FlashNEWS BRIEFING

NVIDIA Open-Sources Autonomous Driving AI Inference Model Alpamayo 2 Super

1 min read

88Z AI, 10 August — NVIDIA has released Alpamayo 2 Super, an open-source autonomous driving model built on Cosmos 3 Super Reasoner. Licensed under OpenMDW 1.1 for commercial use and fine-tuning, it ranks top in benchmarks like LingoQA. The model outputs five result types, including trajectory planning and causal reasoning, ensuring transparent and verifiable decision-making.

At a glance

  • Built on Cosmos 3 Super Reasoner with OpenMDW 1.1 license supporting commercial use and fine-tuning
  • Ranks first in benchmarks like LingoQA, outputting five result types to ensure transparent and verifiable decisions
Cover image for NVIDIA Open-Sources Autonomous Driving AI Inference Model Alpamayo 2 Super
Cover image for NVIDIA Open-Sources Autonomous Driving AI Inference Model Alpamayo 2 Super

The update

NVIDIA has officially launched Alpamayo 2 Super, an open model for intelligent vehicles built on the Cosmos 3 Super Reasoner architecture. The project adopts the OpenMDW 1.1 commercial license, explicitly supporting enterprise commercial deployment and model fine-tuning. In terms of performance, the model ranks first in assisted driving benchmarks such as LingoQA. It is capable of outputting five key types of results: trajectory planning, causal reasoning, meta-actions, automatic annotation, and visual question answering. This multi-dimensional output capability makes the AI's decision-making process more transparent, facilitating verification and debugging by developers, thereby enhancing the safety and reliability of autonomous driving systems.

Sources & editorial note

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.

  1. SuperSource published

Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.

Related reading

All stories
88Z.ai