Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Independent Test of Jev: No Text Generation, 97.5% Accuracy
This post reports an independent evaluation of the Jev model, achieving 97.5% accuracy on 400 verification questions, comparable to GPT-6 Astra, at roughly 500 times lower cost.
«Может ли модель, не генерирующая текст, конкурировать с передовыми LLM? Мы независимо протестировали модель Jev в сравнении с 11 другими моделями. На 400 вопросах проверки утверждений она показала точность 97,5%, как и GPT-6 Astra, затраты составили примерно в 500 раз меньше»
· 4 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
