Skip to content
K = 0.731

Initial AA-AgentPerf Results Show NVIDIA Vera Rubin NVL72 Gains Over GB300 NVL72

1 reports 1 reporting sources 1 day agoNew

Understand the event

AI overview

Artificial Analysis published initial AA-AgentPerf results showing NVIDIA’s Vera Rubin NVL72 delivering up to approximately 5.7 times GB300 NVL72’s throughput per megawatt on DeepSeek V4 Pro, with the largest advantages at faster per-agent output speeds. At peak throughput, gains ranged from 1.14 to 1.45 times across the four tested models. Artificial Analysis reported maximum throughput-per-megawatt advantages of approximately 5.4 times on DeepSeek V4.1 Flash, 3.0 times on GLM-5.2 and 2.8 times on Kimi K3. AA-AgentPerf replays real agentic coding sessions and measures throughput per megawatt of measured GPU power alongside per-agent output speed. NVIDIA submitted all Vera Rubin results using TensorRT-LLM and vLLM with NVIDIA Dynamo.

Generated by AI from reports · Updated 1 day ago

Latest development10/16 09:18 (UTC+8)
NVIDIA Vera Rubin NVL72 posts initial AA-AgentPerf results against GB300 NVL72Artificial Analysis · X

Report timeline

Follow the reports to explore different sides of the event.

10/16
  1. Artificial Analysis · X
    NVIDIA Vera Rubin NVL72 posts initial AA-AgentPerf results against GB300 NVL72

    Artificial Analysis reports that NVIDIA's Vera Rubin NVL72 delivers up to ~5.7x GB300 NVL72's throughput per megawatt on DeepSeek V4 Pro in initial AA-AgentPerf results. Its advantage is largest at faster per-user speeds; peak-throughput gains range from 1.14x to 1.45x across the four tested models. NVIDIA submitted all Vera Rubin results using TensorRT-LLM and vLLM with NVIDIA Dynamo; the benchmark replays real agentic coding sessions and measures throughput per megawatt of measured GPU power alongside per-agent output speed.

Event heat trend

可比范围当前
5
Peak within comparable coverage
1010/16 10:00 (UTC+8)
近 24 小时变化
-51%

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline

Trending now

  1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
  2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
  3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
  4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights