[go: up one dir, main page]

AI Benchmark V6 Mobile

Version:  6.0.0   |   Last Updated: 25.09.2024

AI Benchmark V6 is designed for the next-generation AI accelerators, and is introducing many new tests and workloads including the recent vision transformer (ViT) architectures, large language models (LLMs), and even the Stable Diffusion network running directly on your device. Can your smartphone's NPU handle these new workloads? Get the latest AI Benchmark build to extensively evaluate its performance!

AI Benchmark V5 Mobile

Version:  5.1.2   |   Last Updated: 03.03.2024

Not yet ready for generative AI and large transformer models? Then AI Benchmark V5 is designed for your needs, with numerous classical workloads including FullHD and 4K video super-resolution, real-time question answering, recent neural networks for image recognition, photo reconstruction and NLP tasks, all coupled with accurate power consumption measurements available in the PRO mode.

AI Benchmark IoT

Version:  5.1.2   |   Last Updated: 10.06.2024   |   Direct APK Download

AI Benchmark build for Android Smart TVs and IoT platforms.

AI Benchmark Mobile

Version:  4.0.4

Is your smartphone capable of running the latest Deep Neural Networks to perform these AI-based tasks? Does it have a dedicated AI Chip? Is it fast enough? Run AI Benchmark to professionally evaluate its AI Performance!

AI Benchmark Alpha

Version:  0.1.2

AI Benchmark Alpha is an open source python library for evaluating AI performance of various hardware platforms, including CPUs, GPUs and TPUs. The benchmark is relying on TensorFlow machine learning library, and is providing a precise and lightweight solution for assessing inference and training speed for key ML models.

Burnout Benchmark

Version:  2.0.2

Burnout Benchmark is a professional tool for an extensive performance evaluation of all chipset components. It pushes the device to its limits by loading CPU, GPU, NPU and DSP by 100% separately or simultaneously to assess the real-world device performance under heavy load and check its thermal throttling behavior over time.

Copyright © 2018-2024 by A.I.

ETH Zurich, Switzerland