AA-AgentPerf: Vera Rubin leads on inference energy efficiency
Summary
Artificial Analysis 的 AA-AgentPerf 基准通过回放真实编码 agent 轨迹测试推理硬件能效，结果显示 NVIDIA Vera Rubin 在几乎所有速度档位上均居前沿首位，领先于 DeepSeek V4 Flash/Pro、Kimi K3 和 GLM-5.2/5.3 等模型的测试配置。
Similar Articles
AA-AgentPerf-Local: Benchmarking local AI agents on laptops and workstations
Artificial Analysis open-sources AA-AgentPerf-Local, an inference benchmarking tool that replays real agent trajectories to measure how fast agentic AI runs on laptops and workstations, with initial results for NVIDIA DGX Spark, RTX 5090, AMD Ryzen AI Halo, and MacBook Pro M5 Pro.
Up to 30x More Work Per Watt: NVIDIA Vera Rubin NVL72 Sets a New Efficiency Standard for AI Agents
NVIDIA's Vera Rubin NVL72 system demonstrates up to 30x higher throughput per megawatt for agentic AI workloads, setting a new efficiency standard for AI infrastructure.
NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
NVIDIA's Vera Rubin NVL72 system debuts with leading performance in MLPerf Inference v6.1, delivering up to 3.7x better throughput than GB300 NVL72 on benchmarks like DeepSeek-R1 and Qwen3-VL, emphasizing system performance, scaling efficiency, and software optimizations.
NVIDIA Vera Rubin Maximizes Intelligence per Dollar for Post-Training Workloads — a Key Metric for Agentic AI
NVIDIA introduces Vera Rubin, a new architecture designed to maximize intelligence per dollar for post-training workloads, addressing the continuous learning demands of agentic AI by optimizing cost per token and supporting reinforcement learning at scale.
AA introduces Coding Agent Index - Performance Comparisons between Model & Harness Combinations
Artificial Analysis introduces the Coding Agent Index, a new benchmark suite combining SWE-Bench-Pro-Hard-AA, Terminal-Bench v2, and SWE-Atlas-QnA to evaluate the performance of AI coding agents across diverse tasks.