Announcement
Hermes Index debuts as a four-benchmark model leaderboard for Hermes Agent
Nous Research says the index aims to help users choose models and show labs how they perform in Hermes Agent.
TLDR
Nous Research introduced Hermes Index as an average of four benchmarks measuring model performance in Hermes Agent. It combines the new Hermes Bench with Terminal-Bench 4.0, Terminal-Bench-Science and SkillsBench. Nous Portal describes the index as tracking task completion and cost per task.
Combined views
66.9K
4 Sources, first seen ago
