OpenClaw, told to keep a program library
Told to keep one tested program per task and run it first when the task returns.
- Stream, budget used
- 12.3 solved 98%
- Epilogue, budget used
- 23.5 solved 88%
- Model spend
- $12.35 3,546 calls
- Instances
- 225 15.4 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.
- As shipped
- Memory wiped
- Asked to store
- Told to keep a program library
- Told to keep a program library, memory wiped
- Workstreams
- Sequential
- Random