2026-10-16 · America/Los_Angeles · 行业新闻 · #8

Show HN: Gemini 4 Argon plays StarCraft

I've refreshed StarSkirmish Bench, a benchmark where LLMs play StarCraft BW by writing code, with results from the flagship models of OpenAI, Anthropic, Google, and Muse

热度 58.0 / 100；排名与评分保留该期记录。