Geekbench ML Score

7162
Core ML GPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:54 AM
Views 5
Notes MacBook Pro (14-inch, M3 Pro or M3 Max, Nov 2023)/M3 Pro 11Core CPU/14Core GPU

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (14-inch, Nov 2023)
Model IDMac15,6
Motherboard Mac15,6
CPU Information
Name Apple M3 Pro
Topology 1 Processor, 11 Cores
Identifier Apple M3 Pro
Base Frequency 4.05 GHz
Cluster 15 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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5053
945.6 IPS
 
Image Classification (F16)
100% 5320
995.5 IPS
 
Image Classification (I8)
99% 4678
875.4 IPS
 
Image Segmentation (F32)
100% 2165
36.2 IPS
 
Image Segmentation (F16)
100% 2264
37.8 IPS
 
Image Segmentation (I8)
100% 2209
36.9 IPS
 
Pose Estimation (F32)
100% 33354
40.4 IPS
 
Pose Estimation (F16)
100% 35193
42.6 IPS
 
Pose Estimation (I8)
100% 34359
41.6 IPS
 
Object Detection (F32)
100% 4125
308.0 IPS
 
Object Detection (F16)
100% 4328
323.1 IPS
 
Object Detection (I8)
97% 3814
284.7 IPS
 
Face Detection (F32)
100% 14341
170.5 IPS
 
Face Detection (F16)
98% 16645
197.9 IPS
 
Face Detection (I8)
97% 16270
193.5 IPS
 
Depth Estimation (F32)
100% 22492
174.4 IPS
 
Depth Estimation (F16)
100% 24372
189.0 IPS
 
Depth Estimation (I8)
37% 22554
174.9 IPS
 
Style Transfer (F32)
100% 73599
96.8 IPS
 
Style Transfer (F16)
100% 82496
108.5 IPS
 
Style Transfer (I8)
100% 82338
108.3 IPS
 
Image Super-Resolution (F32)
100% 10318
368.5 IPS
 
Image Super-Resolution (F16)
100% 9889
353.2 IPS
 
Image Super-Resolution (I8)
100% 10101
360.7 IPS
 
Text Classification (F32)
100% 560
804.4 IPS
 
Text Classification (F16)
100% 999
1.44 KIPS
 
Text Classification (I8)
96% 680
977.0 IPS
 
Machine Translation (F32)
100% 1114
20.5 IPS
 
Machine Translation (F16)
100% 1119
20.6 IPS
 
Machine Translation (I8)
99% 1022
18.8 IPS
 

Compare

Set Baseline Geekbench 6 now available