On WebMCP benchmark, Jev alone on raw DOM completes 25/49 tasks. With WebMCP tool selection and Mercury 2.5 writing args, it reaches 49/49 at ~112x lower model cost than GPT-6 Astra.
🧪 The WebMCP benchmark by @0xidanlevin is the best stress test so far. Jev alone on the raw DOM: 25/49 tasks. Jev picking WebMCP tools + Mercury 2.5 writing args: 49/49, ~112x lower model cost than GPT-6 Astra. https://webmcp.com/benchmark
Gregor Zunic showcases an open-source browser agent combining Browser Use and Jev, finding flights in 7 seconds for $0.0039, using a new action space per step, DOM state space, and small LLM fallback for typing.
Scott Williams predicts custom Jev-style models (parallel constrained decoding) will make existing company agent systems more token efficient, creating millionaires.
The user praises the JEV model for its extremely fast reproduction of each movement and command, believing bots will become smarter as a result.
