Geekbench AI Score

4143
Single Precision Score
27425
Half Precision Score
30715
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User edsonchan
Upload Date May 10 2025 04:28 AM
Views 5

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 3.67 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1392
258.9 IPS
 
Image Classification (HP)
100% 15096
2.81 KIPS
 
Image Classification (Q)
96% 18095
3.38 KIPS
 
Image Segmentation (SP)
100% 1675
27.2 IPS
 
Image Segmentation (HP)
100% 20111
326.0 IPS
 
Image Segmentation (Q)
99% 24899
403.6 IPS
 
Pose Estimation (SP)
100% 12969
15.1 IPS
 
Pose Estimation (HP)
100% 107134
125.0 IPS
 
Pose Estimation (Q)
95% 106451
124.8 IPS
 
Object Detection (SP)
100% 1672
132.7 IPS
 
Object Detection (HP)
99% 15802
1.26 KIPS
 
Object Detection (Q)
91% 17686
1.41 KIPS
 
Face Detection (SP)
100% 3604
42.8 IPS
 
Face Detection (HP)
100% 35906
426.6 IPS
 
Face Detection (Q)
100% 46870
556.9 IPS
 
Depth Estimation (SP)
100% 6263
48.3 IPS
 
Depth Estimation (HP)
99% 87362
673.1 IPS
 
Depth Estimation (Q)
85% 108593
848.6 IPS
 
Style Transfer (SP)
100% 25077
32.2 IPS
 
Style Transfer (HP)
100% 203399
261.5 IPS
 
Style Transfer (Q)
96% 190889
246.3 IPS
 
Image Super-Resolution (SP)
100% 5069
187.2 IPS
 
Image Super-Resolution (HP)
100% 41221
1.52 KIPS
 
Image Super-Resolution (Q)
99% 49935
1.84 KIPS
 
Text Classification (SP)
100% 2361
3.15 KIPS
 
Text Classification (HP)
100% 4204
5.61 KIPS
 
Text Classification (Q)
93% 4107
5.51 KIPS
 
Machine Translation (SP)
100% 4357
75.1 IPS
 
Machine Translation (HP)
100% 4237
73.0 IPS
 
Machine Translation (Q)
98% 4423
76.4 IPS
 

Compare

Set Baseline Geekbench 6 now available