Geekbench ML Score

10092
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:56 AM
Views 7
Notes MacBook Pro (14-inch, M3 Pro or M3 Max, Nov 2023)/M3 Pro 11Core CPU/14Core GPU

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (14-inch, Nov 2023)
Model IDMac15,6
Motherboard Mac15,6
CPU Information
Name Apple M3 Pro
Topology 1 Processor, 11 Cores
Identifier Apple M3 Pro
Base Frequency 4.05 GHz
Cluster 15 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 18.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5036
942.3 IPS
 
Image Classification (F16)
100% 7053
1.32 KIPS
 
Image Classification (I8)
99% 7648
1.43 KIPS
 
Image Segmentation (F32)
100% 2198
36.7 IPS
 
Image Segmentation (F16)
100% 2230
37.3 IPS
 
Image Segmentation (I8)
100% 2242
37.4 IPS
 
Pose Estimation (F32)
100% 33015
40.0 IPS
 
Pose Estimation (F16)
100% 96335
116.7 IPS
 
Pose Estimation (I8)
100% 95288
115.4 IPS
 
Object Detection (F32)
100% 3211
239.7 IPS
 
Object Detection (F16)
100% 4955
369.9 IPS
 
Object Detection (I8)
97% 3828
285.8 IPS
 
Face Detection (F32)
100% 14200
168.8 IPS
 
Face Detection (F16)
97% 12844
152.7 IPS
 
Face Detection (I8)
96% 12837
152.6 IPS
 
Depth Estimation (F32)
100% 22285
172.8 IPS
 
Depth Estimation (F16)
100% 40685
315.5 IPS
 
Depth Estimation (I8)
37% 43846
340.0 IPS
 
Style Transfer (F32)
100% 74417
97.9 IPS
 
Style Transfer (F16)
100% 147589
194.1 IPS
 
Style Transfer (I8)
100% 147435
193.9 IPS
 
Image Super-Resolution (F32)
100% 10356
369.9 IPS
 
Image Super-Resolution (F16)
100% 20466
730.9 IPS
 
Image Super-Resolution (I8)
100% 20482
731.5 IPS
 
Text Classification (F32)
100% 731
1.05 KIPS
 
Text Classification (F16)
100% 3802
5.46 KIPS
 
Text Classification (I8)
96% 3693
5.31 KIPS
 
Machine Translation (F32)
100% 1110
20.4 IPS
 
Machine Translation (F16)
100% 3129
57.6 IPS
 
Machine Translation (I8)
99% 1026
18.9 IPS
 

Compare

Set Baseline Geekbench 6 now available