Geekbench AI Score

5376
Single Precision Score
38587
Half Precision Score
52920
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

Upload Date July 01 2025 07:51 AM
Views 4

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% 2065
384.0 IPS
 
Image Classification (HP)
100% 18967
3.53 KIPS
 
Image Classification (Q)
97% 23859
4.45 KIPS
 
Image Segmentation (SP)
100% 2332
37.8 IPS
 
Image Segmentation (HP)
100% 23563
382.0 IPS
 
Image Segmentation (Q)
99% 33983
550.9 IPS
 
Pose Estimation (SP)
100% 17170
20.0 IPS
 
Pose Estimation (HP)
100% 122013
142.4 IPS
 
Pose Estimation (Q)
95% 232200
272.2 IPS
 
Object Detection (SP)
100% 2454
194.7 IPS
 
Object Detection (HP)
100% 20947
1.66 KIPS
 
Object Detection (Q)
91% 25381
2.03 KIPS
 
Face Detection (SP)
100% 4583
54.5 IPS
 
Face Detection (HP)
100% 45816
544.4 IPS
 
Face Detection (Q)
100% 67522
802.3 IPS
 
Depth Estimation (SP)
100% 8571
66.0 IPS
 
Depth Estimation (HP)
99% 112740
868.6 IPS
 
Depth Estimation (Q)
85% 180862
1.41 KIPS
 
Style Transfer (SP)
100% 25486
32.8 IPS
 
Style Transfer (HP)
100% 237573
305.4 IPS
 
Style Transfer (Q)
96% 309921
399.9 IPS
 
Image Super-Resolution (SP)
100% 5887
217.4 IPS
 
Image Super-Resolution (HP)
100% 48336
1.78 KIPS
 
Image Super-Resolution (Q)
99% 83018
3.07 KIPS
 
Text Classification (SP)
100% 2916
3.89 KIPS
 
Text Classification (HP)
100% 6251
8.34 KIPS
 
Text Classification (Q)
93% 6705
9.00 KIPS
 
Machine Translation (SP)
100% 5787
99.7 IPS
 
Machine Translation (HP)
100% 17282
297.7 IPS
 
Machine Translation (Q)
98% 17114
295.8 IPS
 

Compare

Set Baseline Geekbench 6 now available