# MLBenchy — Testing Machine Learning speed > Device performance testing for machine learning inference speeds. (iPhone/iPad app by Francois PIEDNOEL.) - Source: https://appshunter.io/ios/app/mlbenchy/id1482528571 (this page in markdown: same URL + `.md`) - Developer: [Francois PIEDNOEL](https://appshunter.io/developer/1044169697) - Category: Education, Productivity - Price: Free - Rating: 5.00/5 from 1 App Store ratings - Age rating: 4+ - Requires: iOS 12.0 · 369 MB - Languages: American English - Released: 2019-10-22 - Data updated: 2026-06-24 - Monetization: free - User reviews in markdown: https://appshunter.io/ios/app/mlbenchy/id1482528571/reviews.md ## What is MLBenchy? MLBenchy is running few neural networks on the platform. The application is pretty large, around 360MB because it includes 7 of the most commonly used inferences. We recommend that you only download it over wifi. It is using very common machine learning algorithms and evaluate the level of performance of your device. Here are the details of the performance test: Nudity detection model is 224x224, net size is 24MB TinyYolo is 416x416, net size is 64MB Restnet is 224x224, net size is 100MB Sentiment is a Dictionary based inference, with a string to Double association , Net size is 275KB. Car Recognition is 224x224 , net size is 25MB GenderNet is 227x227, net size is 45MB InceptionV3 is 299x299, Net size is 94MB GoogleNetPlaces is 224x224, and net size is 25MB 1st iteration of the benchmark is loading the neuronal network into memory, while running the inference once. It shows you the warm up time of the CoreML system. 2nd iteration is having too much variation to be meaning full. 3rd iteration shows you a pretty stable number. Please contact us if you need interpretation assistance. This application will help you to make a purchasing decision, it will allow you to compare the new platforms with the previous one, and decide if you want to spend the extra money and upgrade. - The Purpose of the app is to help customers/consumers and programmers to understand the level of performance of the platform. - The target audience is consumers interested to understand the level of performance of the platform and my friends in the online tech press interested to evaluate the future usage models enabled by the progress in machine learning across the platforms. - The app is intended for the general public, to allow them to compare platforms and make an inform decision about the machine learning and architecture capabilities of the platform. - The Application does not requires accounts, it is free to use for anybody without logging. - One of the targeted audience is the online press, they did express the need to have this application available for the general public, as they require to get their own customers to verify the analysis they do about the computing platforms they are writing about. ## Key features - Tests neural network inference speeds - Evaluates device performance - Assists in hardware purchasing decisions - Compares platform capabilities - Includes multiple common ML algorithms ## Frequently asked questions about MLBenchy ### What is MLBenchy used for? MLBenchy is used to test the speed and performance of your device's machine learning capabilities by running various neural networks. It helps you understand how well your device handles complex AI tasks and can inform purchasing decisions for new hardware. ### Does MLBenchy require an account? No, MLBenchy does not require any accounts or logging in to use. It is completely free and accessible to anyone who wishes to test their device's performance. ### What kind of machine learning models does MLBenchy test? MLBenchy tests several common machine learning models including Nudity detection, TinyYolo, Restnet, Sentiment analysis, Car Recognition, GenderNet, InceptionV3, and GoogleNetPlaces. ### How large is the MLBenchy application? MLBenchy is a large application, approximately 360MB, due to the inclusion of seven commonly used neural network inferences. It is recommended to download over Wi-Fi. ### What is the purpose of the first iteration in MLBenchy? The first iteration of the benchmark in MLBenchy is designed to load the neural network into memory and run the inference once. This process helps to show the 'warm-up' time of the device's CoreML system. ### Can MLBenchy help me decide if I should upgrade my device? Yes, MLBenchy is intended to help consumers make purchasing decisions. By evaluating the performance of your current platform, you can compare it with previous models and decide if upgrading is worthwhile. ### Is MLBenchy available on all devices? MLBenchy is supported on iPhones, iPads, and iPods. It is designed to run on Apple's ecosystem of devices. ### How often is MLBenchy updated? The provided data indicates that the latest version of MLBenchy is 2.1, and it was last updated on October 22, 2019. There is no information on the frequency of future updates. ## Version history (last 1 release) ### 2.1 — 2019-10-22 No release notes. ## Apps similar to MLBenchy | App | Rating | Price | Category | | --- | --- | --- | --- | | [GraspABC](https://appshunter.io/ios/app/graspabc/id1482901273) | 4.7 (23) | Free | Education | | [Shrimad Bhagavad Gita Complete](https://appshunter.io/ios/app/shrimad-bhagavad-gita-complete/id1462275544) | 4.8 (46) | Free | Education | | [AACC Mobile](https://appshunter.io/ios/app/aacc-mobile/id905999095) | 2.1 (52) | Free | Education | | [Gravitational Wave Events](https://appshunter.io/ios/app/gravitational-wave-events/id1441897107) | 4.8 (118) | Free | Education | | [Baja SAE](https://appshunter.io/ios/app/baja-sae/id1366762799) | 2.5 (13) | Free | Education | | [ARI 9000 - Personal AI Tutor](https://appshunter.io/ios/app/ari-9000-personal-ai-tutor/id1508491281) | 2.6 (5) | Free | Education | ## More apps by Francois PIEDNOEL - [TheMoonView](https://appshunter.io/ios/app/themoonview/id1482525464) - [BlackHolesHD](https://appshunter.io/ios/app/blackholeshd/id1491124772) - [TriBlackHolesHD](https://appshunter.io/ios/app/triblackholeshd/id1491286521) All apps by Francois PIEDNOEL: https://appshunter.io/developer/1044169697 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-06-24.*