to list
sep 20

also in Suites & harnesses