NVIDIA Cites SemiAnalysis AgentX: Rubin NVL72 Shows 30x Better Throughput

nvidia · x · 2026-08-29

NVIDIA highlighted SemiAnalysis's AgentX 1.0, the first open-source, multi-turn agentic coding inference benchmark with 1M context length. Tests indicate that Vera Rubin NVL72 achieves up to 30x better throughput per megawatt compared to GB300 NVL72 on this workload. AgentX replaces fixed sequence length metrics with realistic scenarios featuring long context, high prefill reuse, sub-agent bursts, and KV cache offloading. The $3M dataset is now open source.

Related event: NVIDIA Claims Rubin NVL72 Delivers 30x Better Efficiency on AgentX Benchmark(2 posts)→

Original post →

More from Infra

Infra channel →