🧪NIST Evaluates DeepSeek V4 Pro: Trails US Frontier Models by Eight Months but Wins on Cost
NIST Evaluates DeepSeek V4 Pro: Trails US Frontier Models b…
TL;DR
The Center for AI Standards and Innovation at NIST published its May 2026 evaluation of DeepSeek V4 Pro.
The Center for AI Standards and Innovation at NIST published its May 2026 evaluation of DeepSeek V4 Pro. Capabilities trail leading US closed models by roughly eight months and roughly match GPT-5, while DeepSeek V4 proved more cost-efficient than GPT-5.4 mini on five of seven benchmarks.
Key Points
Capabilities trail US frontier models by ~8 months
Open-weight performance similar to GPT-5
More cost-efficient than GPT-5.4 mini on 5 of 7 benchmarks
Why It Matters
First official US government benchmark of a major Chinese open model, with direct implications for export controls and open-source policy.
Frequently Asked Questions
Why does this matter?
First official US government benchmark of a major Chinese open model, with direct implications for export controls and open-source policy.
What happened?
The Center for AI Standards and Innovation at NIST published its May 2026 evaluation of DeepSeek V4 Pro.
Comments
Be the first to comment
Enjoyed this article?
Get it daily. 7am. Free. Reads in 5 minutes.
Join 3,461 builders reading daily.