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.
Testing Jev's classification accuracy: solid for AIHOT pre-screening
The author tested Jev's classification accuracy for pre-screening AI-related content on AIHOT, finding it solid; GLM 5.3 Flash got everything right but was the slowest.
Finally got some time to test Jev. Its classification accuracy is indeed pretty good. On AIHOT, for a small pre-screening task—judging whether incoming content is AI-related—it's solid. GLM 5.3 Flash is the only one that got everything 100% right, but it's also the slowest and
· 196 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.
