Geekbench AI

A cross-platform AI performance benchmarking tool.

InternationalSelectionOthersAI BenchmarkingPerformance Evaluation

Geekbench AI is a cross-platform AI benchmarking tool that assesses AI workload performance using real-world machine learning tasks. By measuring the performance of CPU, GPU, and NPU, it helps users determine if their devices are ready to handle today’s and future cutting-edge machine learning applications.

Runs ten AI workloads covering three different data types to provide a multidimensional view of device AI performance.
Supports measuring AI performance on CPU
GPU
or dedicated NPU
with the option to select the AI framework on the device for testing.
Runs the same workloads across Android
iOS
Windows
macOS
and Linux platforms for easy cross-platform performance comparison.

Geekbench AI is designed for developers and consumers to evaluate and quantify device performance on machine learning tasks
especially suitable for users who need to test and compare AI performance across different devices.

Smartphone manufacturers use Geekbench AI to test the AI performance of new smartphones.
Software developers leverage Geekbench AI to identify the best combinations of AI frameworks and models to optimize application performance.
Corporate IT departments utilize Geekbench AI to evaluate the AI processing capabilities of different hardware configurations to support business decisions.

Download and install the Geekbench AI application.
Launch the application and select the hardware component to be tested
such as CPU
GPU
or NPU.

Visit

Geekbench AI Visit Over Time

Monthly Visits

1210618

Bounce Rate

45.70%

Page per Visit

2.9

Visit Duration

00:01:50

Geekbench AI Visit Trend

Geekbench AI Visit Geography

Geekbench AI Traffic Sources

Geekbench AI Alternatives

Procyon AI Computer Vision Benchmark — A benchmarking tool for evaluating the performance of AI inference engines on Windows PCs or Apple Macs.

Others•AI Benchmarking•Performance Evaluation

ZML — ZML is an efficient and flexible programming model framework.

InternationalSelection•Machine Learning•Model Deployment

114

OpenCompass Multi-modal Leaderboard — Real-time updated leaderboard of multi-modal model performance

Productivity•Multi-modal•Performance Evaluation

1116

Procyon AI Image Generation Benchmark — A benchmarking tool used to measure the AI accelerator inference performance of devices.

Others•Image Generation•Benchmarking

120

ai-data-science-team — An AI-driven data science team that helps users complete common data science tasks more quickly.

Productivity•Data Science•Automation

timesfm-2.0-500m-pytorch — A pre-trained time series forecasting model developed by Google Research.

Productivity•Time Series Forecasting•Machine Learning

Imitate Before Detect — An advanced approach for detecting machine-revised text, improving detection accuracy by mimicking machine styles.

Programming•Text Detection•Machine Learning

Bakery — An open-source platform for AI model fine-tuning and monetization, empowering AI startups, machine learning engineers, and researchers.

Programming•Model Fine-tuning•Monetization

vectrix-graphs — A graphical library for multi-model embeddings, supporting visualization of various models and data types.

Programming•Graph Library•Multi-Model Embedding

Sonus-1 — Sonus-1: A New Era of Large Language Models (LLMs)

Productivity•Artificial Intelligence•Large Language Models

300

Text-to-CAD UI — Creates B-Rep CAD files and meshes from natural language prompts.

Design•CAD•3D Modeling

210

Zoo.dev — Modern CAD Software for Hardware Design

InternationalSelection•Hardware Design•CAD Software

TangoFlux — An efficient text-to-audio generation model

Music•Text-to-audio•Audio generation

114

InternVL2_5-8B-MPO — A large multimodal language model showcasing exceptional overall performance.

Image•Multimodal•Large Language Model

120

Llama-3.1-70B-Instruct-AWQ-INT4 — Text generation model with 70 billion parameters

Productivity•Text Generation•Natural Language Processing

ModernBERT — ModernBERT is a next-generation encoder model with outstanding performance.

Programming•BERT•Transformer

InternVL2_5-4B-MPO-AWQ — A multimodal large language model designed to enhance image and text interaction capabilities.

Image•Multimodal•Large Language Model

VidTok — A family of open-source video segmenters from Microsoft.

Video•Video Segmentation•Video Compression

DynamicControl — Adaptive condition selection enhances control in text-to-image generation.

Image•Text-to-image•Diffusion model

Valley 2.0 — A multimodal large language model that enhances the ability to process text, image, and video data.

Others•Multimodal•Large Language Model

204

shoonya — Fundamental models and proxies in the business sector

Business•Artificial Intelligence•Machine Learning

Smolagents — A lightweight library for building high-performance intelligent agents.

Programming•Intelligent Agents•Machine Learning

234

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

InternationalSelection•Machine Learning•Reasoning

726

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

InternationalSelection•Machine Learning•Natural Language Processing

372

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

Others•Artificial Intelligence•Machine Learning

126

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Productivity•Machine Learning•Small Language Models

Best AI Websites & Tools