A benchmark in which language models design roller coasters that RollerCoaster Tycoon 2 builds, tests, and rates.
{"dir":2}user cancelled MCP tool call
{"dir":2}user cancelled MCP tool call
{"dir":2,"ride_type":51,"x":50,"y":85}user cancelled MCP tool call
{"dir":2,"ride_type":51,"x":50,"y":85}user cancelled MCP tool call
user cancelled MCP tool call
user cancelled MCP tool call
← gpt-5.6-sol · 20260727-gpt56-sol-design-preflight-failed · all runs