Primate Labs, the developer behind Geekbench, has introduced the Geekbench AI app, a cross-platform AI benchmarking tool designed to evaluate the performance of AI workloads using real-world machine learning tasks.
Geekbench AI assesses your device’s CPU, GPU, and NPU readiness for current and future machine learning applications.
Geekbench AI 1.0
Geekbench AI offers a comprehensive suite for testing machine learning, deep learning, and AI-centric workloads.
It ensures consistent performance across platforms, helping software developers maintain app performance, enabling hardware engineers to measure architectural improvements, and allowing users to troubleshoot device performance.
Supported Platforms:
- Android: Android 12
- iOS: iOS 17
- Linux: Ubuntu 22.04 LTS
- macOS: macOS 14
- Windows: Windows 10
Originally known as “Geekbench ML,” the benchmark was rebranded as “Geekbench AI” to align with industry terminology and ensure clarity about its purpose, the company said.
Key Features
Performance Scoring: Geekbench AI provides three overall scores—Single Precision, Half Precision, and Quantized—to reflect the diverse AI hardware designs across different devices. This multi-dimensional scoring approach captures AI performance more accurately than a single metric.
Speed and Accuracy: The benchmark includes a new accuracy measurement on a per-test basis, highlighting the importance of both speed and accuracy in AI performance. This allows developers to assess the trade-offs between performance and efficiency, particularly when using smaller data types.
Frameworks and Datasets: Geekbench AI 1.0 supports various frameworks, including OpenVINO and TensorFlow Lite delegates (Samsung ENN, ArmNN, Qualcomm QNN). It uses extensive datasets that mirror real-world AI use cases, enhancing the accuracy of evaluations.
Runtime: Each AI workload runs for at least five iterations and a minimum of one second, ensuring that devices reach their peak performance during testing.
Workloads in Geekbench AI
Computer Vision
- Image Classification: Uses MobileNetV1 to predict the category of an object in an image.
- Image Segmentation: Uses DeepLabV3+ to classify each pixel in an image.
- Pose Estimation: Uses OpenPoseV2 to identify human body parts in an image.
- Object Detection: Uses SSD to detect objects and their locations in an image.
- Face Detection: Uses Retinaface to detect and localize faces in an image.
- Depth Estimation: Uses ConvNets to create a depth map of an image.
- Image Super Resolution: Uses RFDN to enhance low-resolution images.
- Style Transfer: Uses a Fast Real-Time Style Transfer model to blend content and style images.
Natural Language Processing
- Text Classification: Uses BERT-Tiny to perform sentiment analysis.
- Machine Translation: Uses Transformer architecture to translate text between languages.
Integration
Geekbench AI is integrated with the Geekbench Browser, allowing users to compare AI performance across devices and access the latest benchmark results.
Professional and Corporate Licenses Offered
Geekbench AI Pro comes with automated testing tools, an offline mode, a commercial use license, and basic email support.
Availability
Geekbench AI 1.0 is available for download on Windows, macOS, Linux, and through the Google Play Store and Apple App Store.
Announcing the availability, Geekbench posted:
After half a decade of engineering, we’re proud of what we’ve achieved with Geekbench AI. The rapid advancements in machine learning, deep learning, and AI are impressive, and our benchmark will continue to evolve in the coming years to mirror how developers and engineers create their products and how consumers interact with them.