Hermes Agent

Multi-modal agentic harness with persistent memory, tool orchestration, and autonomous task execution. Built for production-grade AI workflows.

94.2+1.3% (24h)

Non-Gameable Scoring

Scores are derived from established benchmarks, adjusted for harness-specific performance across four dimensions: Coding, Reasoning, Tool Use, and Autonomy.

Each dimension starts from public benchmark data and applies harness-specific modifiers based on tool integration, context handling, and orchestration quality. The overall score is a weighted composite that penalizes narrow optimization.

Model	Overall	Coding	Reasoning	Tool Use	Autonomy
Claude Sonnet 4.6	96.1	97	95	98	94
GPT-5.4	93.8	94	96	92	91
Grok 3	92.5	91	93	94	90
Gemini 2.5 Pro	91.2	90	92	91	89