Real Unreal Bench · Task 15
Play an athletics game against its spec and fix it
Gemini 4 ArgonRun 1Pass
- Outcome
- Pass
- Duration
- 48m 13s
- Steps
- 56
- Tokens
- 15.2M
- Cost
- $7.52
Task
Before an athletics game ships, the agent plays it against a full spec (the four-event line-up, the menu and its athlete, the meet, throwing and jumping, the run-up camera, hurdling and sound), finds where it falls short and fixes it, without breaking what works.
Run details
Event types
- Thoughts56
- Messages0
- Tool calls146
- Commands22
- Reads74
- Writes49
- Done1