Hamza(@hamza72510):We benchmarked GPT-6 models in DOOM by having LLM agents fight each other. Across 120 matches, we found: - Astra had the highest win rate at 82.5% - Sol made the fastest decisions at avg of 5.34s - Luna had the most wins per dollar at 12.8 GitHub: https://t.co/dt3JHU7338 @OpenAIDevs @rootlyhq

Hamza

@hamza72510

@openai codex ambassador, @rootlyhq AI Labs, undergrad researcher @uoft, @harvard

Joined July 2025

129 Following 38 Followers

Hamza@hamza72510

2026.09.24 21:35

We benchmarked GPT-6 models in DOOM by having LLM agents fight each other. Across 120 matches, we found: - Astra had the highest win rate at 82.5% - Sol made the fastest decisions at avg of 5.34s - Luna had the most wins per dollar at 12.8 GitHub: @OpenAIDevs @rootlyhq