Geekbench AI Score

38
Single Precision Score
717
Half Precision Score
556
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

Upload Date November 22 2026 04:54 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device MediaTek Helio G95
System Information
Operating System Android 13
Model Realme 8
Model IDrealme RMX3085
Motherboard RM6785
CPU Information
Name ARM MT6785V/CD
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.05 GHz
Memory Information
Size 3.53 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
0% 0
45.3 IPS
 
Image Classification (HP)
100% 450
83.7 IPS
 
Image Classification (Q)
97% 439
81.9 IPS
 
Image Segmentation (SP)
73% 322
5.56 IPS
 
Image Segmentation (HP)
100% 649
10.5 IPS
 
Image Segmentation (Q)
98% 588
9.56 IPS
 
Pose Estimation (SP)
100% 1536
1.79 IPS
 
Pose Estimation (HP)
100% 2601
3.04 IPS
 
Pose Estimation (Q)
95% 2488
2.92 IPS
 
Object Detection (SP)
1% 0
17.0 IPS
 
Object Detection (HP)
99% 410
32.5 IPS
 
Object Detection (Q)
83% 372
30.0 IPS
 
Face Detection (SP)
0% 0
8.98 IPS
 
Face Detection (HP)
100% 1830
21.7 IPS
 
Face Detection (Q)
96% 1363
16.3 IPS
 
Depth Estimation (SP)
2% 3
7.33 IPS
 
Depth Estimation (HP)
98% 1832
14.2 IPS
 
Depth Estimation (Q)
62% 1237
11.7 IPS
 
Style Transfer (SP)
100% 2362
3.04 IPS
 
Style Transfer (HP)
100% 4969
6.39 IPS
 
Style Transfer (Q)
98% 4765
6.14 IPS
 
Image Super-Resolution (SP)
100% 534
19.7 IPS
 
Image Super-Resolution (HP)
100% 1050
38.8 IPS
 
Image Super-Resolution (Q)
97% 1066
39.5 IPS
 
Text Classification (SP)
35% 13
115.6 IPS
 
Text Classification (HP)
35% 18
164.5 IPS
 
Text Classification (Q)
32% 15
187.8 IPS
 
Machine Translation (SP)
100% 291
5.02 IPS
 
Machine Translation (HP)
100% 371
6.38 IPS
 
Machine Translation (Q)
43% 92
5.33 IPS
 

Compare

Set Baseline Geekbench AI now available