Snapdragon 870 vs Tensor G2

We compared two 8-core processors: Qualcomm Snapdragon 870 (with Adreno 650 graphics) and Google Tensor G2 (Mali-G710 MP7). Here you will find the pros and cons of each chip, technical specs, and comprehensive tests in benchmarks, like AnTuTu and Geekbench.

Review

General comparison of performance, power consumption, and other indicators
CPU Performance
Single and multi-core processor tests
Gaming Performance
GPU performance in games and OpenCL/Vulkan
Battery life
Efficiency of battery consumption
NanoReview Score
Overall chip score

Key Differences

Main differences and advantages of each chip
Pros of Qualcomm Snapdragon 870
  • Performs 35% better in floating-point computations
  • 12% higher CPU clock speed (3200 vs 2850 MHz)
Pros of Google Tensor G2
  • Has a smaller size transistor (5 versus 7 nm)
  • Higher GPU frequency (~27%)
  • Supports 16% higher memory bandwidth (51.2 against 44 GB/s)
  • Shows better (up to 17%) AnTuTu 11 score – 1186K vs 1010K
  • Better instruction set architecture

Benchmarks

Performance tests in popular benchmarks

AnTuTu 11

The AnTuTu Benchmark measures CPU, GPU, RAM, and I/O performance in different scenarios
1010069
Tensor G2 +17%
1186373
CPU 378231 384056
GPU 155526 278383
Memory 174975 220709
UX 301337 303255
Total score 1010069 1186373
Samples [102 tests] [54 tests]

GeekBench 6

The GeekBench test shows raw single-threaded and multithreaded CPU performance
Single-Core Score
Tensor G2 +13%
1461
Multi-Core Score
Tensor G2 +10%
3867
Asset compression 160.2 MB/sec 149.9 MB/sec
HTML 5 Browser 86.7 pages/sec 99.9 pages/sec
PDF Renderer 116.8 Mpixels/sec 110.2 Mpixels/sec
Image detection 80 images/sec 74.2 images/sec
HDR 108 Mpixels/sec 105.5 Mpixels/sec
Background blur 12 images/sec 11.7 images/sec
Photo processing 33.5 images/sec 35.1 images/sec
Ray tracing 4.41 Mpixels/sec 4.26 Mpixels/sec
Samples 34 tests 26 tests
Compute Score (GPU)
Tensor G2 +39%
4715
Background blur 5.01 images/sec 6.68 images/sec
Face detection 2.04 images/sec 3.96 images/sec
Horizon detection 0.19 Gpixels/sec 0.22 Gpixels/sec
Edge detection 0.26 Gpixels/sec 0.35 Gpixels/sec
Gaussian blur 0.21 Gpixels/sec 0.2 Gpixels/sec
Feature matching 0.03 Gpixels/sec 0.06 Gpixels/sec
Stereo matching 10.3 Gpixels/sec 11.5 Gpixels/sec
Particle physics 650.5 FPS 972.6 FPS
API OpenCL Vulkan
Samples 18 tests 17 tests

3DMark

A cross-platform benchmark that assesses graphics performance in Vulkan (Metal)
3DMark Steel Nomad Light
Score - 702
Stability - 78%
Graphics test - 5 FPS
3DMark Wild Life Extreme
Tensor G2 +49%
1821
Score 1224 1821
Stability 99% 77%
Graphics test 7 FPS 10 FPS

PCMark 3.0

Benchmark for evaluating overall system performance in everyday workloads
PCMark 3.0
12227
10994
Web score 11701 7923
Video editing score 5825 6434
Data manipulation score 9987 11061
Photo editing score 28690 18842
Writing score 15274 15053
Phones tested 2 models 5 models

Gaming

Table of average FPS and graphics settings in mobile games
PUBG Mobile 88 FPS
[Ultra]
-
Call of Duty: Mobile 59 FPS
[Ultra]
-
Fortnite 27 FPS
[Ultra]
-
Shadowgun Legends 102 FPS
[Ultra]
-
World of Tanks Blitz 107 FPS
[Ultra]
-
Genshin Impact 49 FPS
[Ultra]
-
Mobile Legends: Bang Bang 60 FPS
[Ultra]
-
Device Xiaomi Black Shark 4
1080 x 2400
-
We provide average results. FPS may differ, depending on game version, OS and other factors.

Recent User Tests

The latest benchmark tests that have been submitted by users
Qualcomm Snapdragon 870
DateBenchmarkResult
πŸ“˜ 2026-09-23 -> AzuNoBelAnTuTu 121251812
πŸ“˜ 2026-09-23 (Ambarukmo_id)AnTuTu 121182612
πŸ“˜ 2026-09-21 -> sbx.777AnTuTu 121143560
πŸ“˜ 2026-09-21 (alvyan)AnTuTu 121096940
πŸ“˜ 2026-09-03 (DisnaroπŸ‡§πŸ‡·)AnTuTu 111029687
Google Tensor G2
DateBenchmarkResult
πŸ“˜ 2026-09-09 -> Kimash333AnTuTu 111253847
πŸ“˜ 2026-09-08 (Kimash333)AnTuTu 111253847
πŸ“˜ 2026-09-02 -> nanamondAnTuTu 111196742
πŸ“˜ 2026-08-06 -> shu-AnTuTu 111126520
πŸ“˜ 2026-08-05 (shu-)AnTuTu 111126520

Specifications

Full list of technical specifications of Snapdragon 870 and Tensor G2

CPU

Architecture 1x 3.2 GHz – Kryo 585 Prime (Cortex-A77)
3x 2.42 GHz – Kryo 585 Gold (Cortex-A77)
4x 1.8 GHz – Kryo 585 Silver (Cortex-A55)
2x 2.85 GHz – Cortex-X1
2x 2.35 GHz – Cortex-A78
4x 1.8 GHz – Cortex-A55
Cores 8 8
Frequency 3200 MHz 2850 MHz
Instruction set ARMv8.2-A ARMv8.4-A
L1 cache 512 KB -
L2 cache 1 MB -
L3 cache 4 MB 4 MB
Process 7 nanometers 5 nanometers
Transistor count 10.3 billion -
TDP (Sustained Power Limit) 6 W 7 W
Manufacturing TSMC Samsung

Graphics

GPU name Adreno 650 Mali-G710 MP7
Architecture Adreno 600 Valhall 3rd gen
GPU frequency 670 MHz 848 MHz
Pipelines 3 7
Shading units 256 64
Total shaders 768 448
FLOPS 1029.1 Gigaflops 759.8 Gigaflops
Vulkan version 1.1 1.3
OpenCL version 2.0 2.0
DirectX version 12.1 -

AI Accelerator

Neural processor (NPU) Hexagon 698 Next-gen Tensor Processing Unit

Memory

Memory type LPDDR5 LPDDR5
Memory frequency 2750 MHz 3200 MHz
Bus 4x 16 Bit 4x 16 Bit
Max bandwidth 44 Gb/s 51.2 Gb/s
Max size 16 GB 16 GB

Multimedia (ISP)

Storage type UFS 3.0, UFS 3.1 UFS 3.1
Max display resolution 3840 x 2160 3840 x 2160
Max camera resolution 1x 200MP, 2x 25MP 1x 200MP, 2x 32MP
Video capture 8K at 30FPS, 4K at 60FPS 4K at 60FPS
Video playback 8K at 30FPS, 4K at 60FPS 4K at 60FPS
Video codecs - H.264
- H.265
- VP8
- VP9
- H.264
- H.265
- AV1
- VP9
Audio codecs - AAC
- AIFF
- CAF
- MP3
- MP4
- WAV
- AAC
- AIFF
- CAF
- MP3
- MP4
- WAV

Connectivity

Modem X55 Exynos 5300g
4G support LTE Cat. 22 LTE Cat. 24
5G support Yes Yes
Download speed Up to 7500 Mbps Up to 7350 Mbps
Upload speed Up to 3000 Mbps Up to 3670 Mbps
Wi-Fi 6 6
Bluetooth 5.2 5.2
Navigation GPS, GLONASS, Beidou, Galileo, QZSS, SBAS, NAVIC GPS, GLONASS, Beidou, Galileo, QZSS, NAVIC

Info

Announced January 2021 October 2022
Class Flagship Flagship
Model number SM8250-AC GS201 (S5P9855)
Official page Qualcomm Snapdragon 870 official site -
Successor - - Google Tensor G5

Cast your vote

So, which SoC would you choose?
157 (47.6%)
173 (52.4%)
Total votes: 330

Comments

Please give your opinion on the comparison of Tensor G2 and Snapdragon 870, or ask any questions
🌐 Register your profile and become part of NanoReview community!