---
title: "Primotion’s Paimon-0 model tops robot benchmarks and cuts action-chunk inference to 300 ms"
slug: "primotions-paimon-0-model-tops-robot-benchmarks-and-cuts-action-chunk"
date: "2026-10-26"
category: "AI & Automation"
author: "Dr. Kai Wei"
correspondent: "Dr. Kai Wei"
correspondentRole: "Lead Frontier AI Correspondent"
readingTimeMinutes: 2
tags: ["AI","News"]
originalSourceUrl: "https://pandaily.com/primotion-paimon-0-embodied-foundation-model-300ms-action-chunk-fpga-control-chip-roadmap"
canonicalUrl: "https://aurav.ae/primotions-paimon-0-model-tops-robot-benchmarks-and-cuts-action-chunk"
publisher: "Aura-V Intelligence (aurav.ae)"
---

# Primotion’s Paimon-0 model tops robot benchmarks and cuts action-chunk inference to 300 ms

> Shenzhen startup Primotion’s embodied foundation model Paimon-0 leads multiple robot leaderboards and reduces action-chunk inference time to 300 ms with FPGA assistance.

## Key Takeaways (TL;DR)

- Paimon-0 scores 0.7754 on RoboColiseum and leads several embodied AI leaderboards.
- Inference per action chunk drops tenfold to 300 ms; FPGA offload cuts EtherCAT timing error to 152 ns.
- A system-on-chip is slated for 2028 and the Paimon-Eval model will be open-sourced later this year.

Primotion, a Shenzhen startup founded in July 2026, announced its embodied foundation model Paimon-0, which the company says ranks first on several public robot benchmarks. The scores—0.7754 on the RoboColiseum leaderboard, 58.1 overall on RoboCasa365, a 0.73 average success rate on VLA-Arena, and 46.599 points in a dual-arm robot policy challenge—are self-reported by Primotion. [source](https://pandaily.com/primotion-paimon-0-embodied-foundation-model-300ms-action-chunk-fpga-control-chip-roadmap)

The model uses a world-action architecture: a world action model predicts future states, which an inverse dynamics model turns into actions. To avoid the latency of rendering full future video, Paimon-0 employs query tokens that distill core visual features such as 3D object pose, semantics and affordance before action prediction. Primotion says this reduces inference for a single action chunk from roughly 3,000 ms to 300 ms.

Primotion adds an FPGA alongside a robot’s main controller to offload pre- and post-processing. The company reports that worst-case timing error on a 1 kHz EtherCAT control cycle fell from 30 µs in software mode to 152 ns with the FPGA. Much of this logic is intended to migrate onto a dedicated system-on-chip, which Primotion plans to begin delivering in 2028.

CEO Ren Qingyuan, a former vice-president at a RISC-V processor firm, argues that running the full loop of data, model, agent and evaluation on real tasks first defines the chip workload. Primotion will not build robot bodies. It plans to open-source its evaluation model, Paimon-Eval, in November or December and expects to release a second foundation model trained on first-person data in about three months.

---

*Original Think-Tank Source: [Shenzhen Embodied-Chip Startup Primotion Unveils Paimon-0, Cutting Action-Chunk Inference to 300 ms](https://pandaily.com/primotion-paimon-0-embodied-foundation-model-300ms-action-chunk-fpga-control-chip-roadmap)*