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 vs Gemini 3.8 Flash benchmark on app review analysis
The author tested Jev against Gemini 3.8 Flash on 1,000 real app reviews for sentiment, topic, bug, and churn risk detection. Jev took 4.6s and $0.023, while Gemini took 18.8s and $0.158, with a GitHub repo linked.
I evaluated #Jev from @typesafeai against @Google #Gemini 3.8 flash Jev decides sentiment, topic, "bug?" and churn risk for 1,000 real app reviews, racing Gemini 3.8 Flash on the same job. Jev: 4.6s, $0.023. Gemini: 18.8s, $0.158. Git repo → https://github.com/goodrahstar/jev-column-race…
· 8 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.
