Real Unreal Bench · Task 11
Play an action RPG against its spec and fix what breaks
Claude Opus 5.5Run 1Pass
- Outcome
- Pass
- Duration
- 1h 39m
- Steps
- 162
- Tokens
- 59.5M
- Cost
- $51.17
Task
An action RPG has to ship. Given a spec of its levels, world and menus, the agent plays it through the way a player would, finds the places where it breaks the spec (about nine: levels that never end, rooms and enemies out of reach, menus and controls among them) and fixes them without adding content.
Run details
Event types
- Thoughts125
- Messages10
- Tool calls192
- Commands166
- Reads21
- Writes4
- Done1