StarSkirmish Bench: LLMs write StarCraft Brood War bots in one hour, GPT-6 and Opus 5.5 lead
philipvollet · x · 2026-09-27
StarSkirmish Bench gives each LLM one hour to write a Protoss bot in C++ for StarCraft: Brood War (BWAPI 4.4.0 on OpenBW, three ladder maps), scored by win rate against human-written and demo bots (top human bot Stardust = 100, weakest demo = 0).
Key points:
- Tests long-horizon reasoning and agentic coding: LLMs get tools to compile, run practice batches, and read game transcripts with build timings and fight details.
- GPT-6 Astra and Claude Opus 5.5 are functionally tied at the top; with GPT-6 Sol they clearly lead all other models. On a score-vs-cost log plot, GPT-6 Sol offers uniquely good value.
- Games reaching the 60-minute cap (86,400 frames) are decided by kills + razings as on the BASIL ladder.
Related event: StarSkirmish Launches: LLMs Write StarCraft Brood War Bots to Battle(2 posts)→
More from coding & agent
- 100-Paper Review: Most Prompt-Injection Defenses Fail Against Adaptive Attacks — Ok-Lab-7347 · 2026-09-27
- Procedural Three.js Running Horse in One HTML File, via 67 Minutes of AI Thinking — Ok_Bag_7550 · 2026-09-27
- Motion design in pure code: Opus writes Canvas renderer and a Node synth soundtrack — mishig25 · 2026-09-27
- Antigravity Rewind: Open-Source One-Click Surgical Undo for Google Antigravity — Imbourass · 2026-09-27
- Open-Source Fooocus-Style Studio for Qwen-Image 2.1, Built Almost Entirely by Claude — Repulsive_Junket7919 · 2026-09-27
- TailwindCSS MCP server adds class lookup, CSS conversion and palette tools — modelcontextprotocol · 2026-09-27