Geekbench ML Score

1008
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 17 2025 09:39 AM
Views 3

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.66 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 284
53.1 IPS
 
Image Classification (F16)
100% 290
54.3 IPS
 
Image Classification (I8)
99% 290
54.2 IPS
 
Image Segmentation (F32)
100% 292
4.88 IPS
 
Image Segmentation (F16)
100% 323
5.40 IPS
 
Image Segmentation (I8)
100% 322
5.38 IPS
 
Pose Estimation (F32)
100% 2275
2.75 IPS
 
Pose Estimation (F16)
100% 3118
3.78 IPS
 
Pose Estimation (I8)
100% 3122
3.78 IPS
 
Object Detection (F32)
100% 507
37.9 IPS
 
Object Detection (F16)
100% 552
41.2 IPS
 
Object Detection (I8)
97% 540
40.3 IPS
 
Face Detection (F32)
100% 2511
29.9 IPS
 
Face Detection (F16)
97% 2873
34.2 IPS
 
Face Detection (I8)
96% 2890
34.4 IPS
 
Depth Estimation (F32)
100% 2700
20.9 IPS
 
Depth Estimation (F16)
100% 3308
25.7 IPS
 
Depth Estimation (I8)
99% 3193
24.8 IPS
 
Style Transfer (F32)
24% 6044
7.95 IPS
 
Style Transfer (F16)
30% 8831
11.6 IPS
 
Style Transfer (I8)
30% 8802
11.6 IPS
 
Image Super-Resolution (F32)
100% 1328
47.4 IPS
 
Image Super-Resolution (F16)
100% 1390
49.7 IPS
 
Image Super-Resolution (I8)
100% 1466
52.3 IPS
 
Text Classification (F32)
100% 246
354.3 IPS
 
Text Classification (F16)
100% 324
465.3 IPS
 
Text Classification (I8)
96% 323
464.8 IPS
 
Machine Translation (F32)
100% 298
5.48 IPS
 
Machine Translation (F16)
100% 305
5.62 IPS
 
Machine Translation (I8)
99% 298
5.49 IPS
 

Compare

Set Baseline Geekbench 6 now available