Geekbench AI Score

5638
Single Precision Score
36488
Half Precision Score
50941
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

User bluemagic
Upload Date August 12 2025 03:54 PM
Views 8

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4 Max
System Information
Operating System macOS 15.6 (Build 24G84)
Model Mac16,9
Model IDMac16,9
Motherboard Mac16,9
CPU Information
Name Apple M4 Max
Topology 1 Processor, 16 Cores
Identifier Apple M4 Max
Base Frequency 4.51 GHz
Cluster 112 Cores
Cluster 24 Cores
Memory Information
Size 128.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2121
394.5 IPS
 
Image Classification (HP)
100% 16987
3.16 KIPS
 
Image Classification (Q)
97% 23019
4.30 KIPS
 
Image Segmentation (SP)
100% 2373
38.5 IPS
 
Image Segmentation (HP)
100% 22682
367.7 IPS
 
Image Segmentation (Q)
99% 31695
513.8 IPS
 
Pose Estimation (SP)
100% 17958
21.0 IPS
 
Pose Estimation (HP)
100% 122390
142.8 IPS
 
Pose Estimation (Q)
95% 229986
269.6 IPS
 
Object Detection (SP)
100% 2644
209.8 IPS
 
Object Detection (HP)
100% 18976
1.51 KIPS
 
Object Detection (Q)
91% 23444
1.87 KIPS
 
Face Detection (SP)
100% 4999
59.4 IPS
 
Face Detection (HP)
100% 45436
539.9 IPS
 
Face Detection (Q)
100% 63695
756.8 IPS
 
Depth Estimation (SP)
100% 8916
68.7 IPS
 
Depth Estimation (HP)
99% 104669
806.4 IPS
 
Depth Estimation (Q)
85% 180919
1.41 KIPS
 
Style Transfer (SP)
100% 26375
33.9 IPS
 
Style Transfer (HP)
100% 234929
302.0 IPS
 
Style Transfer (Q)
96% 296729
382.9 IPS
 
Image Super-Resolution (SP)
100% 6080
224.5 IPS
 
Image Super-Resolution (HP)
100% 46153
1.70 KIPS
 
Image Super-Resolution (Q)
99% 78070
2.88 KIPS
 
Text Classification (SP)
100% 2972
3.97 KIPS
 
Text Classification (HP)
100% 5516
7.36 KIPS
 
Text Classification (Q)
93% 6815
9.15 KIPS
 
Machine Translation (SP)
100% 6394
110.1 IPS
 
Machine Translation (HP)
100% 16436
283.1 IPS
 
Machine Translation (Q)
98% 16443
284.1 IPS
 

Compare

Set Baseline Geekbench 6 now available