AI Benchmark
8.9 143
v6.0.2 by Ignatov Andrey
關於 AI Benchmark
AI Benchmark（包名：org.benchmark.demo）開發者是Ignatov Andrey，AI Benchmark的最新版本6.0.2更新時間為2025年03月27日。AI Benchmark的分類是工具。您可以查看AI Benchmark的開發者下的所有應用並找到AI Benchmark在安卓上的162個相似應用。目前這個應用免費。該應用可以從APKFab或Google Play下載到Android 5.0+。APKFab.com的所有APK/XAPK文檔都是原始文檔並且100%安全下載的資源。
神經影像生成、臉部辨識、影像分類、問答...
您的智慧型手機是否能夠運行最新的深度神經網路來執行這些以及許多其他基於人工智慧的任務？有專用的AI晶片嗎？夠快嗎？運行AI Benchmark，專業評估其AI性能！
目前手機排名：http://ai-benchmark.com/ranking
AI Benchmark 衡量多個關鍵 AI、電腦視覺和 NLP 模型的速度、準確性、功耗和記憶體需求。測試的解決方案包括影像分類和人臉辨識方法、執行神經影像和文字生成的人工智慧模型、用於影像/視訊超解析度和照片增強的神經網絡，以及用於自動駕駛系統和智慧型手機的即時人工智慧解決方案。演算法輸出的視覺化允許以圖形方式評估其結果，並了解各個人工智慧領域的當前最新技術。
AI Benchmark 總共包含 83 項測試和 30 個部分，如下所示：
第 1 節：分類，MobileNet-V3
第 2 節：分類，Inception-V3
第三節 人臉識別，Swin Transformer
第 4 節：分類，EfficientNet-B4
第 5 節. 分類，MobileViT-V2
第 6/7 節。並行模型執行，8 x Inception-V3
第 8 節. 對象跟踪，YOLO-V8
第 9 節. 光學字元識別，ViT 變壓器
第 10 節. 語意分割，DeepLabV3+
第 11 節：並行分割，2 x DeepLabV3+
第 12 節：語意分割，分割任何內容
第 13 節：照片去模糊，IMDN
第 14 節. 影像超分辨率，ESRGAN
第 15 節：影像超分辨率，SRGAN
第 16 節：影像去噪，U-Net
第 17 節. 深度估計，MV3-深度
第 18 節：深度估計，MiDaS 3.1
第 19/20 節。影像增強，DPED
第 21 節. 學習相機 ISP、MicroISP
第 22 節. 散景效果渲染，PyNET-V2 Mobile
第 23 節：全高清視訊超分辨率，XLSR
第 24/25 節。 4K 視訊超解析度、VideoSR
第 26 節：問答，MobileBERT
第 27 節. 神經文本生成，Llama2
第 28 節. 神經文本生成，GPT2
第 29 節 神經影像生成，穩定擴散 V1.5
第 30 節：記憶體限制，ResNet
除此之外，人們還可以在 PRO 模式下載入和測試自己的 TensorFlow Lite 深度學習模型。
測試的詳細描述可以在這裡找到：http://ai-benchmark.com/tests.html
附註：所有具有專用 NPU 和 AI 加速器的行動 SoC 均支援硬體加速，包括 Qualcomm Snapdragon、MediaTek Dimensity / Helio、Google Tensor、HiSilicon Kirin、Samsung Exynos 和 UNISOC Tiger 晶片組。從 AI Benchmark v4 開始，還可以在舊設備上在設定中啟用基於 GPU 的 AI 加速（“加速”->“啟用 GPU 加速”/“Arm NN”，需要 OpenGL ES-3.0+）。
您的智慧型手機是否能夠運行最新的深度神經網路來執行這些以及許多其他基於人工智慧的任務？有專用的AI晶片嗎？夠快嗎？運行AI Benchmark，專業評估其AI性能！
目前手機排名：http://ai-benchmark.com/ranking
AI Benchmark 衡量多個關鍵 AI、電腦視覺和 NLP 模型的速度、準確性、功耗和記憶體需求。測試的解決方案包括影像分類和人臉辨識方法、執行神經影像和文字生成的人工智慧模型、用於影像/視訊超解析度和照片增強的神經網絡，以及用於自動駕駛系統和智慧型手機的即時人工智慧解決方案。演算法輸出的視覺化允許以圖形方式評估其結果，並了解各個人工智慧領域的當前最新技術。
AI Benchmark 總共包含 83 項測試和 30 個部分，如下所示：
第 1 節：分類，MobileNet-V3
第 2 節：分類，Inception-V3
第三節 人臉識別，Swin Transformer
第 4 節：分類，EfficientNet-B4
第 5 節. 分類，MobileViT-V2
第 6/7 節。並行模型執行，8 x Inception-V3
第 8 節. 對象跟踪，YOLO-V8
第 9 節. 光學字元識別，ViT 變壓器
第 10 節. 語意分割，DeepLabV3+
第 11 節：並行分割，2 x DeepLabV3+
第 12 節：語意分割，分割任何內容
第 13 節：照片去模糊，IMDN
第 14 節. 影像超分辨率，ESRGAN
第 15 節：影像超分辨率，SRGAN
第 16 節：影像去噪，U-Net
第 17 節. 深度估計，MV3-深度
第 18 節：深度估計，MiDaS 3.1
第 19/20 節。影像增強，DPED
第 21 節. 學習相機 ISP、MicroISP
第 22 節. 散景效果渲染，PyNET-V2 Mobile
第 23 節：全高清視訊超分辨率，XLSR
第 24/25 節。 4K 視訊超解析度、VideoSR
第 26 節：問答，MobileBERT
第 27 節. 神經文本生成，Llama2
第 28 節. 神經文本生成，GPT2
第 29 節 神經影像生成，穩定擴散 V1.5
第 30 節：記憶體限制，ResNet
除此之外，人們還可以在 PRO 模式下載入和測試自己的 TensorFlow Lite 深度學習模型。
測試的詳細描述可以在這裡找到：http://ai-benchmark.com/tests.html
附註：所有具有專用 NPU 和 AI 加速器的行動 SoC 均支援硬體加速，包括 Qualcomm Snapdragon、MediaTek Dimensity / Helio、Google Tensor、HiSilicon Kirin、Samsung Exynos 和 UNISOC Tiger 晶片組。從 AI Benchmark v4 開始，還可以在舊設備上在設定中啟用基於 GPU 的 AI 加速（“加速”->“啟用 GPU 加速”/“Arm NN”，需要 OpenGL ES-3.0+）。
AI Benchmark 6.0.2 更新
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.
查看更多
AI Benchmark 資訊
歷史版本
更多
Variant
Arch
Version
DPI
49
2025年03月19日
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
2025年03月20日
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
2025年03月27日
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
2025年03月27日
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
2024年09月26日
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
2024年09月26日
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
2024年09月26日
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
2024年09月26日
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
2024年03月06日
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
2024年03月06日
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
2024年03月06日
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
2024年03月07日
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
更多資訊
更新日期:
2025-03-27
最新版本:
6.0.2
請求更新:
Available on:
系統要求:
Android 5.0+
舉報:
安全下載
APKFab.com和該應用的下載連結是100%安全的。APKFab.com上列出的所有應用下載連結均來自Google Play Store或由用戶提交。對於來自Google Play商店的應用，APKFab.com不會對其進行任何形式的修改。對於用戶提交的應用，APKFab.com會在網站上發佈之前驗證其APK簽名的安全性。