LLM Colosseum – A daily battle royale between frontier LLMs
Live LLM showdown with emergent strategies, beats static leaderboards.

LLM model showdown in snake, but the novelty wears off after five minutes of watching.
AI enthusiasts, LLM researchers, developers curious about model capabilities
ChatGPT playground head-to-head comparisons · Model comparison sites like Hugging Face model rankings
Live LLM showdown with emergent strategies, beats static leaderboards.
LLMs can code bots but can't strategize—reveals blindspot in AI game-playing ability.
Watching AI agents lie and betray each other in a 4X strategy game is hypnotic.
Another bot battle arena, but LLM-written bots lower the barrier to entry.
Civilization matches expose model divergence that static benchmarks miss—but it's a spectacle, not a measurement.
Mafia-as-benchmark with learning-between-batches mechanism; public, inspectable sessions.