| framework | Backend | Device | Single | Half | Quant. | Results |
|---|---|---|---|---|---|---|
TensorFlow Lite | CPU | Intel Core i7-1355U | 1267 | 1118 | 804 | https://browser.geekbench.com/ai/v1/247577 |
ONNX | CPU | Intel Core i7-1355U | 1719 | 537 | 4011 | https://browser.geekbench.com/ai/v1/247584 |
OpenVINO | CPU | Intel Core i7-1355U | 1959 | 1876 | 3832 | https://browser.geekbench.com/ai/v1/247588 |
| Workload (TF Lite) | Accuracy | Score | Workload (ONNX) | Accuracy | Score | Workload | Accuracy | Score |
|---|---|---|---|---|---|---|---|---|
| Image Classification (SP) | 100% | 873 162.3 IPS | Image Classification (SP) | 100% | 1028 191.1 IPS | Image Classification (SP) | 100% | 1141 212.2 IPS |
| Image Classification (HP) | 100% | 865 160.9 IPS | Image Classification (HP) | 100% | 187 34.7 IPS | Image Classification (HP) | 100% | 1145 213.0 IPS |
| Image Classification (Q) | 99% | 546 101.8 IPS | Image Classification (Q) | 97% | 3315 618.6 IPS | Image Classification (Q) | 100% | 2573 478.4 IPS |
| Image Segmentation (SP) | 100% | 1136 18.4 IPS | Image Segmentation (SP) | 100% | 945 15.3 IPS | Image Segmentation (SP) | 100% | 1395 22.6 IPS |
| Image Segmentation (HP) | 100% | 1145 18.6 IPS | Image Segmentation (HP) | 100% | 291 4.71 IPS | Image Segmentation (HP) | 100% | 1443 23.4 IPS |
| Image Segmentation (Q) | 98% | 627 10.2 IPS | Image Segmentation (Q) | 99% | 2271 36.9 IPS | Image Segmentation (Q) | 99% | 2640 42.8 IPS |
| Pose Estimation (SP) | 100% | 1665 1.94 IPS | Pose Estimation (SP) | 100% | 2483 2.90 IPS | Pose Estimation (SP) | 100% | 2272 2.65 IPS |
| Pose Estimation (HP) | 100% | 1097 1.28 IPS | Pose Estimation (HP) | 100% | 1393 1.63 IPS | Pose Estimation (HP) | 100% | 1776 2.07 IPS |
| Pose Estimation (Q) | 96% | 1185 1.39 IPS | Pose Estimation (Q) | 94% | 7970 9.35 IPS | Pose Estimation (Q) | 96% | 5342 6.26 IPS |
| Object Detection (SP) | 100% | 892 70.7 IPS | Object Detection (SP) | 100% | 1124 89.2 IPS | Object Detection (SP) | 100% | 1125 89.2 IPS |
| Object Detection (HP) | 100% | 870 69.0 IPS | Object Detection (HP) | 100% | 194 15.4 IPS | Object Detection (HP) | 100% | 1128 89.4 IPS |
| Object Detection (Q) | 85% | 615 49.5 IPS | Object Detection (Q) | 86% | 3289 264.3 IPS | Object Detection (Q) | 88% | 2552 204.6 IPS |
| Face Detection (SP) | 100% | 1861 22.1 IPS | Face Detection (SP) | 100% | 2262 26.9 IPS | Face Detection (SP) | 100% | 3316 39.4 IPS |
| Face Detection (HP) | 100% | 1342 15.9 IPS | Face Detection (HP) | 100% | 279 3.32 IPS | Face Detection (HP) | 100% | 2781 33.0 IPS |
| Face Detection (Q) | 97% | 1515 18.1 IPS | Face Detection (Q) | 97% | 8407 100.2 IPS | Face Detection (Q) | 100% | 6399 76.0 IPS |
| Depth Estimation (SP) | 100% | 1663 12.8 IPS | Depth Estimation (SP) | 100% | 3168 24.4 IPS | Depth Estimation (SP) | 100% | 2723 21.0 IPS |
| Depth Estimation (HP) | 99% | 1589 12.2 IPS | Depth Estimation (HP) | 99% | 740 5.70 IPS | Depth Estimation (HP) | 99% | 2770 21.3 IPS |
| Depth Estimation (Q) | 63% | 1106 10.4 IPS | Depth Estimation (Q) | 78% | 7653 61.1 IPS | Depth Estimation (Q) | 89% | 6361 49.5 IPS |
| Style Transfer (SP) | 100% | 2077 2.67 IPS | Style Transfer (SP) | 100% | 5451 7.01 IPS | Style Transfer (SP) | 100% | 6421 8.25 IPS |
| Style Transfer (HP) | 100% | 1990 2.56 IPS | Style Transfer (HP) | 100% | 4078 5.24 IPS | Style Transfer (HP) | 100% | 6515 8.37 IPS |
| Style Transfer (Q) | 98% | 2812 3.63 IPS | Style Transfer (Q) | 98% | 10602 13.7 IPS | Style Transfer (Q) | 98% | 15385 19.8 IPS |
| Image Super-Resolution (SP) | 100% | 899 33.2 IPS | Image Super-Resolution (SP) | 100% | 1337 49.4 IPS | Image Super-Resolution (SP) | 100% | 1295 47.8 IPS |
| Image Super-Resolution (HP) | 100% | 907 33.5 IPS | Image Super-Resolution (HP) | 100% | 977 36.1 IPS | Image Super-Resolution (HP) | 100% | 1306 48.2 IPS |
| Image Super-Resolution (Q) | 97% | 714 26.5 IPS | Image Super-Resolution (Q) | 99% | 2829 104.7 IPS | Image Super-Resolution (Q) | 99% | 3217 119.1 IPS |
| Text Classification (SP) | 100% | 924 1.23 KIPS | Text Classification (SP) | 100% | 1085 1.45 KIPS | Text Classification (SP) | 100% | 1266 1.69 KIPS |
| Text Classification (HP) | 100% | 925 1.23 KIPS | Text Classification (HP) | 100% | 465 621.0 IPS | Text Classification (HP) | 100% | 1184 1.58 KIPS |
| Text Classification (Q) | 92% | 337 452.5 IPS | Text Classification (Q) | 97% | 1319 1.77 KIPS | Text Classification (Q) | 92% | 1764 2.37 KIPS |
| Machine Translation (SP) | 100% | 1362 23.5 IPS | Machine Translation (SP) | 100% | 1471 25.3 IPS | Machine Translation (SP) | 100% | 2158 37.2 IPS |
| Machine Translation (HP) | 100% | 1574 27.1 IPS | Machine Translation (HP) | 100% | 356 6.13 IPS | Machine Translation (HP) | 100% | 2105 36.3 IPS |
| Machine Translation (Q) | 58% | 401 9.41 IPS | Machine Translation (Q) | 65% | 2151 43.2 IPS | Machine Translation (Q) | 100% | 2078 35.8 IPS |
Install
| Code Block |
|---|
# OpenVino wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB echo "deb https://apt.repos.intel.com/openvino/2025 ubuntu24 main" | sudo tee /etc/apt/sources.list.d/intel-openvino-2025.list apt update apt-cache search openvino apt install openvino python3 /usr/share/openvino/samples/python/hello_query_device/hello_query_device.py # NPU driver git clone https://github.com/intel/linux-npu-driver.git cd linux-npu-driver/ apt install -y build-essential git git-lfs cmake python3 git submodule update --init --recursive cmake -B build -S . cmake --build build --parallel $(nproc) cmake --install build rmmod intel_vpu modprobe intel_vpu cmake -B build -S . cmake --install build/ --component fw-npu --prefix / #Geekbench mkdir Geekbench cd Geekbench wget https://cdn.geekbench.com/GeekbenchAI-1.3.0-Linux.tar.gz tar xvf GeekbenchAI-1.3.0-Linux.tar.gz cd GeekbenchAI-1.3.0-Linux/ |
...
| Code Block |
|---|
root@server4:~/linux-npu-driver# modinfo intel_vpu filename: /lib/modules/6.8.0-57-generic/kernel/drivers/accel/ivpu/intel_vpu.ko.zst version: 1.0. license: GPL and additional rights description: Driver for Intel NPU (Neural Processing Unit) author: Intel Corporation firmware: intel/vpu/vpu_40xx_v0.0.bin firmware: intel/vpu/vpu_37xx_v0.0.bin srcversion: 853217D6461C2C5899F4F14 alias: pci:v00008086d0000643Esv*sd*bc*sc*i* alias: pci:v00008086d0000AD1Dsv*sd*bc*sc*i* alias: pci:v00008086d00007D1Dsv*sd*bc*sc*i* depends: retpoline: Y intree: Y name: intel_vpu |
OpenVINO CPU
| Code Block |
|---|
root@server4:~/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --ai-framework 14 Geekbench AI 1.3.0 : https://www.geekbench.com/ai/ Geekbench AI requires an active internet connection and automatically uploads benchmark results to the Geekbench Browser. AI Information Framework TensorFlow LiteOpenVINO Backend CPU Device 13th Gen Intel(R) Core(TM) i7-1355U System Information Operating System Ubuntu 24.04.2 LTS Model Default string Default string Motherboard Default string Default string BIOS American Megatrends International, LLC. 5.27 CPU Information Name Intel Core i7-1355U Topology 1 Processor, 10 Cores, 12 Threads Identifier GenuineIntel Family 6 Model 186 Stepping 3 Base Frequency 5.00 GHz Memory Information Size 94.1 GB Running Image Classification (SP) INFO: InitializedRunning TensorFlowImage Lite runtime. INFO: Applying 1 TensorFlow Lite delegate(s) lazily.Classification (HP) Running Image Classification (Q) Running Image ClassificationSegmentation (HPSP) INFO: Applying 1Running TensorFlowImage LiteSegmentation delegate(sHP) lazily. Running Image ClassificationSegmentation (Q) Running ImagePose SegmentationEstimation (SP) INFO: Applying 1Running TensorFlowPose LiteEstimation delegate(s) lazily.HP) Running Pose Estimation (Q) Running ImageObject SegmentationDetection (HPSP) INFO: Applying 1Running TensorFlowObject LiteDetection delegate(sHP) lazily. Running ImageObject SegmentationDetection (Q) Running Face Detection (SP) Running Face Detection (HP) Running Face Detection (Q) Running Depth Estimation (SP) Running Depth Estimation (HP) Running Depth Estimation (Q) Running Style Transfer (SP) Running Style Transfer (HP) Running Style Transfer (Q) Running Image Super-Resolution (SP) Running Image Super-Resolution (HP) Running Image Super-Resolution (Q) Running Text Classification (SP) Running Text Classification (HP) Running Text Classification (Q) Running Machine Translation (SP) Running Machine Translation (HP) Running Machine Translation (Q) Uploading results to the Geekbench Browser. This could take a minute or two depending on the speed of your internet connection. Upload succeeded. Visit the following link and view your results online: https://browser.geekbench.com/ai/v1/247588 |
OpenVINO GPU
| Code Block |
|---|
root@server4:~/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --ai-framework 4 --ai-backend 2 --ai-device 1 Geekbench AI 1.3.0 : https://www.geekbench.com/ai/ Geekbench AI requires an active internet connection and automatically uploads benchmark results to the Geekbench Browser. AI Information Framework OpenVINO Backend GPU Device Intel(R) Iris(R) Xe Graphics (iGPU) System Information Operating System Ubuntu 24.04.2 LTS Model Default string Default string Motherboard Default string Default string BIOS American Megatrends International, LLC. 5.27 CPU Information Name Intel Core i7-1355U Topology 1 Processor, 10 Cores, 12 Threads Identifier GenuineIntel Family 6 Model 186 Stepping 3 Base Frequency 5.00 GHz Memory Information Size 94.1 GB Running Image Classification (SP) free(): invalid pointer .. |