Real Unreal Bench · Task 11
Play an action RPG against its spec and fix what breaks
Qwen3.8 MaxRun 1Fail
- Outcome
- Fail
- Duration
- 1h 41m
- Steps
- 156
- Tokens
- 40.9M
- Cost
- $12.57
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
- Thoughts156
- Messages1
- Tool calls195
- Commands92
- Reads52
- Writes50
- Done1