Back to News
DeepSeek V4.1 Flash Beats Larger Models While Running on Just Two GPUs
A new agentic coding benchmark shows DeepSeek V4.1 Flash squeezing 261M tokens per second per megawatt out of NVIDIA GB300.
Source
Artificial Analysis
Published
Author
AlphaSignal Newsroom
Read
1 min read
A new agentic coding benchmark shows DeepSeek V4.1 Flash squeezing 261M tokens per second per megawatt out of NVIDIA GB300.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
Read original report
