Geekbench ML Score

10906
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 09 2024 09:37 AM
Views 4

System Information

System Information
Operating System macOS 14.5 (Build 23F5074a)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,9
Motherboard Mac15,9
CPU Information
Name Apple M3 Max
Topology 1 Processor, 16 Cores
Identifier Apple M3 Max
Base Frequency 4.05 GHz
Cluster 112 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 128.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6987
1.31 KIPS
 
Image Classification (F16)
100% 6423
1.20 KIPS
 
Image Classification (I8)
99% 6734
1.26 KIPS
 
Image Segmentation (F32)
100% 3068
51.2 IPS
 
Image Segmentation (F16)
100% 2598
43.4 IPS
 
Image Segmentation (I8)
100% 2606
43.5 IPS
 
Pose Estimation (F32)
100% 84411
102.2 IPS
 
Pose Estimation (F16)
100% 86384
104.6 IPS
 
Pose Estimation (I8)
100% 93594
113.3 IPS
 
Object Detection (F32)
100% 5323
397.4 IPS
 
Object Detection (F16)
100% 3883
289.9 IPS
 
Object Detection (I8)
97% 5272
393.6 IPS
 
Face Detection (F32)
100% 27785
330.4 IPS
 
Face Detection (F16)
97% 12003
142.7 IPS
 
Face Detection (I8)
96% 12039
143.1 IPS
 
Depth Estimation (F32)
100% 36049
279.6 IPS
 
Depth Estimation (F16)
100% 38008
294.8 IPS
 
Depth Estimation (I8)
37% 34690
269.0 IPS
 
Style Transfer (F32)
100% 153278
201.6 IPS
 
Style Transfer (F16)
100% 139901
184.0 IPS
 
Style Transfer (I8)
100% 141301
185.9 IPS
 
Image Super-Resolution (F32)
100% 10105
360.9 IPS
 
Image Super-Resolution (F16)
100% 15738
562.0 IPS
 
Image Super-Resolution (I8)
100% 16408
586.0 IPS
 
Text Classification (F32)
100% 940
1.35 KIPS
 
Text Classification (F16)
100% 2212
3.18 KIPS
 
Text Classification (I8)
96% 2265
3.25 KIPS
 
Machine Translation (F32)
100% 1106
20.4 IPS
 
Machine Translation (F16)
100% 3710
68.3 IPS
 
Machine Translation (I8)
99% 992
18.2 IPS
 

Compare

Set Baseline Geekbench 6 now available