Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Jev 1.13.0 Benchmarks: #1 in Intelligence
Benchmark Heaven's head-to-head test for Jev 1.13.0: Hopper beats Jev in Calibration, Speed, and Cost, but Jev keeps #1 in Intelligence (53.1 vs 48.0) and wins the hard tier. Overall score Jev 63.29 vs Hopper 59.43.
Hopper (#3) beats Jev 1.13.0 on three of four columns: Calibration 79.1 vs 76.3, Speed 86.8 vs 83.3, Cost 58.7 vs 52.0. Jev keeps #1 on the fourth: Intelligence 53.1 vs 48.0, hard tier 74.1% vs 65.0%. Under 50, the gate applies. Score 63.29 vs 59.43. https://benchmarkheaven.com/jev-models/v1.4.1?compare=jev-1.13.0,hopper…
· 0 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.
