Geekbench ML Score

3492
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 08 2024 06:10 PM
Views 2

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (14-inch, 2023)
Model IDMac14,9
Motherboard Mac14,9
CPU Information
Name Apple M2 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M2 Pro
Base Frequency 3.48 GHz
Cluster 16 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 16.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1463
273.7 IPS
 
Image Classification (F16)
100% 1802
337.2 IPS
 
Image Classification (I8)
99% 1821
340.8 IPS
 
Image Segmentation (F32)
100% 880
14.7 IPS
 
Image Segmentation (F16)
100% 877
14.6 IPS
 
Image Segmentation (I8)
100% 883
14.8 IPS
 
Pose Estimation (F32)
100% 6080
7.36 IPS
 
Pose Estimation (F16)
100% 14273
17.3 IPS
 
Pose Estimation (I8)
100% 14262
17.3 IPS
 
Object Detection (F32)
100% 1470
109.7 IPS
 
Object Detection (F16)
100% 1951
145.7 IPS
 
Object Detection (I8)
97% 1469
109.7 IPS
 
Face Detection (F32)
100% 2959
35.2 IPS
 
Face Detection (F16)
97% 4286
51.0 IPS
 
Face Detection (I8)
97% 4288
51.0 IPS
 
Depth Estimation (F32)
100% 5457
42.3 IPS
 
Depth Estimation (F16)
100% 8626
66.9 IPS
 
Depth Estimation (I8)
99% 8575
66.5 IPS
 
Style Transfer (F32)
100% 16511
21.7 IPS
 
Style Transfer (F16)
100% 25886
34.1 IPS
 
Style Transfer (I8)
100% 25858
34.0 IPS
 
Image Super-Resolution (F32)
100% 3915
139.8 IPS
 
Image Super-Resolution (F16)
100% 5033
179.7 IPS
 
Image Super-Resolution (I8)
100% 4973
177.6 IPS
 
Text Classification (F32)
100% 2140
3.08 KIPS
 
Text Classification (F16)
100% 3441
4.94 KIPS
 
Text Classification (I8)
96% 3379
4.86 KIPS
 
Machine Translation (F32)
100% 1120
20.6 IPS
 
Machine Translation (F16)
100% 1547
28.5 IPS
 
Machine Translation (I8)
99% 1123
20.7 IPS
 

Compare

Set Baseline Geekbench 6 now available