GitHub · by Yifan-Lan
Tests, calibration audits and failure-mode studies of Jev.
Yifan-Lan’s awesome-jev-robustness collects tests, calibration audits and failure-mode studies of Jev: jaggedness, consistency, injection and abstention.
Open the source
GitHubBenchmarks and evals
A Python toolkit: question builders, confidence gates and calibration.
Daniel Ari Friedman
5
GitHubBenchmarks and evals
Vercel’s open agent framework, with Jev as its default evaluate model.
Vercel
5.3k
GitHubBenchmarks and evals
Where Jev holds up and where it breaks, with real API receipts.
Zaious
24