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/
./banff

root@server6:/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

# 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
wget https://github.com/intel/linux-npu-driver/releases/download/v1.17.0/intel-driver-compiler-npu_1.17.0.20250508-14912879441_ubuntu24.04_amd64.deb
wget https://github.com/intel/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-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

#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/
./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

root@server6:/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  

root@server6:/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(R) Core(TM) Ultra 9 185H
 3 ONNX4 OpenVINO   |  2 GPU        |  1 Intel(R) Arc(TM) Graphics (iGPU)

root@server6:/mnt/GeekbenchAI-1.3.0-Linux# CPU python3 /usr/share/openvino/samples/python/hello_query_device/hello_query_device.py

[ INFO ] Available devices:
[ INFO |]  0 Intel Core Ultra 9 185H
 4 OpenVINOCPU :
[ INFO ]   |  1 CPU  SUPPORTED_PROPERTIES:
[ INFO ]    |  0 Intel(R) Core(TM) Ultra 9 185H
 4 OpenVINO   |  2 GPU AVAILABLE_DEVICES:
[ INFO ]       |  1 Intel(R) Arc(TM) Graphics (iGPU)

root@server6:/mnt/GeekbenchAI-1.3.0-Linux#  python3 /usr/share/openvino/samples/python/hello_query_device/hello_query_device.py

 RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1
[ INFO ] Available devices:
[ INFO ] CPU :
[ INFO ]        SUPPORTEDRANGE_FOR_PROPERTIESSTREAMS: 1, 22
[ INFO ]                AVAILABLEEXECUTION_DEVICES: CPU
[ INFO ]                RANGEFULL_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1DEVICE_NAME: Intel(R) Core(TM) Ultra 9 185H
[ INFO ]                RANGE_FOR_STREAMS: 1, 22OPTIMIZATION_CAPABILITIES: FP32, INT8, BIN, EXPORT_IMPORT
[ INFO ]                EXECUTIONDEVICE_DEVICESTYPE: CPUType.INTEGRATED
[ INFO ]                FULL_DEVICE_NAMEARCHITECTURE: Intel(R) Core(TM) Ultra 9 185Hintel64
[ INFO ]                OPTIMIZATIONNUM_CAPABILITIESSTREAMS: FP32, INT8, BIN, EXPORT_IMPORT1
[ INFO ]                DEVICEINFERENCE_NUM_TYPETHREADS: Type.INTEGRATED0
[ INFO ]                DEVICEPERF_ARCHITECTURECOUNT: intel64False
[ INFO ]                NUM_STREAMS: 1INFERENCE_PRECISION_HINT: <Type: 'float32'>
[ INFO ]                INFERENCEPERFORMANCE_NUM_THREADSHINT: 0PerformanceMode.LATENCY
[ INFO ]                PERFEXECUTION_MODE_COUNTHINT: FalseExecutionMode.PERFORMANCE
[ INFO ]                INFERENCEPERFORMANCE_HINT_PRECISIONNUM_HINTREQUESTS: <Type: 'float32'>0
[ INFO ]                PERFORMANCEENABLE_CPU_HINTPINNING: PerformanceMode.LATENCYTrue
[ INFO ]                EXECUTIONENABLE_MODECPU_HINTRESERVATION: ExecutionMode.PERFORMANCEFalse
[ INFO ]                PERFORMANCESCHEDULING_HINTCORE_NUM_REQUESTSTYPE: 0SchedulingCoreType.ANY_CORE
[ INFO ]                ENABLEMODEL_CPUDISTRIBUTION_PINNING: TruePOLICY: set()
[ INFO ]                ENABLE_CPUHYPER_RESERVATIONTHREADING: FalseTrue
[ INFO ]                SCHEDULINGDEVICE_CORE_TYPE: SchedulingCoreType.ANY_COREID:
[ INFO ]                MODELCPU_DISTRIBUTIONDENORMALS_POLICYOPTIMIZATION: set()False
[ INFO ]                ENABLELOG_HYPER_THREADINGLEVEL: TrueLevel.NO
[ INFO ]                DEVICE_ID:CPU_SPARSE_WEIGHTS_DECOMPRESSION_RATE: 1.0
[ INFO ]                CPUDYNAMIC_QUANTIZATION_DENORMALSGROUP_OPTIMIZATIONSIZE: False32
[ INFO ]                LOG_LEVEL: Level.NOKV_CACHE_PRECISION: <Type: 'uint8_t'>
[ INFO ]                CPUKEY_SPARSE_WEIGHTS_DECOMPRESSION_RATE: 1.0CACHE_PRECISION: <Type: 'uint8_t'>
[ INFO ]                DYNAMICVALUE_QUANTIZATION_GROUP_SIZE: 32CACHE_PRECISION: <Type: 'uint8_t'>
[ INFO ]                KVKEY_CACHE_GROUP_PRECISIONSIZE: <Type: 'uint8_t'>0
[ INFO ]                KEYVALUE_CACHE_GROUP_PRECISIONSIZE: <Type: 'uint8_t'>0
[ INFO ]
[ INFO ]   GPU :
[ INFO ]        VALUESUPPORTED_CACHE_PRECISION: <Type: 'uint8_t'>PROPERTIES:
[ INFO ]                KEY_CACHE_GROUP_SIZEAVAILABLE_DEVICES: 0
[ INFO ]                VALUERANGE_FOR_CACHEASYNC_GROUPINFER_SIZEREQUESTS: 01, 2, 1
[ INFO ]
[   INFO ] GPU :
[ INFO ]        SUPPORTEDRANGE_FOR_PROPERTIESSTREAMS: 1, 2
[ INFO ]                AVAILABLEOPTIMAL_BATCH_DEVICESSIZE: 01
[ INFO ]                RANGE_FOR_ASYNC_INFER_REQUESTS MAX_BATCH_SIZE: 1, 2, 1
[ INFO ]                RANGE_FOR_STREAMS: 1, 2DEVICE_ARCHITECTURE: GPU: vendor=0x8086 arch=v12.71.4
[ INFO ]                OPTIMALFULL_BATCHDEVICE_SIZE: 1NAME: Intel(R) Arc(TM) Graphics (iGPU)
[ INFO ]                MAXDEVICE_BATCH_SIZEUUID: 18680557d080000000002000000000000
[ INFO ]                DEVICE_ARCHITECTURE: GPU: vendor=0x8086 arch=v12.71.4LUID: 409a0000499a0000
[ INFO ]                FULL_DEVICE_NAME: Intel(R) Arc(TM) Graphics (iGPU)TYPE: Type.INTEGRATED
[ INFO ]                DEVICE_GOPS: {<Type: 'float16'>: 9625.599609375, <Type: 'float32'>: 4812.7998046875, <Type: 'int8_t'>: 19251.19921875, <Type:  DEVICE_UUID: 8680557d080000000002000000000000'uint8_t'>: 19251.19921875}
[ INFO ]                DEVICEOPTIMIZATION_LUIDCAPABILITIES: 409a0000499a0000FP32, BIN, FP16, INT8, EXPORT_IMPORT
[ INFO ]                GPU_DEVICE_TYPETOTAL_MEM_SIZE: Type.INTEGRATED62438608896
[ INFO ]                DEVICE_GOPS: {<Type: 'float16'>: 9625.599609375, <Type: 'float32'>: 4812.7998046875, <Type: 'int8_t'>: 19251.19921875, <Type: 'uint8_t'>: 19251.19921875}        GPU_UARCH_VERSION: 12.71.4
[ INFO ]                OPTIMIZATION_CAPABILITIES: FP32, BIN, FP16, INT8, EXPORT_IMPORTGPU_EXECUTION_UNITS_COUNT: 128
[ INFO ]                GPU_DEVICE_TOTAL_MEM_SIZEMEMORY_STATISTICS: 62438608896{}
[ INFO ]                GPUPERF_UARCH_VERSIONCOUNT: 12.71.4False
[ INFO ]                GPU_EXECUTION_UNITS_COUNTMODEL_PRIORITY: 128Priority.MEDIUM
[ INFO ]                GPU_HOST_MEMORYTASK_STATISTICSPRIORITY: {}Priority.MEDIUM
[ INFO ]                PERFGPU_QUEUE_COUNTPRIORITY: FalsePriority.MEDIUM
[ INFO ]                MODELGPU_QUEUE_PRIORITYTHROTTLE: Priority.MEDIUM
[ INFO ]                GPU_HOSTENABLE_TASKSDPA_PRIORITYOPTIMIZATION: Priority.MEDIUMTrue
[ INFO ]                GPU_QUEUEENABLE_LOOP_PRIORITYUNROLLING: Priority.MEDIUMTrue
[ INFO ]                GPU_QUEUEDISABLE_WINOGRAD_THROTTLECONVOLUTION: Priority.MEDIUMFalse
[ INFO ]                GPU_ENABLE_SDPA_OPTIMIZATION: TrueCACHE_DIR:
[ INFO ]                GPU_ENABLE_LOOP_UNROLLING: TrueCACHE_MODE: CacheMode.OPTIMIZE_SPEED
[ INFO ]                GPU_DISABLE_WINOGRAD_CONVOLUTIONPERFORMANCE_HINT: FalsePerformanceMode.LATENCY
[ INFO ]                CACHEEXECUTION_MODE_DIRHINT: ExecutionMode.PERFORMANCE
[ INFO ]                CACHECOMPILATION_NUM_MODETHREADS: CacheMode.OPTIMIZE_SPEED22
[ INFO ]                PERFORMANCENUM_HINTSTREAMS: PerformanceMode.LATENCY1
[ INFO ]                EXECUTIONPERFORMANCE_HINT_MODENUM_HINTREQUESTS: ExecutionMode.PERFORMANCE0
[ INFO ]                COMPILATIONINFERENCE_NUM_THREADSPRECISION_HINT: <Type: 22'float16'>
[ INFO ]                NUMENABLE_CPU_STREAMSPINNING: 1False
[ INFO ]                PERFORMANCEENABLE_HINTCPU_NUM_REQUESTSRESERVATION: 0False
[ INFO ]                INFERENCEDEVICE_PRECISION_HINTID: <Type: 'float16'>0
[ INFO ]                ENABLEDYNAMIC_QUANTIZATION_CPUGROUP_PINNINGSIZE: False0
[ INFO ]                ENABLEACTIVATIONS_CPUSCALE_RESERVATIONFACTOR: False-1.0
[ INFO ]                DEVICEWEIGHTS_IDPATH: 0
[ INFO ]                DYNAMICCACHE_QUANTIZATIONENCRYPTION_GROUP_SIZECALLBACKS: UNSUPPORTED 0TYPE
[ INFO ]                ACTIVATIONSKV_SCALE_FACTOR: -1.0CACHE_PRECISION: <Type: 'dynamic'>
[ INFO ]                WEIGHTSMODEL_PATHPTR: UNSUPPORTED TYPE
[ INFO ]
[ INFO ] NPU :
[ INFO ]          CACHE_ENCRYPTION_CALLBACKS: UNSUPPORTED TYPESUPPORTED_PROPERTIES:
[ INFO ]                KVAVAILABLE_CACHE_PRECISIONDEVICES: <Type: 'dynamic'>3720
[ INFO ]                MODELCACHE_PTRDIR: UNSUPPORTED TYPE
[ INFO ]
[   INFO ] NPU :
[ INFO ]        SUPPORTEDCOMPILATION_NUM_PROPERTIESTHREADS: 22
[ INFO ]                AVAILABLEDEVICE_DEVICESARCHITECTURE: 3720
[ INFO ]                CACHEDEVICE_DIRGOPS:
[ INFO ]                COMPILATION_NUM_THREADS: 22{<Type: 'bfloat16'>: 0.0, <Type: 'float16'>: 4300.7998046875, <Type: 'float32'>: 0.0, <Type: 'int8_t'>: 8601.599609375, <Type: 'uint8_t'>: 8601.599609375}
[ INFO ]                DEVICE_ARCHITECTUREID: 3720
[ INFO ]                DEVICE_PCI_GOPSINFO: {<Typedomain: 'bfloat16'>0 bus: 0.0, <Typedevice: 'float16'>: 4300.7998046875, <Type: 'float32'>: 0.0, <Type: 'int8_t'>: 8601.599609375, <Type: 'uint8_t'>: 8601.599609375}0xb function: 0}
[ INFO ]                DEVICE_TYPE: Type.INTEGRATED
[ INFO ]                DEVICE_IDUUID: 80d1d11eb73811eab3de0242ac130004
[ INFO ]                DEVICEENABLE_PCICPU_INFOPINNING: {domain: 0 bus: 0 device: 0xb function: 0}False
[ INFO ]                DEVICEEXECUTION_TYPEDEVICES: Type.INTEGRATEDNPU
[ INFO ]                DEVICEEXECUTION_MODE_UUIDHINT: 80d1d11eb73811eab3de0242ac130004ExecutionMode.PERFORMANCE
[ INFO ]                ENABLEFULL_CPUDEVICE_PINNING: FalseNAME: Intel(R) AI Boost
[ INFO ]                EXECUTION_DEVICES: NPUINFERENCE_PRECISION_HINT: <Type: 'float16'>
[ INFO ]                EXECUTIONLOG_MODE_HINTLEVEL: ExecutionModeLevel.PERFORMANCEERR
[ INFO ]                FULLMODEL_DEVICE_NAME: Intel(R) AI BoostPRIORITY: Priority.MEDIUM
[ INFO ]                INFERENCENPU_BYPASS_PRECISIONUMD_HINTCACHING: <Type: 'float16'>False
[ INFO ]                LOG_LEVEL: Level.ERRNPU_COMPILATION_MODE_PARAMS:
[ INFO ]                MODEL_PRIORITYNPU_COMPILER_DYNAMIC_QUANTIZATION: Priority.MEDIUMFalse
[ INFO ]                NPU_BYPASSCOMPILER_UMD_CACHINGVERSION: False458772
[ INFO ]                NPU_COMPILATIONDEFER_MODEWEIGHTS_PARAMSLOAD: False
[ INFO ]                NPU_COMPILERDEVICE_ALLOC_DYNAMICMEM_QUANTIZATIONSIZE: False0
[ INFO ]                NPU_DEVICE_TOTAL_COMPILERMEM_VERSIONSIZE: 45877266926030848
[ INFO ]                NPU_DEFERDRIVER_WEIGHTS_LOADVERSION: False1746727061
[ INFO ]                NPU_DEVICE_ALLOC_MEM_SIZEMAX_TILES: 02
[ INFO ]                NPU_DEVICE_TOTAL_MEM_SIZEQDQ_OPTIMIZATION: 66926030848False
[ INFO ]                NPU_DRIVER_VERSIONTILES: 1746727061-1
[ INFO ]                NPU_MAX_TILESTURBO: 2False
[ INFO ]                NPUNUM_QDQ_OPTIMIZATIONSTREAMS: False1
[ INFO ]                NPU_TILESOPTIMAL_NUMBER_OF_INFER_REQUESTS: -1
[ INFO ]                NPUOPTIMIZATION_TURBOCAPABILITIES: FalseFP16, INT8, EXPORT_IMPORT
[ INFO ]                NUMPERFORMANCE_STREAMSHINT: 1PerformanceMode.LATENCY
[ INFO ]                OPTIMALPERFORMANCE_NUMBERHINT_OF_INFERNUM_REQUESTS: 1
[ INFO ]                OPTIMIZATIONPERF_CAPABILITIESCOUNT: FP16, INT8, EXPORT_IMPORTFalse
[ INFO ]                PERFORMANCE_HINT: PerformanceMode.LATENCYRANGE_FOR_ASYNC_INFER_REQUESTS: 1, 10, 1
[ INFO ]                PERFORMANCERANGE_HINTFOR_NUM_REQUESTSSTREAMS: 1, 4
[ INFO ]                PERFWEIGHTS_COUNTPATH: False
[ INFO ]                RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 10, 1
[ INFO ]                RANGE_FOR_STREAMS: 1, 4
[ INFO ]                WEIGHTS_PATH:
[ INFO ]                WORKLOAD_TYPE: WorkloadType.DEFAULT

WORKLOAD_TYPE: WorkloadType.DEFAULT