Demo-cache floor
The model alone, shown every demonstration it bought for the task again for free.
- Stream, budget used
- 38.1 solved 63%
- Epilogue, budget used
- 47.8 solved 48%
- Model spend
- $1.60 1,548 calls
- Instances
- 225 5.5 hours
Budget used is the share of the cap of 16 that an instance used, averaged over the instances: a wrong answer and a demonstration each cost 1, so lower is better.
- Workstreams
- Sequential
- Random
- Fresh
- Stateless floor
- Demo-cache floor
- Program library
- Prime Agent
- Hermes Agent
- OpenClaw