All projects

system-one-bench

hgavert/system-one-bench

Hands-on experiments with open-source System One (Jev-style) decision models on an Apple M5: a zero-shot tweet-sentiment benchmark against local LLMs, and a study of how they play Snake.

Python
Stars
0
Forks
1

Why it is listed

Hands-on benchmark tests open Jev-style models zero-shot on tweet sentiment, Snake decisions and Finnish comprehension, with task reports and comparison baselines.