Geekbench AI Score

4889
Single Precision Score
37028
Half Precision Score
51761
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User Martythebrit
Upload Date February 17 2026 09:59 PM
Views 12

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 26.3 (Build 25D125)
Model Mac mini (2024)
Model IDMac16,10
Motherboard Mac16,10
CPU Information
Name Apple M4
Topology 1 Processor, 10 Cores
Identifier Apple M4
Base Frequency 4.42 GHz
Cluster 14 Cores
Cluster 26 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2075
385.8 IPS
 
Image Classification (HP)
100% 18532
3.45 KIPS
 
Image Classification (Q)
97% 24631
4.60 KIPS
 
Image Segmentation (SP)
100% 2033
33.0 IPS
 
Image Segmentation (HP)
100% 22209
360.0 IPS
 
Image Segmentation (Q)
99% 30233
490.1 IPS
 
Pose Estimation (SP)
100% 10033
11.7 IPS
 
Pose Estimation (HP)
100% 123188
143.7 IPS
 
Pose Estimation (Q)
95% 232253
272.2 IPS
 
Object Detection (SP)
100% 2422
192.1 IPS
 
Object Detection (HP)
100% 18414
1.46 KIPS
 
Object Detection (Q)
91% 26396
2.11 KIPS
 
Face Detection (SP)
100% 4191
49.8 IPS
 
Face Detection (HP)
100% 43455
516.3 IPS
 
Face Detection (Q)
100% 60597
720.0 IPS
 
Depth Estimation (SP)
100% 8463
65.2 IPS
 
Depth Estimation (HP)
99% 100041
770.8 IPS
 
Depth Estimation (Q)
85% 166520
1.30 KIPS
 
Style Transfer (SP)
100% 24159
31.1 IPS
 
Style Transfer (HP)
100% 233131
299.7 IPS
 
Style Transfer (Q)
96% 321639
415.1 IPS
 
Image Super-Resolution (SP)
100% 6051
223.4 IPS
 
Image Super-Resolution (HP)
100% 53921
1.99 KIPS
 
Image Super-Resolution (Q)
99% 87915
3.25 KIPS
 
Text Classification (SP)
100% 3248
4.34 KIPS
 
Text Classification (HP)
99% 5775
7.71 KIPS
 
Text Classification (Q)
93% 5760
7.73 KIPS
 
Machine Translation (SP)
100% 4526
78.0 IPS
 
Machine Translation (HP)
100% 16445
283.3 IPS
 
Machine Translation (Q)
98% 18402
318.0 IPS
 

Compare

Set Baseline Geekbench 6 now available