Geekbench AI Score

5138
Single Precision Score
43734
Half Precision Score
57346
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User sergeymitr
Upload Date March 11 2026 04:56 PM
Views 5

System Information

AI Information
Framework Core ML
Backend Neural Engine
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 4.61 GHz
Cluster 16 Cores
Cluster 212 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2388
444.2 IPS
 
Image Classification (HP)
100% 19582
3.64 KIPS
 
Image Classification (Q)
97% 23078
4.31 KIPS
 
Image Segmentation (SP)
100% 2480
40.2 IPS
 
Image Segmentation (HP)
100% 25938
420.5 IPS
 
Image Segmentation (Q)
99% 35967
583.1 IPS
 
Pose Estimation (SP)
100% 11671
13.6 IPS
 
Pose Estimation (HP)
100% 183097
213.6 IPS
 
Pose Estimation (Q)
95% 336681
394.6 IPS
 
Object Detection (SP)
100% 2868
227.5 IPS
 
Object Detection (HP)
100% 21858
1.73 KIPS
 
Object Detection (Q)
91% 27223
2.18 KIPS
 
Face Detection (SP)
100% 5392
64.1 IPS
 
Face Detection (HP)
100% 49355
586.4 IPS
 
Face Detection (Q)
100% 68937
819.1 IPS
 
Depth Estimation (SP)
100% 9546
73.5 IPS
 
Depth Estimation (HP)
99% 137276
1.06 KIPS
 
Depth Estimation (Q)
85% 193940
1.52 KIPS
 
Style Transfer (SP)
100% 27479
35.3 IPS
 
Style Transfer (HP)
100% 287797
370.0 IPS
 
Style Transfer (Q)
96% 394707
509.3 IPS
 
Image Super-Resolution (SP)
100% 6055
223.6 IPS
 
Image Super-Resolution (HP)
100% 64890
2.40 KIPS
 
Image Super-Resolution (Q)
99% 98709
3.64 KIPS
 
Text Classification (SP)
100% 2993
3.99 KIPS
 
Text Classification (HP)
99% 5360
7.15 KIPS
 
Text Classification (Q)
93% 5287
7.10 KIPS
 
Machine Translation (SP)
100% 2524
43.5 IPS
 
Machine Translation (HP)
100% 18568
319.8 IPS
 
Machine Translation (Q)
98% 18359
317.3 IPS
 

Compare

Set Baseline Geekbench 6 now available