# ROBOTERA reports manipulation benchmark lead for open-source VPP2

_Published Friday, October 9, 2026 at 12:19 PM EDT · Robotics · Latest · Tier 2 — Notable_

![ROBOTERA reports manipulation benchmark lead for open-source VPP2 — Primary](https://s.yimg.com/lo/mysterio/api/f9da9cdfc97865757cc6d8f1cb0b1001dca278aa819280a8a4d60278a3a4b165/lightyear_networkapi/resizefill_w1200%3Bquality_80%3Bformat_webp/https%3A%2F%2Fmedia.zenfs.com%2Fen%2Fprnewswire.com%2F1b4e99b33ddecffe0c85b9cadf1b1bee.jpg)

ROBOTERA said its open-source VPP2 robot model ranked first on RoboDojo, a benchmark covering simulated and real-world manipulation tasks, with a 32.26% average success rate. The company said the result required neither additional data nor agent-based reinforcement self-improvement.

VPP2 combines predictions of how objects will move with commands that translate instructions into physical actions. ROBOTERA reported a 58.5% average success rate across 10 task categories on the ALOHA platform. Adding high-level task planning raised success across five task groups from 27.6% to 57.6%, making the planning configuration a material qualification to its performance claims.

## Sources

- [Yahoo Finance](https://finance.yahoo.com/technology/ai/articles/robotera-tops-embodied-ai-benchmark-144400309.html)

---
Canonical: https://techandbusiness.org/newswire/uInt7x3AAStPZu77lzDv1h
Published: 2026-10-09T16:19:09.001Z
Story chronology: 2026-10-09T14:44:00.000Z
Retrieved: 2026-10-09T19:34:19.725Z
Publisher: Tech & Business (techandbusiness.org)