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 Classifies 2,300 AI Papers in ~83s for $0.14: A Pipeline Cost Discussion
The author notes Jev's case suits small teams: 2,300 AI papers in ~83 seconds for $0.14, but cautions this isn't Jev's single-model cost—old labels were pre-run by DeepSeek V4 Flash, so the real test is the full classification pipeline of preprocessing, Jev decisions, and human spot checks.
Jev 这个案例很适合小团队：2,300 篇 AI 论文，约 83 秒，成本 $0.14。 但这个数字不能直接当成 Jev 的单模型成本。旧标签先由 DeepSeek V4 Flash 跑过，真正该测的是整条分类链路：预处理、Jev 决策和人工抽检加起来还剩多少。
· 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.
