anisselbd/jev-phishing-bench
7 0PythonUpdated 1 week ago
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
Our verdict: not recommended
a reproducible benchmark of Jev vs Claude on phishing emails, not a reusable component for his tooling
Filed under agent harnesses in our directory.