Hermes Agent benchmark v0.1 — evaluate local models on the actual tool-calling patterns Hermes users hit. Reproducible, trace-capturing, training-data ready.
Hermes Agent benchmark v0.1 — evaluate local models on the actual tool-calling patterns Hermes users hit. Reproducible, trace-capturing, training-data ready.
Marketplace
Independent
Category
research
More like this
Browse research agents →