StarSkirmish

Latest news

1. 16 Oct
   StarSkirmish benchmark lets LLMs write StarCraft bots in one hour

   StarSkirmish v0.2 is a benchmark where large language models get one hour to write a Protoss bot in C++ and are scored by win rate against human-written and demo bots. The v0.2 run compares flagship models from OpenAI, Anthropic, Google and Meta, with GPT-6 Astra top-scoring and Gemini 4 Argon, Claude Opus 5.5 and Claude Fable 5.1 grouped behind other leaders.

   Models · 1 source

   

Articles

No articles about StarSkirmish yet.