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.
Pairing the Jev Model with DuckDB for Analytical Q&A
Pairing the new Jev model with DuckDB shows potential for answering one-off analytical questions and returning classifier-like probabilities.
Pairing the new Jev model with DuckDB is already showing a lot of potential. Many analytical questions are simply a "Yes" or "No" question that is usually meant to get you to the next question. Jev allows you to ask one off questions and get probabilities similar to a classifier
· 0 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.
