devwithjev
— reading now— views
Submit a build

Benchmarks Jev on Pokémon Red

The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.

hughwalker08hughwalker08@hughwalker08
Benchmarking Jev (TypeSafe's fast decision model) against Jev + a GPT-6 Sol planner at playing Pokémon Red, in a shared PyBoy harness built on NousResearch/pokemon-agent.
Sep 27, 2026GitHubView on GitHub
The benchmarks use a shared PyBoy harness built on NousResearch/pokemon-agent.

Also filed under Games & real time