# AIvaluateXR: An Evaluation Framework for on-Device AI in XR with Benchmarking Results

arXiv: https://arxiv.org/abs/2502.15761 · HTML: https://mlsanity.com/paper/2502.15761/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Builds on (most cited first, 21 of 21)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships](https://mlsanity.com/paper/2402.12259/) (2024)
- [Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs](https://mlsanity.com/paper/2309.05516/) (2023)
- [Instant3D: Instant Text-to-3D Generation](https://mlsanity.com/paper/2311.08403/) (2023)
- [LLMR: Real-time Prompting of Interactive Worlds using Large Language Models](https://mlsanity.com/paper/2309.12276/) (2023)
- [Embedding Large Language Models into Extended Reality: Opportunities and Challenges for Inclusion, Engagement, and Privacy](https://mlsanity.com/paper/2402.03907/) (2024)
- [VOICE: Visual Oracle for Interaction, Conversation, and Explanation](https://mlsanity.com/paper/2304.04083/) (2023)
- [LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models](https://mlsanity.com/paper/2502.02441/) (2025)
- [Everyday AR through AI-in-the-Loop](https://mlsanity.com/paper/2412.12681/) (2024)
- [Augmenting a Large Language Model with a Combination of Text and Visual Data for Conversational Visualization of Global Geospatial Data](https://mlsanity.com/paper/2501.09521/) (2025)

## Built on by (most cited first, 1 of 1)

- [ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality](https://mlsanity.com/paper/2604.04905/) (2026)

## Abstract (arXiv)

The deployment of large language models (LLMs) on extended reality (XR) devices has great potential to advance the field of human-AI interaction. In the case of direct, on-device model inference, selecting the appropriate model and device for specific tasks remains challenging. In this paper, we present AIvaluateXR, a comprehensive evaluation framework for benchmarking LLMs running on XR devices. To demonstrate the framework, we deploy 17 selected LLMs across four XR platforms: Magic Leap 2, Meta Quest 3, Vivo X100s Pro, and Apple Vision Pro, and conduct an extensive evaluation. Our experimental setup measures four key metrics: performance consistency, processing speed, memory usage, and battery consumption. For each of the 68 model-device pairs, we assess performance under varying string lengths, batch sizes, and thread counts, analyzing the trade-offs for real-time XR applications. We propose a unified evaluation method based on the 3D Pareto Optimality theory to select the optimal device-model pairs from quality and speed objectives. Additionally, we compare the efficiency of on-device LLMs with client-server and cloud-based setups, and evaluate their accuracy on two interactive tasks. We believe our findings offer valuable insight to guide future optimization efforts for LLM deployment on XR devices. Our evaluation method can be used as standard groundwork for further research and development in this emerging field. The source code and supplementary materials are available at: www.nanovis.org/AIvaluateXR.html