Hermes Agent, memory wiped
Everything the harness wrote deleted before every instance.
- Held-out tasks, budget used
- 24.1 solved 93%
- Model spend
- $3.99 4,692 calls
- Instances
- 100 10.3 hours
Budget used is the share of the cap of 16 that an instance was charged, averaged over the instances: a solved instance costs 1 for each wrong answer and each demonstration, an unsolved one all 16, so lower is better.