Best models for Hermes

Hermes runs your skills locally and leans on the model for planning and skill use. These are the models that pair best with it right now, ranked by real agentic-coding performance and day-to-day reliability.

The ranking
  • 1Claude
    Claude Opus 4.8AnthropicTop-tier planning and skill use. The safest default if budget allows.
    Context1M
    Input$5/M
    CursorBench63.8%
  • 2Claude
    Claude Sonnet 4.6AnthropicThe sweet spot: near-Opus quality for routine Hermes runs at lower cost.
    Context1M
    Input$3/M
    CursorBench49%
  • 3Gemini
    Gemini 3 FlashGoogle DeepMindThe fastest cheap option, great for high-volume local automation.
    Context1.049M
    Input$0.5/M
    CursorBench—
  • 4DeepSeek
    DeepSeek V4DeepSeekBest open-weight pick if you want to self-host the model too.
    Context1.049M
    Input$0.435/M
    CursorBench—
  • 5OpenAI
    GPT-5.2 CodexOpenAIExcellent for code-heavy Hermes workflows and test loops.
    Context400K
    Input$1.75/M
    CursorBench—
More rankings for Hermes

Best free models for Hermes

Want to run Hermes without paying per token? Every model here costs $0 on OpenRouter (rate limits apply) and still handles real agent work.

Best open-source models for Hermes

Open-weight models you can inspect, fine-tune, and self-host. Ideal for privacy-sensitive or air-gapped Hermes setups.
Share:
Details:

  • Agent

    Hermes

  • Models

    5

  • Updated

    June 2026