ARAgentRanks
~ / stacks / hermes-agent-deepseek-v4-flash

Hermes Agent + DeepSeek V4 Flash

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

ARscore 30.81M context$0.14/$0.28fully open
AgentHermes Agent
ModelDeepSeek V4 Flash
Agent score39
Model SWE-bench79%
Combined score30.8
Best fitskills-based terminal experimentation

Related Hermes Agent stacks

Same agent, different model choices.

Hermes Agent + DeepSeek V4 Pro

ARscore 31.4, 1M context, $0.44/$0.87

view stack

Hermes Agent + Llama 4 Maverick

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

view stack

Related DeepSeek V4 Flash stacks

Same model, different agent wrappers.

Cursor + DeepSeek V4 Flash

ARscore 56.1, IDE workflow

view stack

Cline + DeepSeek V4 Flash

ARscore 48.2, Extension workflow

view stack

Aider + DeepSeek V4 Flash

ARscore 47.4, CLI workflow

view stack

OpenCode + DeepSeek V4 Flash

ARscore 41.9, CLI workflow

view stack