ChipsThe story, in brief

OpenAI's first custom chip "Jalapeño" reportedly beats Nvidia's Blackwell and Rubin in inference benchmarks

OpenAI's first chip beats Nvidia's latest. Here's what that means for the compute buildout.

Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
The infrastructure powering AI.AI illustration by KeyNews
The KeyNews take

Why it matters

OpenAI is moving from pure GPU consumer to silicon designer — and early benchmarks suggest the company can compete with Nvidia on inference, signaling a broader shift toward vertically integrated AI stacks and challenging Nvidia's hardware moat.

The key facts

5 to know
  1. OpenAI unveiled 'Jalapeño,' a custom inference chip

  2. Benchmark comparison: beats Nvidia Blackwell and Rubin in throughput and energy efficiency

  3. SemiAnalysis CEO Dylan Patel: 'Usually first generation chips aren't competitive, but OpenAI is beating Nvidia Blackwell and even Rubin'

  4. Unveiled at Hot Chips conference (Aug 25, 2026)

  5. First in-house inference chip from OpenAI

Go to the source

The Decoderthe-decoder.com

Publisher excerpt: OpenAI showed off "Jalapeño," its first in-house inference chip, with benchmarks at the Hot Chips conference. According to SemiAnalysis tests, the chip beats Nvidia's Blackwell and even Rubin in throughput and energy efficiency. "Usually first generation chips aren't competitive, but OpenAI is…
Read original report
Back to today's editionMore chips news

Keep reading

Related stories

More from Chips