NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt

Properly characterizing hardware performance for this workload presents new challenges. A useful benchmark must capture long-context prefill, KV-cache reuse, interactive decode, tool-call gaps, and distributed mixture of experts (MoE) execution under realistic concurrency. It must also show how much of the AI-factory power budget is converted into useful agentic throughput while maintaining an acceptable user experience.

This post examines SemiAnalysis AgentX, a benchmark that evaluates AI infrastructure for agentic-coding inference using replayed production-style sessions. It highlights Vera Rubin NVL72 preview results showing up to 30x higher AI-factory throughput per megawatt than GB300 NVL72, while showing that Blackwell GB300 NVL72 extends its order-of-magnitude throughput-per-megawatt advantage over prior generations to dynamic agentic workloads.

What is AgentX?[](#what_is_agentx)

AgentX is the agentic-coding benchmark in InferenceX, SemiAnalysis’s open-source benchmark suite. It measures how efficiently accelerators serve the request patterns produced by real coding agents.

AgentX testing and measurement methodology[](#agentx_testing_and_measurement_methodology)

Agentic sessions are long, stateful, and variable: they chain model calls, tool use, and growing context rather than following a fixed prompt-and-response pattern (Figure 1, below). AgentX therefore measures whether a platform can serve replayed agent traffic responsively, reuse previously processed context, and maximize agentic throughput per provisioned megawatt.

Figure 1. Agentic sessions create variable inference sequences