Geekbench AI Score

5177
Single Precision Score
46160
Half Precision Score
43210
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User ledzep443
Upload Date March 19 2026 06:04 PM
Views 8

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M5 Max
System Information
Operating System macOS 26.3.1 (Build 25D2128)
Model Mac17,6
Model IDMac17,6
Motherboard Mac17,6
CPU Information
Name Apple M5 Max
Topology 1 Processor, 18 Cores
Identifier Apple M5 Max
Base Frequency 4.61 GHz
Cluster 16 Cores
Cluster 212 Cores
Memory Information
Size 128.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2378
442.2 IPS
 
Image Classification (HP)
100% 20835
3.87 KIPS
 
Image Classification (Q)
97% 25551
4.77 KIPS
 
Image Segmentation (SP)
100% 2532
41.0 IPS
 
Image Segmentation (HP)
100% 25977
421.1 IPS
 
Image Segmentation (Q)
99% 36874
597.7 IPS
 
Pose Estimation (SP)
100% 11025
12.9 IPS
 
Pose Estimation (HP)
100% 184346
215.1 IPS
 
Pose Estimation (Q)
95% 340449
399.0 IPS
 
Object Detection (SP)
100% 2868
227.5 IPS
 
Object Detection (HP)
100% 23908
1.90 KIPS
 
Object Detection (Q)
91% 28534
2.28 KIPS
 
Face Detection (SP)
100% 5330
63.3 IPS
 
Face Detection (HP)
100% 50312
597.8 IPS
 
Face Detection (Q)
100% 71564
850.3 IPS
 
Depth Estimation (SP)
100% 9457
72.9 IPS
 
Depth Estimation (HP)
99% 139560
1.08 KIPS
 
Depth Estimation (Q)
85% 218048
1.70 KIPS
 
Style Transfer (SP)
100% 27259
35.0 IPS
 
Style Transfer (HP)
100% 289606
372.3 IPS
 
Style Transfer (Q)
96% 401283
517.8 IPS
 
Image Super-Resolution (SP)
100% 6062
223.8 IPS
 
Image Super-Resolution (HP)
100% 69279
2.56 KIPS
 
Image Super-Resolution (Q)
99% 3682
136.0 IPS
 
Text Classification (SP)
100% 3481
4.65 KIPS
 
Text Classification (HP)
99% 6682
8.92 KIPS
 
Text Classification (Q)
93% 5579
7.49 KIPS
 
Machine Translation (SP)
100% 2509
43.2 IPS
 
Machine Translation (HP)
100% 19561
336.9 IPS
 
Machine Translation (Q)
98% 19278
333.1 IPS
 

Compare

Set Baseline Geekbench 6 now available