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.
JEV Model in Action: 20K LinkedIn Contacts Processed in Minutes
User shares their experience using the JEV model since the weekend, integrating it into workflows and successfully analyzing/sorting 20,000 LinkedIn contacts in a few minutes for under a dollar.
Model JEV - používám od víkendu a už ho mám v několika workflows. Jako první jsem mu dal 20 000 LinkedIn kontaktů a VELMI dobře je zvládl analyzovat a protřídit...za pár minut a necelý dolar...🔝
· 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.
