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 Open Access Test: 900 Decisions Graded by Opus 5
The author ran 9 decisions on each of 300 public web pages for 2 cents total, then had Opus 5 grade all 900: 85.8/100 overall agreement, rising to 98/100 when Jev is confident, with open source and a side-by-side video.
First thing I did with open access: 300 public web pages, 9 decisions each, 2 cents total, then Opus 5 graded 900 of them. 85.8 of 100 agree, and where Jev is sure it is 98 of 100. Open source, with a side by side video:
· 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.
