Demo-cache floor
The model alone, shown every demonstration it bought for the task again for free.
- Stream, budget used
- 53.6 solved 24%
- Epilogue, budget used
- 66.5 solved 4%
- Model spend
- $2.41 2,031 calls
- Instances
- 225 8.7 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.