View Source

framework	Backend	Device	Single	Half	Quant.	Results
TensorFlow Lite	CPU	Intel(R) N150	601	612	430	https://browser.geekbench.com/ai/v1/247221/claim?key=748782
ONNX	CPU	Intel(R) N150
OpenVINO	CPU	Intel(R) N150

Workload	Accuracy	Score
Image Classification (SP)	100%	406 75.5 IPS
Image Classification (HP)	100%	411 76.5 IPS
Image Classification (Q)	99%	275 51.2 IPS
Image Segmentation (SP)	100%	517 8.38 IPS
Image Segmentation (HP)	100%	515 8.35 IPS
Image Segmentation (Q)	98%	332 5.40 IPS
Pose Estimation (SP)	100%	632 0.74 IPS
Pose Estimation (HP)	100%	649 0.76 IPS
Pose Estimation (Q)	96%	611 0.72 IPS
Object Detection (SP)	100%	369 29.3 IPS
Object Detection (HP)	100%	378 30.0 IPS
Object Detection (Q)	85%	286 23.0 IPS
Face Detection (SP)	100%	771 9.16 IPS
Face Detection (HP)	100%	870 10.3 IPS
Face Detection (Q)	97%	719 8.57 IPS
Depth Estimation (SP)	100%	724 5.58 IPS
Depth Estimation (HP)	99%	747 5.76 IPS
Depth Estimation (Q)	63%	549 5.15 IPS
Style Transfer (SP)	100%	1256 1.61 IPS
Style Transfer (HP)	100%	1264 1.63 IPS
Style Transfer (Q)	98%	1454 1.87 IPS
Image Super-Resolution (SP)	100%	362 13.4 IPS
Image Super-Resolution (HP)	100%	338 12.5 IPS
Image Super-Resolution (Q)	97%	357 13.2 IPS
Text Classification (SP)	100%	612 816.3 IPS
Text Classification (HP)	100%	614 819.4 IPS
Text Classification (Q)	92%	266 356.9 IPS
Machine Translation (SP)	100%	819 14.1 IPS
Machine Translation (HP)	100%	833 14.3 IPS
Machine Translation (Q)	58%	253 5.95 IPS

Install

Check Available frameworks

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

help

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.

example run

root@server5:/storage/apps/Geekbench/GeekbenchAI-1.3.0-Linux# ./banff --ai-framework 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                     TensorFlow Lite
  Backend                       CPU
  Device                        Intel(R) N150

System Information
  Operating System              Ubuntu 24.04.2 LTS
  Model                         GMKtec NucBoxG9
  Motherboard                   GMKtec GMKtec
  BIOS                          American Megatrends International, LLC. 5.27

CPU Information
  Name                          Intel(R) N150
  Topology                      1 Processor, 4 Cores
  Identifier                    GenuineIntel Family 6 Model 190 Stepping 0
  Base Frequency                3.60 GHz

Memory Information
  Size                          11.4 GB

  Running Image Classification (SP)
INFO: Initialized TensorFlow Lite runtime.
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Image Classification (HP)
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Image Classification (Q)
  Running Image Segmentation (SP)
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Image Segmentation (HP)
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Image Segmentation (Q)
  Running Pose Estimation (SP)
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Pose Estimation (HP)
INFO: Applying 1 TensorFlow Lite delegate(s) lazily.
  Running Pose Estimation (Q)
...