Skip to content
Techavy

HermesBench

HermesBench benchmarks full Hermes personal-agent configurations with public recipes, redacted trace evidence, and reproducibility metadata.

Quick answer

What is HermesBench?

HermesBench benchmarks full Hermes personal-agent configurations with public recipes, redacted trace evidence, and reproducibility metadata. The current public baseline scores 78.

At a glance

Pricing
Not disclosed
Starting price
Not disclosed
Free tier
No
Platforms
Not disclosed
Launched
Not disclosed
Company
Not disclosed

About HermesBench

HermesBench benchmarks full Hermes personal-agent configurations with public recipes, redacted trace evidence, and reproducibility metadata. The current public baseline scores 78.2 across 27 personal-agent recipes with redacted traces you can inspect. The site is deliberately clear that this is one early baseline, not a base-model leaderboard. Recipes What was tested Search by category, prompt, goal, and criteria. The public user pathway is intentionally simple: copy the prompt to Codex, Claude, or another coding agent. Full bundle runs are opt-in because they take longer and cost more.

From the community

User reviews

No user reviews yet. Be the first to share your experience with HermesBench.

Alternatives

Similar to HermesBench

Techavy is reader supported. When you buy through links on our site we may earn an affiliate commission. This never changes our ratings or what we recommend. See our methodology.