Artificial Analysis Reports Up to 1.5x Faster DeepSeek V4.1 Flash on GB300 NVL72

1 reports 1 reporting sources Updated 1 hours ago

Understand the event

AI overview

Artificial Analysis reported that DeepSeek V4.1 Flash delivered up to 1.5 times more tokens per second per agent on GB300 NVL72 systems in its AA-AgentPerf benchmark, compared with a month earlier. The benchmark runs realistic agentic coding workloads on data center systems. Artificial Analysis attributed the improvement to a newer vLLM version and new vLLM kernels.

Generated by AI from reports · Updated 57 minutes ago

Latest development11/7 04:33 (UTC+8)

DeepSeek V4.1 Flash Speeds on GB300 NVL72 Increase by Up to 1.5x Artificial Analysis · X

Models in this story

DeepSeek V4.1 Flash$0.051 input / $0.57 output per million tokens

API prices of all models

Report timeline

Follow the reports to explore different sides of the event.

11/7

04:33
Artificial Analysis · X
DeepSeek V4.1 Flash Speeds on GB300 NVL72 Increase by Up to 1.5x
DeepSeek V4.1 Flash speeds on GB300 NVL72 have increased by up to 1.5x tok/s per agent over the past month on AA-AgentPerf, our benchmark of datacenter systems running realistic agentic coding workloads This improvement comes from a newer vLLM version, new vLLM kernels for https://t.co/IyfpiEyhO5

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.