Real Unreal Bench · Task 15
Play an athletics game against its spec and fix it
GPT-6 AstraRun 1Pass
- Outcome
- Pass
- Duration
- 28m 14s
- Steps
- 50
- Tokens
- 4.8M
- Cost
- $11.55
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
- Thoughts34
- Messages4
- Tool calls59
- Commands47
- Reads10
- Writes1
- Done1