StarSkirmish Bench
AssessPlatforms
A benchmark that evaluates LLMs by the quality of StarCraft bot code they can produce under time limits.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7Hacker News·10/16/2026researchGemini 4 Argon ranks third in StarSkirmish StarCraft bot benchmark
StarSkirmish Bench v0.2 measures how well LLMs can write a Protoss StarCraft: Brood War bot in one hour, then tests the result against human-written and model-written bots. In this version, GPT-6 Astra leads, while Gemini 4 Argon places third and shows higher run-to-run variance than some peers.