Hermes Index Launched — Agentic Performance + Cost Benchmark

Nous launched the Hermes Index, an opinionated leaderboard measuring real agentic task completion and cost-per-task inside Hermes Agent. Claude Opus 5.5 currently leads (~63.31 at ~$4.99/task). Other models (GPT-6 variants, DeepSeek, etc.) ranked with cost transparency. Scores are updated as new models land (e.g., Step 5 Preview adjustments).

Credit@NousResearch

Cover art for Releases: Hermes Index Launched — Agentic Performance + Cost Benchmark

Why it matters

Gives builders concrete data on which models actually deliver work inside Hermes rather than raw benchmarks. Cost-aware ranking is especially useful for production and multi-agent setups.

From the source

Hermes Agent #hermes-index #benchmarks #cost #agent-performance #models

More Releases

ReleasesOct 27

GPT-6.1 Terra Available in Hermes Agent

Teknium announced GPT-6.1 Terra is now available in Hermes Agent via Nous Portal and OpenRouter. OpenAI positions Terra as fast, capable computer-use model at lower cost.

Credit@Teknium

ReleasesSep 30

Favorite Models Land in Hermes Desktop

A community PR from @HermesAgentTips is merged: you can favourite a model in Hermes Desktop so the picker stops being a scroll hunt. @imbabybrooklyn posted the screenshot; Tips confirmed the merge.

Credit@imbabybrooklyn, @HermesAgentTips

ReleasesSep 28

Hermes Agent v0.21.5 Patch Drop

Patch release with ~460 merged PRs since v0.21.4. Improvements to Desktop plugin SDK, new interface mode, Connectors page, and expanded model support (GPT-6, Claude Opus 5.5). Update via `hermes update`.

Credit@AmintasTec

Never miss a night

Every pick, delivered to your reader.

One feed for everything, or one per agent harness you run. Rebuilt every night, with full credit on every item.