Geekbench ML Score

4540
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User 46fy45
Upload Date January 06 2025 05:00 AM
Views 4

System Information

System Information
Operating System macOS 15.1 (Build 24B83)
Model MacBook Pro (16-inch, 2023)
Model IDMac14,10
Motherboard Mac14,10
CPU Information
Name Apple M2 Pro
Topology 1 Processor, 12 Cores
Identifier Apple M2 Pro
Base Frequency 3.46 GHz
Cluster 18 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% 1371
256.5 IPS
 
Image Classification (F16)
100% 2220
415.3 IPS
 
Image Classification (I8)
99% 2247
420.4 IPS
 
Image Segmentation (F32)
100% 1032
17.2 IPS
 
Image Segmentation (F16)
100% 1340
22.4 IPS
 
Image Segmentation (I8)
100% 1353
22.6 IPS
 
Pose Estimation (F32)
100% 12571
15.2 IPS
 
Pose Estimation (F16)
100% 23791
28.8 IPS
 
Pose Estimation (I8)
100% 24046
29.1 IPS
 
Object Detection (F32)
100% 1555
116.1 IPS
 
Object Detection (F16)
100% 2334
174.2 IPS
 
Object Detection (I8)
97% 1544
115.3 IPS
 
Face Detection (F32)
100% 3343
39.7 IPS
 
Face Detection (F16)
97% 5750
68.4 IPS
 
Face Detection (I8)
97% 5693
67.7 IPS
 
Depth Estimation (F32)
100% 6069
47.1 IPS
 
Depth Estimation (F16)
100% 11982
92.9 IPS
 
Depth Estimation (I8)
99% 12367
95.9 IPS
 
Style Transfer (F32)
100% 24814
32.6 IPS
 
Style Transfer (F16)
100% 38030
50.0 IPS
 
Style Transfer (I8)
100% 39189
51.6 IPS
 
Image Super-Resolution (F32)
100% 5377
192.0 IPS
 
Image Super-Resolution (F16)
100% 7161
255.7 IPS
 
Image Super-Resolution (I8)
100% 7233
258.3 IPS
 
Text Classification (F32)
100% 2092
3.01 KIPS
 
Text Classification (F16)
100% 3490
5.02 KIPS
 
Text Classification (I8)
96% 3643
5.24 KIPS
 
Machine Translation (F32)
100% 1487
27.4 IPS
 
Machine Translation (F16)
100% 1692
31.1 IPS
 
Machine Translation (I8)
99% 1473
27.1 IPS
 

Compare

Set Baseline Geekbench 6 now available