Hermes Bench leaderboard

Hermes Bench (Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind) is an agentic benchmark published by Hermes Bench (Hermes Index). Tests agents on 150 tasks across 25 categories, including Hermes skills, research, diagrams and art, memory, tool use and safety. Each agent starts in a workspace with real files, some tasks add follow-up turns, and the grader checks the files and state left behind. Its evaluation set is described by the source as 150 tasks across 25 categories. The source rates its difficulty as frontier agentic.

Each model's result is published by Hermes Bench (Hermes Index) as pass@1 score. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 17 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.