AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems

TL;DR

AI-NativeBench introduces a white-box, application-centric benchmark suite for AI-Native systems, enabling detailed analysis of system-level behaviors and engineering challenges beyond traditional model capability metrics.

Contribution

This work presents the first open-source, white-box benchmark suite for AI-Native systems based on Model Context Protocol and Agent-to-Agent standards, enabling granular system analysis.

Findings

Lightweight models often outperform flagship models in protocol adherence.

Inference dominance makes protocol overhead less significant.

Self-healing mechanisms can increase costs on unviable workflows.

Abstract

The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic services. However, this shift renders traditional black-box evaluation paradigms insufficient: existing benchmarks measure raw model capabilities while remaining blind to system-level execution dynamics. To bridge this gap, we introduce AI-NativeBench, the first application-centric and white-box AI-Native benchmark suite grounded in Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards. By treating agentic spans as first-class citizens within distributed traces, our methodology enables granular analysis of engineering characteristics beyond simple capabilities. Leveraging this benchmark across 21 system variants, we uncover critical engineering realities invisible to traditional metrics: a parameter paradox where lightweight models often surpass flagships in protocol adherence, a pervasive inference dominance that renders protocol overhead secondary, and an expensive failure pattern where self-healing mechanisms paradoxically act as cost multipliers on unviable workflows. This work provides the first systematic evidence to guide the transition from measuring model capability to engineering reliable AI-Native systems. To facilitate reproducibility and further research, we have open-sourced the benchmark and dataset.