Geekbench AI Score

13538
Single Precision Score
14893
Half Precision Score
13495
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User DJENT
Upload Date March 12 2025 06:26 AM
Views 7

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Pro
System Information
Operating System macOS 15.3.1 (Build 24D70)
Model MacBook Pro (14-inch, 2024)
Model IDMac16,8
Motherboard Mac16,8
CPU Information
Name Apple M4 Pro
Topology 1 Processor, 12 Cores
Identifier Apple M4 Pro
Base Frequency 4.51 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 6859
1.28 KIPS
 
Image Classification (HP)
100% 7260
1.35 KIPS
 
Image Classification (Q)
97% 6218
1.16 KIPS
 
Image Segmentation (SP)
100% 10586
171.6 IPS
 
Image Segmentation (HP)
100% 11069
179.4 IPS
 
Image Segmentation (Q)
99% 11319
183.5 IPS
 
Pose Estimation (SP)
100% 46217
53.9 IPS
 
Pose Estimation (HP)
100% 48337
56.4 IPS
 
Pose Estimation (Q)
95% 45709
53.6 IPS
 
Object Detection (SP)
100% 6691
530.7 IPS
 
Object Detection (HP)
100% 7215
572.3 IPS
 
Object Detection (Q)
91% 5963
476.5 IPS
 
Face Detection (SP)
100% 22751
270.3 IPS
 
Face Detection (HP)
100% 24525
291.4 IPS
 
Face Detection (Q)
100% 18447
219.2 IPS
 
Depth Estimation (SP)
100% 30854
237.7 IPS
 
Depth Estimation (HP)
99% 32871
253.3 IPS
 
Depth Estimation (Q)
85% 27268
213.1 IPS
 
Style Transfer (SP)
100% 104883
134.8 IPS
 
Style Transfer (HP)
100% 112441
144.5 IPS
 
Style Transfer (Q)
96% 107014
138.1 IPS
 
Image Super-Resolution (SP)
100% 16448
607.4 IPS
 
Image Super-Resolution (HP)
100% 17293
638.5 IPS
 
Image Super-Resolution (Q)
99% 13753
507.8 IPS
 
Text Classification (SP)
100% 2931
3.91 KIPS
 
Text Classification (HP)
100% 5265
7.03 KIPS
 
Text Classification (Q)
93% 5182
6.95 KIPS
 
Machine Translation (SP)
100% 2596
44.7 IPS
 
Machine Translation (HP)
100% 2322
40.0 IPS
 
Machine Translation (Q)
98% 2724
47.1 IPS
 

Compare

Set Baseline Geekbench 6 now available