Geekbench ML Score

10824
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 07 2024 11:56 PM
Views 30

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% 6994
1.31 KIPS
 
Image Classification (F16)
100% 6685
1.25 KIPS
 
Image Classification (I8)
99% 6533
1.22 KIPS
 
Image Segmentation (F32)
100% 3056
51.0 IPS
 
Image Segmentation (F16)
100% 2576
43.0 IPS
 
Image Segmentation (I8)
100% 2486
41.5 IPS
 
Pose Estimation (F32)
100% 83692
101.3 IPS
 
Pose Estimation (F16)
100% 90400
109.5 IPS
 
Pose Estimation (I8)
100% 93446
113.2 IPS
 
Object Detection (F32)
100% 5074
378.8 IPS
 
Object Detection (F16)
100% 3786
282.7 IPS
 
Object Detection (I8)
97% 4986
372.2 IPS
 
Face Detection (F32)
100% 24463
290.9 IPS
 
Face Detection (F16)
97% 12096
143.8 IPS
 
Face Detection (I8)
96% 12023
143.0 IPS
 
Depth Estimation (F32)
100% 35567
275.8 IPS
 
Depth Estimation (F16)
100% 35891
278.3 IPS
 
Depth Estimation (I8)
37% 33677
261.2 IPS
 
Style Transfer (F32)
100% 153456
201.9 IPS
 
Style Transfer (F16)
100% 144403
189.9 IPS
 
Style Transfer (I8)
100% 140886
185.3 IPS
 
Image Super-Resolution (F32)
100% 10500
375.0 IPS
 
Image Super-Resolution (F16)
100% 16058
573.5 IPS
 
Image Super-Resolution (I8)
100% 16043
572.9 IPS
 
Text Classification (F32)
100% 998
1.43 KIPS
 
Text Classification (F16)
100% 2582
3.71 KIPS
 
Text Classification (I8)
96% 2572
3.70 KIPS
 
Machine Translation (F32)
100% 1037
19.1 IPS
 
Machine Translation (F16)
100% 3280
60.4 IPS
 
Machine Translation (I8)
99% 913
16.8 IPS
 

Compare

Set Baseline Geekbench 6 now available