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.
FLock Benchmark: THIS/THAT Model 94.1% vs Jev Hosted System One 76.5%
FLock.io shares a third-party-recorded 68-question accuracy test: FLock's THIS/THAT Model 1.0 scores 94.1%, while Jev (hosted System One service) scores 76.5%. The post calls this a promising result for a specialised decision model, noting complex tasks needing graph search or multi-step arithmetic remain challenging.
In a test of 68 questions recorded by a third party for accuracy: - FLock's THIS / THAT Model 1.0: 94.1% - Jev (hosted System One service): 76.5% A promising result for a specialised decision model. Complex tasks requiring graph search or multi-step arithmetic remain
· 2 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.
