Table of Contents

Ubuntu 24.04 Linux

With 2x32GB 4800 MT/s CL38 DDR5 RAM

framework	Backend	Device	Single	Half	Quant.	Results
TensorFlow Lite	CPU	Intel Core Ultra 9 185H	1971	2037	1382	https://browser.geekbench.com/ai/v1/259291
ONNX	CPU	Intel Core Ultra 9 185H	2138	643	5634	https://browser.geekbench.com/ai/v1/259319
OpenVINO	CPU	Intel Core Ultra 9 185H	4507	4541	10765	https://browser.geekbench.com/ai/v1/259321
OpenVINO	GPU	Intel(R) Arc(TM) Graphics (iGPU)	4958	8259	11080	https://browser.geekbench.com/ai/v1/259327

Table of Contents

With 2x64GB 5600 MT/s CL46 DDR5 RAM

governor: performance, PL1=70W, PL2=80W

framework	Backend	Device	Single	Half	Quant.	Results
TensorFlow Lite	CPU	Intel Core Ultra 9 185H	2174	2165	1413	https://browser.geekbench.com/ai/v1/259993
ONNX	CPU	Intel Core Ultra 9 185H	2304	716	5762	https://browser.geekbench.com/ai/v1/260000
OpenVINO	CPU	Intel Core Ultra 9 185H	4631	4682	11063	https://browser.geekbench.com/ai/v1/260002
OpenVINO	GPU	Intel(R) Arc(TM) Graphics (iGPU)	6196	9348	13454	https://browser.geekbench.com/ai/v1/260003

3013Q99%109974073 Q99%17460646Text Classification (SP1229.64 KIPSText Classification (SP1105148 KIPSText Classification (SP2778371 KIPS333
444.7 HP2783371 HP71%1545224 Q92%3905243 IPSQ97%108345 Q92%48166Q92%1499201 KIPSMachine Translation (SP1771305 IPSMachine Translation (SP100%1320227 IPSMachine Translation (SP100%4745817 Machine Translation SP100%1463252 IPS2135
36.8 IPSHP530914 HP4772822 HP96%2510434 Q58%52012Q65%3117626 Q4756819 Q

Workload (TF Lite)	Accuracy	Score	Workload (ONNX)	Accuracy	Score	Workload (OpenVINO-CPU)	Accuracy	Score	Workload (OpenVINO-GPU)	Accuracy	Score
Image Classification (SP)	100%	1510 280.9 IPS	Image Classification (SP)	100%	1106 205.7 IPS	Image Classification (SP)	100%	2587 481.0 IPS	Image Classification (SP)	100%	2587 481.0 IPS
Image Classification (HP)	100%	1428 265.6 IPS	Image Classification (HP)	100%	133 24.6 IPS	Image Classification (HP)	100%	2716 505.1 IPS	Image Classification (HP)	100%	4288 797.5 IPS
Image Classification (Q)	99%	993 185.1 IPS	Image Classification (Q)	97%	4177 779.5 IPS	Image Classification (Q)	100%	6637 1.23 KIPS	Image Classification (Q)	100%	5112 950.6 IPS
Image Segmentation (SP)	100%	2253 36.5 IPS	Image Segmentation (SP)	100%	1141 18.5 IPS	Image Segmentation (SP)	100%	3453 56.0 IPS	Image Segmentation (SP)	100%	3131 50.7 IPS
Image Segmentation (HP)	100%	2243 36.4 IPS	Image Segmentation (HP)	100%	209 3.38 IPS	Image Segmentation (HP)	100%	3468 56.2 IPS	Image Segmentation (HP)	100%	6965 112.9 IPS
Image Segmentation (Q)	98%	1035 16.8 IPS	Image Segmentation (Q)	99%	2658 43.2 IPS	Image Segmentation (Q)	99%	6945 112.6 IPS	Image Segmentation (Q)	99%	9262 150.6 IPS
Pose Estimation (SP)	100%	2357 2.75 IPS	Pose Estimation (SP)	100%	3668 4.28 IPS	Pose Estimation (SP)	100%	5030 5.87 IPS	Pose Estimation (SP)	100%	22411 26.1 IPS
Pose Estimation (HP)	100%	2309 2.69 IPS	Pose Estimation (HP)	100%	3007 3.51 IPS	Pose Estimation (HP)	100%	5100 5.95 IPS	Pose Estimation (HP)	99%	20212 23.7 IPS
Pose Estimation (Q)	96%	3224 3.78 IPS	Pose Estimation (Q)	94%	20021 23.5 IPS	Pose Estimation (Q)	96%	18872 22.1 IPS	Pose Estimation (Q)	97%	44712 52.3 IPS
Object Detection (SP)	100%	1654 131.2 IPS	Object Detection (SP)	100%	1544 122.5 IPS	Object Detection (SP)	100%	2648 210.0 IPS	Object Detection (SP)	100%	2429 192.7 IPS
Object Detection (HP)	100%	1648 130.7 IPS	Object Detection (HP)	100%	269 21.3 IPS	Object Detection (HP)	100%	2652 210.4 IPS	Object Detection (HP)	100%	3775 299.4 IPS
Object Detection (Q)	85%	1024 82.4 IPS	Object Detection (Q)	86%	4605 370.1 IPS	Object Detection (Q)	88%	6968 558.5 IPS	Object Detection (Q)	88%	6319 506.4 IPS
Face Detection (SP)	100%	3071 36.5 IPS	Face Detection (SP)	100%	2807 33.4 IPS	Face Detection (SP)	100%	7234 86.0 IPS	Face Detection (SP)	100%	5692 67.6 IPS
Face Detection (HP)	100%	3060 36.4 IPS	Face Detection (HP)	100%	314 3.73 IPS	Face Detection (HP)	100%	7248 86.1 IPS	Face Detection (HP)	100%	11061 131.4 IPS
Face Detection (Q)	97%	2278 27.2 IPS	Face Detection (Q)	97%	12436 148.3 IPS	Face Detection (Q)	100%	14581 173.3 IPS	Face Detection (Q)	100%	16836 200.0 IPS
Depth Estimation (SP)	100%	2317 17.9 IPS	Depth Estimation (SP)	100%	4220 32.5 IPS	Depth Estimation (SP)	100%	6716 51.7 IPS	Depth Estimation (SP)	100%	12001 92.5 IPS
Depth Estimation (HP)	99%	2507 19.3 IPS	Depth Estimation (HP)	99%	1121 8.64 IPS	Depth Estimation (HP)	99%	6752 52.0 IPS	Depth Estimation (HP)	98%	20362 157.4 IPS
Depth Estimation (Q)	63%	1964 18.4 IPS	Depth Estimation (Q)	78%	13848 110.5 IPS	Depth Estimation (Q)	89%	17848 138.8 IPS	Depth Estimation (Q)	89%	22566 175.4 IPS
Style Transfer (SP)	100%	2892 3.72 IPS	Style Transfer (SP)	100%	9110 11.7 IPS	Style Transfer (SP)	100%	15042 19.3 IPS	Style Transfer (SP)	100%	46431 59.7 IPS
Style Transfer (HP)	100%	2928 3.76 IPS	Style Transfer (HP)	100%	7498 9.64 IPS	Style Transfer (HP)	100%	14930 19.2 IPS	Style Transfer (HP)	100%	62424 80.2 IPS
Style Transfer (Q)	98%	5650 7.29 IPS	Style Transfer (Q)	98%	17976 23.2 IPS	Style Transfer (Q)	98%	52607 67.8 IPS	Style Transfer (Q)	98%	115671 149.2 IPS
Image Super-Resolution (SP)	100%	1494 55.2 IPS	Image Super-Resolution (SP)	100%	1774 65.5 IPS	Image Super-Resolution (SP)	100%
Workload (TF Lite)	Accuracy	Score	Workload (ONNX)	Accuracy	Score	Workload (OpenVINO-CPU)	Accuracy	Score	Workload (OpenVINO-GPU)	Accuracy	Score
Image Classification (SP)	100%	1510 280.9 IPS	Image Classification (SP)	100%	1106 205.7 IPS	Image Classification (SP)	100%	2587 481.0 IPS	Image Classification (SP)	100%	2587 481.0 IPS
Image Classification (HP)	100%	1428 265.6 IPS	Image Classification (HP)	100%	133 24.6 IPS	Image Classification (HP)	100%	2716 505.1 IPS	Image Classification (HP)	100%	4288 797.5 IPS
Image Classification (Q)	99%	993 185.1 IPS	Image Classification (Q)	97%	4177 779.5 IPS	Image Classification (Q)	100%	6637 1.23 KIPS	Image Classification (Q)	100%	5112 950.6 IPS
Image Segmentation (SP)	100%	2253 36.5 IPS	Image Segmentation (SP)	100%	1141 18.5 IPS	Image Segmentation (SP)	100%	3453 56.0 IPS	Image Segmentation (SP)	100%	3131 50.7 IPS
Image Segmentation (HP)	100%	2243 36.4 IPS	Image Segmentation (HP)	100%	209 3.38 IPS	Image Segmentation (HP)	100%	3468 56.2 IPS	Image Segmentation (HP)	100%	6965 112.9 IPS
Image Segmentation (Q)	98%	1035 16.8 IPS	Image Segmentation (Q)	99%	2658 43.2 IPS	Image Segmentation (Q)	99%	6945 112.6 IPS	Image Segmentation (Q)	99%	9262 150.6 IPS
Pose Estimation (SP)	100%	2357 2.75 IPS	Pose Estimation (SP)	100%	3668 4.28 IPS	Pose Estimation (SP)	100%	5030 5.87 IPS	Pose Estimation (SP)	100%	22411 26.1 IPS
Pose Estimation (HP)	100%	2309 2.69 IPS	Pose Estimation (HP)	100%	3007 3.51 IPS	Pose Estimation (HP)	100%	5100 5.95 IPS	Pose Estimation (HP)	99%	20212 23.7 IPS
Pose Estimation (Q)	96%	3224 3.78 IPS	Pose Estimation (Q)	94%	20021 23.5 IPS	Pose Estimation (Q)	96%	18872 22.1 IPS	Pose Estimation (Q)	97%	44712 52.3 IPS
Object Detection (SP)	100%	1654 131.2 IPS	Object Detection (SP)	100%	1544 122.5 IPS	Object Detection (SP)	100%	2648 210.0 IPS	Object Detection (SP)	100%	2429 192.7 IPS
Object Detection (HP)	100%	1648 130.7 IPS	Object Detection (HP)	100%	269 21.3 IPS	Object Detection (HP)	100%	2652 210.4 IPS	Object Detection (HP)	100%	3775 299.4 IPS
Object Detection (Q)	85%	1024 82.4 IPS	Object Detection (Q)	86%	4605 370.1 IPS	Object Detection (Q)	88%	6968 558.5 IPS	Object Detection (Q)	88%	6319 506.4 IPS
Face Detection (SP)	100%	3071 36.5 IPS	Face Detection (SP)	100%	2807 33.4 IPS	Face Detection (SP)	100%	7234 86.0 IPS	Face Detection (SP)	100%	5692 67.6 IPS
Face Detection (HP)	100%	3060 36.4 IPS	Face Detection (HP)	100%	314 3.73 IPS	Face Detection (HP)	100%	7248 86.1 IPS	Face Detection (HP)	100%	11061 131.4 IPS
Face Detection (Q)	97%	2278 27.2 IPS	Face Detection (Q)	97%	12436 148.3 IPS	Face Detection (Q)	100%	14581 173.3 IPS	Face Detection (Q)	100%	16836 200.0 IPS
Depth Estimation (SP)	100%	2317 17.9 IPS	Depth Estimation (SP)	100%	4220 32.5 IPS	Depth Estimation (SP)	100%	6716 51.7 IPS	Depth Estimation (SP)	100%	12001 92.5 IPS
Depth Estimation (HP)	99%	2507 19.3 IPS	Depth Estimation (HP)	99%	1121 8.64 IPS	Depth Estimation (HP)	99%	6752 52.0 IPS	Depth Estimation (HP)	98%	20362 157.4 IPS
Depth Estimation (Q)	63%	1964 18.4 IPS	Depth Estimation (Q)	78%	13848 110.5 IPS	Depth Estimation (Q)	89%	17848 138.8 IPS	Depth Estimation (Q)	89%	22566 175.4 IPS
Style Transfer (SP)	100%	2892 3.72 IPS	Style Transfer (SP)	100%	9110 11.7 IPS	Style Transfer (SP)	100%	15042 19.3 IPS	Style Transfer (SP)	100%	46431 59.7 IPS
Style Transfer (HP)	100%	2928 3.76 IPS	Style Transfer (HP)	100%	7498 9.64 IPS	Style Transfer (HP)	100%	14930 19.2 IPS	Style Transfer (HP)	100%	62424 80.2 IPS
Style Transfer (Q)	98%	5650 7.29 IPS	Style Transfer (Q)	98%	17976 23.2 IPS	Style Transfer (Q)	98%	52607 67.8 IPS	Style Transfer (Q)	98%	115671 149.2 IPS
Image Super-Resolution (SP)	100%	1494 55.2 IPS	Image Super-Resolution (SP)	100%	1774 65.5 IPS	Image Super-Resolution (SP)	100%	3022 111.6 IPS	Image Super-Resolution (SP)	100%	4275 157.9 IPS
Image Super-Resolution (HP)	100%	1911 70.6 IPS	Image Super-Resolution (HP)	100%	1166 43.1 IPS	Image Super-Resolution (HP)	100%	3020 111.5 IPS	Image Super-Resolution (HP)	100%	11896 439.2 IPS
Image Super-Resolution (Q)	97%	1463 54.2 IPS	Image Super-Resolution (Q)	99%	3022	111.6 IPS	Image Super-Resolution (	SP)	100%	4275	157.	9 IPS
Image Super-Resolution (	HP)	100%	1911	70.6 IPS	Image Super-Resolution (HP)	100%	1166 43.1	IPS	Image Super-Resolution (HP	)	100%	3020	111.	5 IPS	Image Super-Resolution (HP	)	100%	11896	439.2 IPS
Image Super-Resolution (Q)	97%	1463 54.2 IPS	Image Super-Resolution (Q)	99%	3013 111.6 IPS	Image Super-Resolution (Q)	99%	10997 407.3 IPS	Image Super-Resolution (Q)	99%	17460 646.6	Text Classification (SP)	71%	1028 1.49 KIPS	Text Classification (HP)	100%	1105 1.47 KIPS	Text Classification (HP)	100%	IPS
Text Classification (	SP)	100%	1229	1.	64 KIPS	Text Classification (	SP)	100%	1105	1.	48 KIPS	Text Classification (	SP)	100%	2778	3.	71 KIPS	Text Classification (	SP)	71%	1028 1.	49 KIPS
Text Classification (	HP)	100%	1105	1.47 KIPS	Text Classification (	HP)	100%	333	444.	7 IPS	Text Classification (HP)	100%	2783	3.	71 KIPS	Text Classification (HP	)	71%	1545	2.	24 KIPS
Text Classification (Q)	92%	390	524.	3 IPS	Text Classification (	Q)	97%	1083	1.	Machine Translation (HP)	100%	45 KIPS	Text Classification (Q)	92%	4816 6.47 KIPS	Text Classification (Q)	92%	1499 2.01 KIPS
Machine Translation (	SP)	100%	1771	30.	5 IPS	Machine Translation (	SP)	100%	1320	22.	7 IPS	Machine Translation (	SP)	100%	4745	81.	7 IPS	Machine Translation (	SP)	100%	1463	25.2 IPS
Machine Translation (	HP)	100%	2135	36.	8 IPS	Machine Translation (	HP)	100%	530	9.	14 IPS	Machine Translation (	HP)	100%	4772 82.2 IPS	Machine Translation (HP)	96%	2510 43.4 IPS
Machine Translation (Q)	58%	520 12.2 IPS	Machine Translation (Q)	65%	3117 62.6 IPS	Machine Translation (Q)	100%	4756 81.9 IPS	Machine Translation (Q)	100%	1814 1814 31.3 IPS

before some drivers added

Code Block
root@server6wget 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/ ./banff

before some drivers added

Code Block

root@server6:/mnt/mnt/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 Core Ultra 9 185H
 3 ONNX       |  1 CPU        |  0 Intel Core Ultra 9 185H
 4 OpenVINO   |  1 CPU        |  0 Intel(R) Core(TM) Ultra 9 185H

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 1 CPU        |  0 Intel(R) Core(TM) Ultra 9 185H

Install

Code Block

# OpenVinotee /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
wget https://apt.repos.intelgithub.com/intel/linux-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
echo "debnpu-driver/releases/download/v1.17.0/intel-driver-compiler-npu_1.17.0.20250508-14912879441_ubuntu24.04_amd64.deb
wget https://aptgithub.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 driverintel/linux-npu-driver/releases/download/v1.17.0/intel-fw-npu_1.17.0.20250508-14912879441_ubuntu24.04_amd64.deb
wget https://github.com/intel/linux-npu-driver/releases/download/v1.17.0/intel-driverlevel-compilerzero-npu_1.17.0.20250508-14912879441_ubuntu24.04_amd64.deb
dpkg --purge --force-remove-reinstreq intel-driver-compiler-npu intel-fw-npu intel-level-zero-npu
apt update
apt install libtbb12
dpkg -i *.deb
wget https://github.com/intel/linuxoneapi-npusrc/level-driverzero/releases/download/v1.1721.09/intellevel-fw-npuzero_1.1721.0.20250508-14912879441_ubuntu24.9+u24.04_amd64.deb
dpkg -i level-zero*.deb

Code Block

#Geekbench
mkdir Geekbench
cd Geekbench
wget https://githubcdn.geekbench.com/intel/linux-npu-driver/releases/download/v1.17.0/intel-level-zero-npu_1.17.0.20250508-14912879441_ubuntu24.04_amd64.deb
dpkg --purge --force-remove-reinstreq intel-driver-compiler-npu intel-fw-npu intel-level-zero-npu
apt update
apt install libtbb12
dpkg -i *.deb
wget https://github.com/oneapi-src/level-zero/releases/download/v1.21.9/level-zero_1.21.9+u24.04_amd64.deb
dpkg -i level-zero*.deb

Code Block

#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/GeekbenchAI-1.3.0-Linux.tar.gz
tar xvf GeekbenchAI-1.3.0-Linux.tar.gz
cd GeekbenchAI-1.3.0-Linux/
./banff --ai-list
./banff --ai-framework 1 --ai-backend 1 --ai-device 0
./banff --ai-framework 3 --ai-backend 1 --ai-device 0
./banff --ai-framework 4 --ai-backend 1 --ai-device 0
./banff --ai-framework 4 --ai-backend 2 --ai-device 1

Check Available frameworks

...

BIOS: Turbo Performance

Windows: Balanced

Framework	Backend	Single	Half	Quantized	URL
OpenVino	GPU	8496	13371	20718	https://browser.geekbench.com/ai/v1/256798
OpenVINO	CPU	2896	3003	6822	https://browser.geekbench.com/ai/v1/256805
ONNX	DirectML	5049	8199	3647	https://browser.geekbench.com/ai/v1/256809
ONNX	CPU	3719	1508	6668	https://browser.geekbench.com/ai/v1/256810

Page tree

Versions Compared

Old Version 6

New Version Current

Key

Ubuntu 24.04 Linux

With 2x32GB 4800 MT/s CL38 DDR5 RAM

With 2x64GB 5600 MT/s CL46 DDR5 RAM

Page tree

Page History

Versions Compared

Old Version 6

New Version Current

Key

Ubuntu 24.04 Linux

With 2x32GB 4800 MT/s CL38 DDR5 RAM

With 2x64GB 5600 MT/s CL46 DDR5 RAM