Geekbench AI Score

4103
Single Precision Score
27218
Half Precision Score
30336
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User danilonc
Upload Date June 27 2025 07:32 PM
Views 3

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 15.5 (Build 24F74)
Model Mac Studio (2023)
Model IDMac14,13
Motherboard Mac14,13
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1392
258.8 IPS
 
Image Classification (HP)
100% 14042
2.61 KIPS
 
Image Classification (Q)
96% 17039
3.18 KIPS
 
Image Segmentation (SP)
100% 1625
26.3 IPS
 
Image Segmentation (HP)
100% 20057
325.1 IPS
 
Image Segmentation (Q)
99% 24780
401.7 IPS
 
Pose Estimation (SP)
100% 12808
14.9 IPS
 
Pose Estimation (HP)
100% 106782
124.6 IPS
 
Pose Estimation (Q)
95% 104768
122.8 IPS
 
Object Detection (SP)
100% 1672
132.6 IPS
 
Object Detection (HP)
99% 15896
1.26 KIPS
 
Object Detection (Q)
91% 17352
1.39 KIPS
 
Face Detection (SP)
100% 3551
42.2 IPS
 
Face Detection (HP)
100% 35556
422.5 IPS
 
Face Detection (Q)
100% 46054
547.2 IPS
 
Depth Estimation (SP)
100% 6056
46.7 IPS
 
Depth Estimation (HP)
99% 87929
677.4 IPS
 
Depth Estimation (Q)
85% 109864
858.5 IPS
 
Style Transfer (SP)
100% 25157
32.3 IPS
 
Style Transfer (HP)
100% 205552
264.2 IPS
 
Style Transfer (Q)
96% 190652
246.0 IPS
 
Image Super-Resolution (SP)
100% 5025
185.6 IPS
 
Image Super-Resolution (HP)
100% 41988
1.55 KIPS
 
Image Super-Resolution (Q)
99% 49859
1.84 KIPS
 
Text Classification (SP)
100% 2357
3.15 KIPS
 
Text Classification (HP)
100% 4157
5.55 KIPS
 
Text Classification (Q)
93% 4133
5.55 KIPS
 
Machine Translation (SP)
100% 4357
75.0 IPS
 
Machine Translation (HP)
100% 4162
71.7 IPS
 
Machine Translation (Q)
98% 4327
74.8 IPS
 

Compare

Set Baseline Geekbench 6 now available