Geekbench ML Score

2085
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date December 22 2023 12:35 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 10 Enterprise LTSC (64-bit)
Model Micro-Star International Co., Ltd. B450 Gaming MAG META 5 (MS-B930)
Motherboard Micro-Star International Co., Ltd. B450M PRO-VDH MAX (MS-7A38)
Power PlanWinterOS: Rev10
CPU Information
Name AMD Ryzen 7 3700X
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 23 Model 113 Stepping 0
Base Frequency 3.60 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache512 KB x 8
L3 Cache16.0 MB x 2
Memory Information
Size 40.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1290
241.4 IPS
 
Image Classification (F16)
100% 1286
240.7 IPS
 
Image Classification (I8)
97% 2010
376.1 IPS
 
Image Segmentation (F32)
100% 782
13.1 IPS
 
Image Segmentation (F16)
100% 757
12.6 IPS
 
Image Segmentation (I8)
97% 1401
23.4 IPS
 
Pose Estimation (F32)
100% 5114
6.19 IPS
 
Pose Estimation (F16)
100% 5031
6.09 IPS
 
Pose Estimation (I8)
100% 5932
7.18 IPS
 
Object Detection (F32)
100% 1092
81.5 IPS
 
Object Detection (F16)
100% 1079
80.6 IPS
 
Object Detection (I8)
60% 1075
80.3 IPS
 
Face Detection (F32)
100% 1391
16.5 IPS
 
Face Detection (F16)
100% 1390
16.5 IPS
 
Face Detection (I8)
87% 2184
26.0 IPS
 
Depth Estimation (F32)
100% 4974
38.6 IPS
 
Depth Estimation (F16)
100% 4968
38.5 IPS
 
Depth Estimation (I8)
74% 5950
46.1 IPS
 
Style Transfer (F32)
100% 11318
14.9 IPS
 
Style Transfer (F16)
100% 11315
14.9 IPS
 
Style Transfer (I8)
85% 8456
11.1 IPS
 
Image Super-Resolution (F32)
100% 2176
77.7 IPS
 
Image Super-Resolution (F16)
100% 2186
78.1 IPS
 
Image Super-Resolution (I8)
97% 1958
69.9 IPS
 
Text Classification (F32)
100% 1119
1.61 KIPS
 
Text Classification (F16)
100% 1132
1.63 KIPS
 
Text Classification (I8)
94% 323
464.9 IPS
 
Machine Translation (F32)
100% 1241
22.8 IPS
 
Machine Translation (F16)
100% 1266
23.3 IPS
 
Machine Translation (I8)
67% 1753
32.3 IPS
 

Compare

Set Baseline Geekbench 6 now available