Geekbench AI Score

5373
Single Precision Score
37962
Half Precision Score
51530
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

Upload Date June 22 2025 09:43 AM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4 Pro
System Information
Operating System macOS 15.5 (Build 24F74)
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 24.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2045
380.3 IPS
 
Image Classification (HP)
100% 18171
3.38 KIPS
 
Image Classification (Q)
97% 23045
4.30 KIPS
 
Image Segmentation (SP)
100% 2325
37.7 IPS
 
Image Segmentation (HP)
100% 23551
381.8 IPS
 
Image Segmentation (Q)
99% 32373
524.8 IPS
 
Pose Estimation (SP)
100% 17137
20.0 IPS
 
Pose Estimation (HP)
100% 122844
143.3 IPS
 
Pose Estimation (Q)
95% 228115
267.4 IPS
 
Object Detection (SP)
100% 2458
195.0 IPS
 
Object Detection (HP)
100% 20251
1.61 KIPS
 
Object Detection (Q)
91% 24398
1.95 KIPS
 
Face Detection (SP)
100% 4601
54.7 IPS
 
Face Detection (HP)
100% 45794
544.1 IPS
 
Face Detection (Q)
100% 64490
766.3 IPS
 
Depth Estimation (SP)
100% 8632
66.5 IPS
 
Depth Estimation (HP)
99% 112070
863.4 IPS
 
Depth Estimation (Q)
85% 179675
1.40 KIPS
 
Style Transfer (SP)
100% 25675
33.0 IPS
 
Style Transfer (HP)
100% 237391
305.2 IPS
 
Style Transfer (Q)
96% 302312
390.1 IPS
 
Image Super-Resolution (SP)
100% 5953
219.8 IPS
 
Image Super-Resolution (HP)
100% 47536
1.76 KIPS
 
Image Super-Resolution (Q)
99% 81137
3.00 KIPS
 
Text Classification (SP)
100% 2913
3.89 KIPS
 
Text Classification (HP)
100% 5878
7.85 KIPS
 
Text Classification (Q)
93% 6607
8.87 KIPS
 
Machine Translation (SP)
100% 5672
97.7 IPS
 
Machine Translation (HP)
100% 17153
295.5 IPS
 
Machine Translation (Q)
98% 16932
292.6 IPS
 

Compare

Set Baseline Geekbench 6 now available