Geekbench AI Score

27422
Single Precision Score
43953
Half Precision Score
40831
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User Betancd
Upload Date March 17 2026 03:08 PM
Views 12

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M5 Max
System Information
Operating System macOS 26.3.1 (Build 25D2128)
Model Mac17,6
Model IDMac17,6
Motherboard Mac17,6
CPU Information
Name Apple M5 Max
Topology 1 Processor, 18 Cores
Identifier Apple M5 Max
Base Frequency 4.31 GHz
Cluster 16 Cores
Cluster 212 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 10708
1.99 KIPS
 
Image Classification (HP)
100% 13489
2.51 KIPS
 
Image Classification (Q)
97% 11808
2.20 KIPS
 
Image Segmentation (SP)
100% 27821
451.0 IPS
 
Image Segmentation (HP)
100% 41958
680.2 IPS
 
Image Segmentation (Q)
99% 38755
628.2 IPS
 
Pose Estimation (SP)
100% 130475
152.2 IPS
 
Pose Estimation (HP)
100% 333965
389.7 IPS
 
Pose Estimation (Q)
95% 287124
336.5 IPS
 
Object Detection (SP)
100% 10127
803.3 IPS
 
Object Detection (HP)
100% 15518
1.23 KIPS
 
Object Detection (Q)
94% 14825
1.18 KIPS
 
Face Detection (SP)
100% 49696
590.5 IPS
 
Face Detection (HP)
100% 71914
854.5 IPS
 
Face Detection (Q)
100% 64514
766.6 IPS
 
Depth Estimation (SP)
100% 53226
410.1 IPS
 
Depth Estimation (HP)
99% 88229
679.8 IPS
 
Depth Estimation (Q)
86% 84462
659.4 IPS
 
Style Transfer (SP)
100% 265320
341.1 IPS
 
Style Transfer (HP)
100% 547074
703.3 IPS
 
Style Transfer (Q)
96% 607881
784.5 IPS
 
Image Super-Resolution (SP)
100% 34718
1.28 KIPS
 
Image Super-Resolution (HP)
100% 51697
1.91 KIPS
 
Image Super-Resolution (Q)
99% 41666
1.54 KIPS
 
Text Classification (SP)
100% 3019
4.03 KIPS
 
Text Classification (HP)
99% 5672
7.57 KIPS
 
Text Classification (Q)
93% 5584
7.49 KIPS
 
Machine Translation (SP)
100% 8306
143.1 IPS
 
Machine Translation (HP)
100% 9014
155.3 IPS
 
Machine Translation (Q)
98% 8580
148.3 IPS
 

Compare

Set Baseline Geekbench 6 now available