~ / stacks / hermes-agent-deepseek-v4-pro

Hermes Agent + DeepSeek V4 Pro

A CLI agent plus open/open-weight coding model stack for skills-based terminal experimentation.

AgentHermes Agent
ModelDeepSeek V4 Pro
Agent score39
Model SWE-bench80.6%
Combined score31.4
Best fitskills-based terminal experimentation

Related Hermes Agent stacks

Same agent, different model choices.

Hermes Agent + DeepSeek V4 Flash

ARscore 30.8, 1M context, $0.14/$0.28

view stack

Hermes Agent + Llama 4 Maverick

ARscore 24.2, 1M context, $0.8/$2.2

view stack

Related DeepSeek V4 Pro stacks

Same model, different agent wrappers.

Cursor + DeepSeek V4 Pro

ARscore 57.2, IDE workflow

view stack

Cline + DeepSeek V4 Pro

ARscore 49.2, Extension workflow

view stack

Aider + DeepSeek V4 Pro

ARscore 48.4, CLI workflow

view stack

Continue + DeepSeek V4 Pro

ARscore 47.6, Extension workflow

view stack