Hermes Agent, as shipped
Every learning mechanism the harness ships switched on.
- Held-out tasks, budget used
- 29.1 solved 87%
- Model spend
- $5.18 7,461 calls
- Instances
- 100 11.9 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.