Ubuntu 26.04 Linux beta

With 2x48GB 5600MT/s CL46 DDR5 RAM

frameworkBackendDeviceSingleHalfQuant.Results
TensorFlow LiteCPUIntel Core Ultra 9 285H224322701728https://browser.geekbench.com/ai/v1/458629 
ONNXCPUIntel Core Ultra 9 285H17727877913https://browser.geekbench.com/ai/v1/458630 
OpenVINOCPUIntel Core Ultra 9 285H4074293611023https://browser.geekbench.com/ai/v1/458635 
OpenVINOGPUIntel(R) Arc(TM) Graphics (iGPU)103742638734460https://browser.geekbench.com/ai/v1/458641 


wget https://cdn.geekbench.com/GeekbenchAI-1.5.0-Linux.tar.gz
tar xvf GeekbenchAI-1.7.0-Linux.tar.gz
cd GeekbenchAI-1.7.0-Linux/
./banff


root@server7:~/GeekbenchAI-1.7.0-Linux# ./banff --ai-list
Geekbench AI 1.7.0 : https://www.geekbench.com/ai/

Geekbench AI requires an active internet connection and automatically uploads
benchmark results to the Geekbench Browser.

+-----------------+----+---------+----+----------------------------------+----+
| Framework       | ID | Backend | ID | Device                           | ID |
+-----------------+----+---------+----+----------------------------------+----+
| TensorFlow Lite | 1  | CPU     | 1  | Intel Core Ultra 9 285H          | 0  |
+-----------------+----+---------+----+----------------------------------+----+
| ONNX            | 3  | CPU     | 1  | Intel Core Ultra 9 285H          | 0  |
+-----------------+----+---------+----+----------------------------------+----+
| OpenVINO        | 4  | CPU     | 1  | Intel(R) Core(TM) Ultra 9 285H   | 0  |
+-----------------+----+---------+----+----------------------------------+----+
| OpenVINO        | 4  | GPU     | 2  | Intel(R) Arc(TM) Graphics (iGPU) | 1  |
+-----------------+----+---------+----+----------------------------------+----+


execution

./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


compare to Morefine S800 GeekbenchAI 1.3.0

Windows 11

https://wiki.liutyi.info/display/DEVOPS/GMKTect+EVO-T1+Windows+benchmarks#GMKTectEVOT1Windowsbenchmarks-GeekbenchAi1.7.0 


FrameworkbackendSingle PrecisionHalf Precision

Quantized

ONNXCPU486718558775
ONNXDirectML (GPU)8066121025314
OpenVINOCPU5276549812615
OpenVINOGPU106322605032788
OpenVINONPU5165990815226