Geekbench ML Score

10863
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User StevenZZH
Upload Date August 01 2024 08:24 PM
Views 3

System Information

System Information
Operating System macOS 15.0 (Build 24A5298h)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,7
Motherboard Mac15,7
CPU Information
Name Apple M3 Pro
Topology 1 Processor, 12 Cores
Identifier Apple M3 Pro
Base Frequency 4.05 GHz
Cluster 16 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% 5139
961.7 IPS
 
Image Classification (F16)
100% 7622
1.43 KIPS
 
Image Classification (I8)
99% 8858
1.66 KIPS
 
Image Segmentation (F32)
100% 2121
35.4 IPS
 
Image Segmentation (F16)
100% 2111
35.3 IPS
 
Image Segmentation (I8)
100% 2154
36.0 IPS
 
Pose Estimation (F32)
100% 42111
51.0 IPS
 
Pose Estimation (F16)
100% 98238
119.0 IPS
 
Pose Estimation (I8)
100% 96798
117.2 IPS
 
Object Detection (F32)
100% 3180
237.4 IPS
 
Object Detection (F16)
100% 4680
349.4 IPS
 
Object Detection (I8)
97% 3736
278.9 IPS
 
Face Detection (F32)
100% 14131
168.0 IPS
 
Face Detection (F16)
97% 14482
172.2 IPS
 
Face Detection (I8)
96% 14672
174.4 IPS
 
Depth Estimation (F32)
100% 25521
197.9 IPS
 
Depth Estimation (F16)
100% 37579
291.4 IPS
 
Depth Estimation (I8)
37% 40310
312.6 IPS
 
Style Transfer (F32)
100% 86868
114.3 IPS
 
Style Transfer (F16)
100% 138494
182.2 IPS
 
Style Transfer (I8)
100% 139070
182.9 IPS
 
Image Super-Resolution (F32)
100% 11613
414.7 IPS
 
Image Super-Resolution (F16)
100% 21370
763.2 IPS
 
Image Super-Resolution (I8)
100% 20980
749.3 IPS
 
Text Classification (F32)
100% 2527
3.63 KIPS
 
Text Classification (F16)
100% 4316
6.20 KIPS
 
Text Classification (I8)
96% 4318
6.21 KIPS
 
Machine Translation (F32)
100% 1125
20.7 IPS
 
Machine Translation (F16)
100% 2794
51.4 IPS
 
Machine Translation (I8)
99% 1077
19.8 IPS
 

Compare

Set Baseline Geekbench 6 now available