
Geekbench AI - Cross-Platform AI Benchmark
Geekbench AI is a cross-platform AI benchmark that uses real-world machine learning tasks to evaluate AI workload performance. Geekbench AI measures your CPU, GPU, and NPU to determine whether …
Download Geekbench AI
Windows Download for Windows System Requirements: Windows 10 (64-bit) or later 8GB of RAM Processor Requirements: AMD, ARM, or Intel processor
Geekbench AI Editions
Includes machine learning workloads that model real-world AI tasks and applications. Geekbench ML is a benchmark that helps users determine if their devices are ready for today's and tomorrow's cutting …
Latest Geekbench AI Results
2 days ago · Explore the latest Geekbench AI results for evaluating AI performance across various platforms and devices.
Geekbench AI 1.5 - Geekbench Blog
Sep 5, 2025 · Geekbench AI 1.5, the latest update to our cross-platform AI benchmark, is now available. This update includes updates to several AI frameworks, improving compatibility with the latest …
Geekbench 6 - Cross-Platform Benchmark
Verify device performance using the Geekbench Benchmark Charts. Available on the Geekbench Browser, these charts are based on data aggregated from real users in real-world environments.
AI Benchmarks - Geekbench
The data on this chart is gathered from user-submitted Geekbench AI results from the Geekbench Browser. To make sure the results accurately reflect the average performance of each device, the …
Geekbench AI 1.0 - Geekbench Blog
Aug 15, 2024 · Geekbench AI gives you the insight a developer or a hardware vendor would look for when benchmarking a given device’s AI performance by showing you performance across three …
AI Benchmark scores are used to evaluate and optimize CPU, GPU, NPU, and DSP performance using workloads that include Computer Vision and Natural Language Processing tasks.
Geekbench AI 1.2 - Geekbench Blog
Dec 2, 2024 · Due to these improvements, Geekbench AI 1.2 scores may be higher than Geekbench AI 1.1 scores on Android and Windows, which means Geekbench AI 1.2 scores aren’t strictly …