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 Benchmarks: Accuracy vs. Calibration Evaluation
Evaluation of Jev and nine open checkpoints across 22 tasks shows Jev leads on macro accuracy, but an open 4B model produces better-calibrated probabilities; jev-bench is fully open.
Jev Tests: Accuracy gave one ranking. Calibration gave another. We evaluated Jev and nine open checkpoints across 22 tasks. Jev led on macro accuracy. But an open 4B model produced better-calibrated probabilities. jev-bench is fully open 👇
· 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.
