AI Benchmark
8.9 143
v6.0.2 by Ignatov Andrey
About AI Benchmark
AI Benchmark (Package Name: org.benchmark.demo) is developed by Ignatov Andrey and the latest version of AI Benchmark 6.0.2 was updated on March 27, 2025. AI Benchmark is in the category of Tools. You can check all apps from the developer of AI Benchmark and find 162 alternative apps to AI Benchmark on Android. Currently this app is for free. This app can be downloaded on Android 5.0+ on APKFab or Google Play. All APK/XAPK files on APKFab.com are original and 100% safe with fast download.
Neural Image Generation, Face Recognition, Image Classification, Question Answering...
Is your smartphone capable of running the latest Deep Neural Networks to perform these and many other AI-based tasks? Does it have a dedicated AI Chip? Is it fast enough? Run AI Benchmark to professionally evaluate its AI Performance!
Current phone ranking: http://ai-benchmark.com/ranking
AI Benchmark measures the speed, accuracy, power consumption and memory requirements for several key AI, Computer Vision and NLP models. Among the tested solutions are Image Classification and Face Recognition methods, AI models performing neural image and text generation, neural networks used for Image / Video Super-Resolution and Photo Enhancement, as well as AI solutions used in autonomous driving systems and smartphones for real-time Depth Estimation and Semantic Image Segmentation. The visualization of the algorithms’ outputs allows to assess their results graphically and to get to know the current state-of-the-art in various AI fields.
In total, AI Benchmark consists of 83 tests and 30 sections listed below:
Section 1. Classification, MobileNet-V3
Section 2. Classification, Inception-V3
Section 3. Face Recognition, Swin Transformer
Section 4. Classification, EfficientNet-B4
Section 5. Classification, MobileViT-V2
Sections 6/7. Parallel Model Execution, 8 x Inception-V3
Section 8. Object Tracking, YOLO-V8
Section 9. Optical Character Recognition, ViT Transformer
Section 10. Semantic Segmentation, DeepLabV3+
Section 11. Parallel Segmentation, 2 x DeepLabV3+
Section 12. Semantic Segmentation, Segment Anything
Section 13. Photo Deblurring, IMDN
Section 14. Image Super-Resolution, ESRGAN
Section 15. Image Super-Resolution, SRGAN
Section 16. Image Denoising, U-Net
Section 17. Depth Estimation, MV3-Depth
Section 18. Depth Estimation, MiDaS 3.1
Section 19/20. Image Enhancement, DPED
Section 21. Learned Camera ISP, MicroISP
Section 22. Bokeh Effect Rendering, PyNET-V2 Mobile
Section 23. FullHD Video Super-Resolution, XLSR
Section 24/25. 4K Video Super-Resolution, VideoSR
Section 26. Question Answering, MobileBERT
Section 27. Neural Text Generation, Llama2
Section 28. Neural Text Generation, GPT2
Section 29. Neural Image Generation, Stable Diffusion V1.5
Section 30. Memory Limits, ResNet
Besides that, one can load and test their own TensorFlow Lite deep learning models in the PRO Mode.
A detailed description of the tests can be found here: http://ai-benchmark.com/tests.html
Note: Hardware acceleration is supported on all mobile SoCs with dedicated NPUs and AI accelerators, including Qualcomm Snapdragon, MediaTek Dimensity / Helio, Google Tensor, HiSilicon Kirin, Samsung Exynos, and UNISOC Tiger chipsets. Starting from AI Benchmark v4, one can also enable GPU-based AI acceleration on older devices in the settings ("Accelerate" -> "Enable GPU Acceleration" / "Arm NN", OpenGL ES-3.0+ is required).
Is your smartphone capable of running the latest Deep Neural Networks to perform these and many other AI-based tasks? Does it have a dedicated AI Chip? Is it fast enough? Run AI Benchmark to professionally evaluate its AI Performance!
Current phone ranking: http://ai-benchmark.com/ranking
AI Benchmark measures the speed, accuracy, power consumption and memory requirements for several key AI, Computer Vision and NLP models. Among the tested solutions are Image Classification and Face Recognition methods, AI models performing neural image and text generation, neural networks used for Image / Video Super-Resolution and Photo Enhancement, as well as AI solutions used in autonomous driving systems and smartphones for real-time Depth Estimation and Semantic Image Segmentation. The visualization of the algorithms’ outputs allows to assess their results graphically and to get to know the current state-of-the-art in various AI fields.
In total, AI Benchmark consists of 83 tests and 30 sections listed below:
Section 1. Classification, MobileNet-V3
Section 2. Classification, Inception-V3
Section 3. Face Recognition, Swin Transformer
Section 4. Classification, EfficientNet-B4
Section 5. Classification, MobileViT-V2
Sections 6/7. Parallel Model Execution, 8 x Inception-V3
Section 8. Object Tracking, YOLO-V8
Section 9. Optical Character Recognition, ViT Transformer
Section 10. Semantic Segmentation, DeepLabV3+
Section 11. Parallel Segmentation, 2 x DeepLabV3+
Section 12. Semantic Segmentation, Segment Anything
Section 13. Photo Deblurring, IMDN
Section 14. Image Super-Resolution, ESRGAN
Section 15. Image Super-Resolution, SRGAN
Section 16. Image Denoising, U-Net
Section 17. Depth Estimation, MV3-Depth
Section 18. Depth Estimation, MiDaS 3.1
Section 19/20. Image Enhancement, DPED
Section 21. Learned Camera ISP, MicroISP
Section 22. Bokeh Effect Rendering, PyNET-V2 Mobile
Section 23. FullHD Video Super-Resolution, XLSR
Section 24/25. 4K Video Super-Resolution, VideoSR
Section 26. Question Answering, MobileBERT
Section 27. Neural Text Generation, Llama2
Section 28. Neural Text Generation, GPT2
Section 29. Neural Image Generation, Stable Diffusion V1.5
Section 30. Memory Limits, ResNet
Besides that, one can load and test their own TensorFlow Lite deep learning models in the PRO Mode.
A detailed description of the tests can be found here: http://ai-benchmark.com/tests.html
Note: Hardware acceleration is supported on all mobile SoCs with dedicated NPUs and AI accelerators, including Qualcomm Snapdragon, MediaTek Dimensity / Helio, Google Tensor, HiSilicon Kirin, Samsung Exynos, and UNISOC Tiger chipsets. Starting from AI Benchmark v4, one can also enable GPU-based AI acceleration on older devices in the settings ("Accelerate" -> "Enable GPU Acceleration" / "Arm NN", OpenGL ES-3.0+ is required).
AI Benchmark 6.0.2 Update
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
Read More
AI Benchmark Features
Previous Versions
More
Variant
Arch
Version
DPI
49
March 19, 2025
AI Benchmark
6.0.2
(49)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 7ea86a86aa018ed350bb359d338892c05ac0bea6
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxhdpi, config.zh
Size: 1.41 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
49
March 20, 2025
AI Benchmark
6.0.2
(49)
Requires Android: Android 5.0+
Architecture: armeabi-v7a
Screen DPI: nodpi
SHA1: 4f90a22352f730b7a2107078130add4f4b225412
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.armeabi_v7a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xhdpi, config.zh
Size: 1.34 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
armeabi-v7a
Android 5.0+
nodpi
49
March 27, 2025
AI Benchmark
6.0.2
(49)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 9227ff08f762a223ba345772671e08098538e066
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xhdpi, config.zh
Size: 1.41 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
49
March 27, 2025
AI Benchmark
6.0.2
(49)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 9feaeb81a2a7285db5026dc7fcd5b10e57b45d89
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxxhdpi, config.zh
Size: 1.41 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 198e153e93f20ab2408c4eaee954a44209879624
Size: 1.41 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
Variant
Arch
Version
DPI
47
September 26, 2024
AI Benchmark
6.0.0
(47)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 3219a8a291728f921c73ab021bea246aefa61eb8
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxhdpi, config.zh
Size: 1.39 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
47
September 26, 2024
AI Benchmark
6.0.0
(47)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 3497ae284fb50888ae3f6fb2bc30c13aad1da77e
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.arm64_v8a, config.en, config.fr, config.mdpi
Size: 1.39 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
47
September 26, 2024
AI Benchmark
6.0.0
(47)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 4b20dff1bc9639546889d4730e496d7f2fb7f47d
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxhdpi, config.zh
Size: 1.39 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
arm64-v8a
Android 5.0+
nodpi
47
September 26, 2024
AI Benchmark
6.0.0
(47)
Requires Android: Android 5.0+
Architecture: armeabi-v7a
Screen DPI: nodpi
SHA1: 8e8e1f9d1fedd058e3f0bbc676178c06de180ff8
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.armeabi_v7a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xhdpi, config.zh
Size: 1.34 GB
What's New:
1. New tasks and models: Vision Transformer (ViT) architectures, Large Language Models (LLMs), Stable Diffusion network, etc.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
2. Added tests checking the performance of quantized INT16 inference.
3. LiteRT (TFLite) runtime updated to version 2.17.
4. Updated Qualcomm QNN, MediaTek Neuron, TFLite NNAPI, GPU and Hexagon NN delegates.
5. Added Arm NN delegate for AI inference acceleration on Mali GPUs.
6. The total number of tests increased to 83.
armeabi-v7a
Android 5.0+
nodpi
Variant
Arch
Version
DPI
40
March 6, 2024
AI Benchmark
5.1.2
(40)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: 6a648cc39344d73cae597505ea039ec32d776a15
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xhdpi, config.zh
Size: 778.85 MB
What's New:
1. Updated Qualcomm QNN and MediaTek Neuron delegates.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
arm64-v8a
Android 5.0+
nodpi
40
March 6, 2024
AI Benchmark
5.1.2
(40)
Requires Android: Android 5.0+
Architecture: arm64-v8a
Screen DPI: nodpi
SHA1: cadf1d58fa3693a0d58b886b96f6e17f277f2290
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.arm64_v8a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxhdpi, config.zh
Size: 778.86 MB
What's New:
1. Updated Qualcomm QNN and MediaTek Neuron delegates.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
arm64-v8a
Android 5.0+
nodpi
40
March 6, 2024
AI Benchmark
5.1.2
(40)
Requires Android: Android 5.0+
Architecture: armeabi-v7a
Screen DPI: nodpi
SHA1: 8500f1060c091b6e98330c2c263e53092431524d
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.armeabi_v7a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xxhdpi, config.zh
Size: 739.11 MB
What's New:
1. Updated Qualcomm QNN and MediaTek Neuron delegates.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
armeabi-v7a
Android 5.0+
nodpi
40
March 7, 2024
AI Benchmark
5.1.2
(40)
Requires Android: Android 5.0+
Architecture: armeabi-v7a
Screen DPI: nodpi
SHA1: 3d1fc857f1f3cb46c0cf6e3aa721f459c64bb19d
Base APK: org.benchmark.demo.apk
Split APKs: ai_benchmark_assets, config.ar, config.armeabi_v7a, config.de, config.en, config.es, config.fr, config.hi, config.in, config.it, config.ja, config.ko, config.my, config.pt, config.ru, config.th, config.tr, config.vi, config.xhdpi, config.zh
Size: 739.09 MB
What's New:
1. Updated Qualcomm QNN and MediaTek Neuron delegates.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
2. Enhanced stability and accuracy of the power consumption test.
3. Various bug fixes and performance improvements.
armeabi-v7a
Android 5.0+
nodpi
More Information
Package Name:
Update Date:
2025-03-27
Latest Version:
6.0.2
Need Update:
Available on:
Requirements:
Android 5.0+
Report:
Safe to Download
APKFab.com and the download link of this app are 100% safe. All download links of apps listed on APKFab.com are from Google Play Store or submitted by users. For the app from Google Play Store, APKFab.com won't modify it in any way. For the app submitted by users, APKFab.com will verify its APK signature safety before release it on our website.