Jev beats Gemini 2.5 Flash Lite on classifier eval quality and speed
Malte Ubl ran TypeSafe AI's Jev against an existing classifier eval, where it saturated the eval on quality and was 6x faster than Gemini 2.5 Flash Lite.
Screening 1,000 Resumes with Jev
A user shares running 1,000 resumes against a Senior Backend Engineer JD with Jev in 1 min 28 sec, scoring skill depth, domain fit, and seniority before filtering by experience, education, and required skills.
Ran 1,000 resumes against a Senior Backend Engineer JD using Jev. Whole batch took 1 min 28 sec (~0.44s per resume). It wasn't doing keyword matching. It scored skill depth, domain fit, and seniority first, then filtered for years of experience, education, and required skills.
· 1 likesOpen on X
More like this
Fast row classification in DuckDB with Jev
The author released a DuckDB extension that uses TypeSafe AI's Jev to quickly classify rows in CSV/Parquet files or DuckDB tables, taking about 10 seconds for 1k rows—faster than an LLM and more ergonomic than a classifier.
Classifying 1,018 AI Papers with Jev for $0.08
The author summarized each paper with DeepSeek V4 Flash, then sent the title, summary, and 24 candidate topics to Jev for classification, processing 1,018 AI papers at $0.08 total cost and 256ms median end-to-end latency per paper.
