Geekbench ML Score

19978
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 04 2026 06:23 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Default string Default string
Motherboard Default string Default string
Power PlanBalanced
CPU Information
Name AMD Ryzen AI Max+ 395
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 26 Model 112 Stepping 0
Base Frequency 3.00 GHz
Cluster 116 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache1.00 MB x 16
L3 Cache32.0 MB x 2
Memory Information
Size 128.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) 8060S Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 10706
2.00 KIPS
 
Image Classification (F16)
100% 11207
2.10 KIPS
 
Image Classification (I8)
100% 9360
1.75 KIPS
 
Image Segmentation (F32)
100% 16725
279.3 IPS
 
Image Segmentation (F16)
100% 17069
285.1 IPS
 
Image Segmentation (I8)
98% 13660
228.1 IPS
 
Pose Estimation (F32)
100% 121928
147.6 IPS
 
Pose Estimation (F16)
100% 116956
141.6 IPS
 
Pose Estimation (I8)
100% 105980
128.3 IPS
 
Object Detection (F32)
100% 4537
338.7 IPS
 
Object Detection (F16)
100% 4738
353.7 IPS
 
Object Detection (I8)
62% 4722
352.5 IPS
 
Face Detection (F32)
100% 22957
273.0 IPS
 
Face Detection (F16)
100% 24732
294.1 IPS
 
Face Detection (I8)
89% 18494
219.9 IPS
 
Depth Estimation (F32)
100% 46454
360.2 IPS
 
Depth Estimation (F16)
100% 49556
384.3 IPS
 
Depth Estimation (I8)
95% 40377
313.1 IPS
 
Style Transfer (F32)
100% 215926
284.0 IPS
 
Style Transfer (F16)
100% 212813
279.9 IPS
 
Style Transfer (I8)
98% 178165
234.4 IPS
 
Image Super-Resolution (F32)
100% 33361
1.19 KIPS
 
Image Super-Resolution (F16)
100% 35741
1.28 KIPS
 
Image Super-Resolution (I8)
99% 26820
957.8 IPS
 
Text Classification (F32)
100% 4308
6.19 KIPS
 
Text Classification (F16)
100% 4160
5.98 KIPS
 
Text Classification (I8)
98% 2815
4.05 KIPS
 
Machine Translation (F32)
100% 6019
110.8 IPS
 
Machine Translation (F16)
100% 6308
116.1 IPS
 
Machine Translation (I8)
70% 3161
58.2 IPS
 

Compare

Set Baseline Geekbench 6 now available