Geekbench ML Score

4492
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 22 2025 01:45 AM
Views 7

System Information

System Information
Operating System iOS 26.0
Model iPhone 15 Pro Max
Model IDiPhone16,2
Motherboard D84AP
CPU Information
Name Apple A17 Pro
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.78 GHz
Cluster 12 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 7.47 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1541
288.4 IPS
 
Image Classification (F16)
100% 2881
539.1 IPS
 
Image Classification (I8)
99% 2942
550.6 IPS
 
Image Segmentation (F32)
100% 972
16.2 IPS
 
Image Segmentation (F16)
100% 1213
20.3 IPS
 
Image Segmentation (I8)
100% 1277
21.3 IPS
 
Pose Estimation (F32)
100% 7514
9.10 IPS
 
Pose Estimation (F16)
100% 16969
20.5 IPS
 
Pose Estimation (I8)
100% 16616
20.1 IPS
 
Object Detection (F32)
100% 1559
116.4 IPS
 
Object Detection (F16)
100% 2709
202.3 IPS
 
Object Detection (I8)
97% 1567
117.0 IPS
 
Face Detection (F32)
100% 2966
35.3 IPS
 
Face Detection (F16)
97% 6321
75.2 IPS
 
Face Detection (I8)
96% 6320
75.1 IPS
 
Depth Estimation (F32)
100% 6702
52.0 IPS
 
Depth Estimation (F16)
100% 12663
98.2 IPS
 
Depth Estimation (I8)
99% 12620
97.9 IPS
 
Style Transfer (F32)
100% 21250
28.0 IPS
 
Style Transfer (F16)
100% 33286
43.8 IPS
 
Style Transfer (I8)
100% 33343
43.9 IPS
 
Image Super-Resolution (F32)
100% 5054
180.5 IPS
 
Image Super-Resolution (F16)
100% 6319
225.7 IPS
 
Image Super-Resolution (I8)
100% 6334
226.2 IPS
 
Text Classification (F32)
100% 2972
4.27 KIPS
 
Text Classification (F16)
100% 5074
7.29 KIPS
 
Text Classification (I8)
96% 5056
7.27 KIPS
 
Machine Translation (F32)
100% 1328
24.4 IPS
 
Machine Translation (F16)
100% 1691
31.1 IPS
 
Machine Translation (I8)
99% 1315
24.2 IPS
 

Compare

Set Baseline Geekbench 6 now available