Geekbench ML Score

7872
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 09 2024 09:56 AM
Views 1

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (16-inch, 2021)
Model IDMacBookPro18,1
Motherboard MacBookPro18,1
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3583
670.4 IPS
 
Image Classification (F16)
100% 6676
1.25 KIPS
 
Image Classification (I8)
99% 7060
1.32 KIPS
 
Image Segmentation (F32)
100% 1289
21.5 IPS
 
Image Segmentation (F16)
100% 3525
58.9 IPS
 
Image Segmentation (I8)
100% 3496
58.4 IPS
 
Pose Estimation (F32)
100% 31616
38.3 IPS
 
Pose Estimation (F16)
100% 61258
74.2 IPS
 
Pose Estimation (I8)
100% 63428
76.8 IPS
 
Object Detection (F32)
100% 2848
212.7 IPS
 
Object Detection (F16)
100% 4498
335.8 IPS
 
Object Detection (I8)
97% 2680
200.1 IPS
 
Face Detection (F32)
100% 11797
140.3 IPS
 
Face Detection (F16)
97% 10636
126.5 IPS
 
Face Detection (I8)
96% 10657
126.7 IPS
 
Depth Estimation (F32)
100% 19139
148.4 IPS
 
Depth Estimation (F16)
100% 37024
287.1 IPS
 
Depth Estimation (I8)
37% 31152
241.6 IPS
 
Style Transfer (F32)
100% 45074
59.3 IPS
 
Style Transfer (F16)
100% 110881
145.9 IPS
 
Style Transfer (I8)
100% 117162
154.1 IPS
 
Image Super-Resolution (F32)
100% 6888
246.0 IPS
 
Image Super-Resolution (F16)
100% 17292
617.6 IPS
 
Image Super-Resolution (I8)
100% 16036
572.7 IPS
 
Text Classification (F32)
100% 458
657.8 IPS
 
Text Classification (F16)
100% 2003
2.88 KIPS
 
Text Classification (I8)
96% 1980
2.85 KIPS
 
Machine Translation (F32)
100% 772
14.2 IPS
 
Machine Translation (F16)
100% 2287
42.1 IPS
 
Machine Translation (I8)
99% 639
11.8 IPS
 

Compare

Set Baseline Geekbench 6 now available