Toys & Experiments
Four Models Play Doom
A vision-to-action benchmarking dashboard comparing four AI models playing Doom.
byHimanshu
Description
An experimental dashboard that evaluates four distinct AI models—Jev 1.13, Laya, ModernCE, and Qwen3.5—on the 'Defend the Center' scenario in Doom. The project highlights a tiny 48M parameter model performing competitively against flagship models using vision-to-action with pure text output.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.