ComingUp ComingUp
StarSkirmish Bench v0.2

StarSkirmish Bench v0.2

Gallery

StarSkirmish Bench v0.2

About

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

Comments (1)

Gregory Emard Gregory Emard 1 week ago

interesting to see how the different models perform in StarCraft BW, what tech stack are you using for the benchmarks?