| framework | Backend | Device | Single | Half | Quant. | Results |
|---|---|---|---|---|---|---|
TensorFlow Lite | CPU | Intel(R) N150 | 601 | 612 | 430 | https://browser.geekbench.com/ai/v1/247221 |
ONNX | CPU | Intel(R) N150 | 755 | 295 | 1449 | https://browser.geekbench.com/ai/v1/247226 |
OpenVINO | CPU | Intel(R) N150 | 928 | 941 | 1902 | https://browser.geekbench.com/ai/v1/247228 |
| Workload (TF Lite) | Accuracy | Score | Workload (ONNX) | Accuracy | Score | Workload (OpenVINO) | Accuracy | Score |
|---|---|---|---|---|---|---|---|---|
| Image Classification (SP) | 100% | 406 75.5 IPS |
| Image Classification (SP) | 100% | 522 97.0 IPS | Image Classification (SP) | 100% | 553 102.8 IPS | |
| Image Classification (HP) | 100% | 411 76.5 |
| IPS | Image Classification (HP) | 100% | 97 18.1 IPS | Image Classification (HP) | 100% | 554 103.0 IPS |
| Image Classification (Q) | 99% | 275 51.2 IPS |
| Image Classification (Q) | 97% | 1131 211.0 IPS | Image Classification (Q) | 100% | 1165 216.7 IPS |
| Image Segmentation (SP) | 100% | 517 8.38 |
| IPS | Image Segmentation (SP) | 100% | 445 7.22 IPS | Image Segmentation (SP) | 100% | 655 10.6 IPS |
| Image Segmentation (HP) | 100% | 515 8.35 |
| IPS | Image Segmentation (HP) | 100% | 146 2.37 IPS | Image Segmentation (HP) | 100% | 667 10.8 IPS |
| Image Segmentation (Q) | 98% | 332 5.40 IPS |
| Image Segmentation (Q) | 99% | 954 15.5 IPS | Image Segmentation (Q) | 99% | 1235 20.0 IPS |
| Pose Estimation (SP) | 100% | 632 0.74 |
| IPS | Pose Estimation (SP) | 100% | 997 1.16 IPS | Pose Estimation (SP) | 100% | 948 1.11 IPS |
| Pose Estimation (HP) | 100% | 649 0.76 IPS | Pose Estimation (HP) | 100% | 753 0.88 IPS |
| Pose Estimation (HP) | 100% | 957 1.12 IPS | |
| Pose Estimation (Q) | 96% | 611 0.72 IPS |
| Pose Estimation (Q) | 94% | 2459 2.88 IPS | Pose Estimation (Q) | 96% | 2538 2.97 IPS |
| Object Detection (SP) | 100% | 369 29.3 |
| IPS | Object Detection (SP) | 100% | 489 38.8 IPS | Object Detection (SP) | 100% | 497 39.5 IPS |
| Object Detection (HP) | 100% | 378 30.0 IPS | Object Detection (HP) | 100% | 122 9.68 IPS |
| Object Detection (HP) | 100% | 525 41.7 IPS | |
| Object Detection (Q) | 85% | 286 23.0 IPS |
| Object Detection (Q) | 86% | 1114 89.5 IPS | Object Detection (Q) | 88% | 1168 93.6 IPS | |
| Face Detection (SP) | 100% | 771 9.16 IPS |
| Face Detection (SP) | 100% | 1086 12.9 IPS | Face Detection (SP) | 100% | 1619 19.2 IPS | |
| Face Detection (HP) | 100% | 870 10.3 IPS |
| Face Detection (HP) | 100% | 207 2.46 IPS | Face Detection (HP) | 100% | 1632 19.4 IPS |
| Face Detection (Q) | 97% | 719 8.57 IPS |
| Face Detection (Q) | 97% | 2934 35.0 IPS | Face Detection (Q) | 100% | 2980 35.4 IPS | |
| Depth Estimation (SP) | 100% | 724 5.58 IPS | Depth Estimation (SP) | 100% | 1312 10.1 IPS |
| Depth Estimation (SP) | 100% | 1241 9.56 IPS | |
| Depth Estimation (HP) | 99% | 747 5.76 IPS |
| Depth Estimation (HP) | 99% | 462 3.56 IPS | Depth Estimation (HP) | 99% | 1236 9.52 IPS |
| Depth Estimation (Q) | 63% | 549 5.15 IPS |
| Depth Estimation (Q) | 78% | 2596 20.7 IPS | Depth Estimation (Q) | 89% | 3103 24.1 IPS |
| Style Transfer (SP) | 100% | 1256 1.61 IPS |
| Style Transfer (SP) | 100% | 2473 3.18 IPS | Style Transfer (SP) | 100% | 2786 3.58 IPS | |
| Style Transfer (HP) | 100% | 1264 1.63 IPS | Style Transfer (HP) | 100% | 1993 2.56 IPS |
| Style Transfer (HP) | 100% | 2854 3.67 IPS | |
| Style Transfer (Q) | 98% | 1454 1.87 IPS |
| Style Transfer (Q) | 98% | 4651 6.00 IPS | Style Transfer (Q) | 98% | 7229 9.32 IPS |
| Image Super-Resolution (SP) | 100% | 362 13.4 IPS |
| Image Super-Resolution (SP) | 100% | 588 21.7 IPS | Image Super-Resolution (SP) | 100% | 599 22.1 IPS | |
| Image Super-Resolution (HP) | 100% | 338 12.5 IPS |
| Image Super-Resolution (HP) | 100% | 430 15.9 IPS | Image Super-Resolution (HP) | 100% | 606 22.4 IPS |
| Image Super-Resolution (Q) | 97% | 357 13.2 IPS |
| Image Super-Resolution (Q) | 99% | 876 32.4 IPS | Image Super-Resolution (Q) | 99% | 1505 55.7 IPS | |
| Text Classification (SP) | 100% | 612 816.3 IPS |
| Text Classification (SP) | 100% | 297 397.0 IPS | Text Classification (SP) | 100% | 704 939.7 IPS | |
| Text Classification (HP) | 100% | 614 819.4 IPS |
| Text Classification (HP) | 100% | 180 240.0 IPS | Text Classification (HP) | 100% | 702 937.4 IPS |
| Text Classification (Q) | 92% | 266 356.9 IPS |
| Text Classification (Q) | 97% | 412 552.4 IPS | Text Classification (Q) | 92% | 1199 1.61 KIPS |
| Machine Translation (SP) | 100% | 819 14.1 IPS |
| Machine Translation (SP) | 100% | 875 15.1 IPS | Machine Translation (SP) | 100% | 1184 20.4 IPS | |
| Machine Translation (HP) | 100% | 833 14.3 IPS |
| Machine Translation (HP) | 100% | 267 4.60 IPS | Machine Translation (HP) | 100% | 1210 20.8 IPS |
| Machine Translation (Q) | 58% | 253 5.95 IPS |
| Machine Translation (Q) | 65% | 1085 21.8 IPS | Machine Translation (Q) | 100% | 1206 20.8 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
#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/ |
Check Available frameworks
Ubuntu 24.04
| Code Block |
|---|
root@server5:/storage/apps/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --ai-list
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.
Framework | Backend | Device
1 TensorFlow Lite | 1 CPU | 0 Intel(R) N150
3 ONNX | 1 CPU | 0 Intel(R) N150
4 OpenVINO | 1 CPU | 0 Intel(R) N150
|
Ubuntu 25.04
| Code Block |
|---|
root@server5:/storage/apps/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --ai-list
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.
Framework | Backend | Device
1 TensorFlow Lite | 1 CPU | 0 Intel(R) N150
3 ONNX | 1 CPU | 0 Intel(R) N150
4 OpenVINO | 1 CPU | 0 Intel(R) N150
4 OpenVINO | 2 GPU | 1 Intel(R) Graphics (iGPU)
|
help
| Code Block |
|---|
root@server5:/storage/apps/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --help Geekbench AI 1.3.0 : https://www.geekbench.com/ai/ Usage: ./banff [ options ] Options: -h, --help print this message AI Benchmark Options: --ai run the AI benchmark --ai-framework [ID] use AI framework ID --ai-backend [ID] use AI backend ID --ai-device [ID] use AI device ID --ai-list list available AI settings If no options are given, the default action is to run the inference benchmark. |
...