Home > Smartphone processors comparison > Tensor G2 vs Google Tensor โ€“ what's better?

Tensor G2 vs Google Tensor

Tensor G2
VS
Google Tensor
Tensor G2
Google Tensor

We compared two 8-core processors: Google Tensor G2 (with Mali-G710 MP7 graphics) and Google Tensor (Mali-G78 MP20). Here you will find the pros and cons of each chip, technical specs, and comprehensive tests in benchmarks, like AnTuTu and Geekbench.

  1. Review
  2. Differences
  3. Benchmarks
  4. AnTuTu v11
  5. GeekBench 6
  6. Specs
  7. Comments (11)

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 Google Tensor G2
  • Shows better (up to 17%) AnTuTu 11 score โ€“ 1186K vs 1010K
  • Better instruction set architecture
Pros of Google Tensor
  • Performs 43% better in floating-point computations

Benchmarks

Performance tests in popular benchmarks
SoC:
Tensor G2
vs
Google Tensor

AnTuTu 11

The AnTuTu Benchmark measures CPU, GPU, RAM, and I/O performance in different scenarios
Tensor G2 +17%
1186373
Google Tensor
1010025
CPU 384056 365546
GPU 278383 169803
Memory 220709 178763
UX 303255 295913
Total score 1186373 1010025
Samples [54 tests] [51 tests]
Submit your AnTuTu result

GeekBench 6

The GeekBench test shows raw single-threaded and multithreaded CPU performance
Single-Core Score
Tensor G2
1461
Google Tensor +1%
1477
Multi-Core Score
Tensor G2 +8%
3867
Google Tensor
3595
Asset compression 149.9 MB/sec 159.8 MB/sec
HTML 5 Browser 99.9 pages/sec 97.5 pages/sec
PDF Renderer 110.2 Mpixels/sec 138.9 Mpixels/sec
Image detection 74.2 images/sec 83.4 images/sec
HDR 105.5 Mpixels/sec 119.7 Mpixels/sec
Background blur 11.7 images/sec 14.1 images/sec
Photo processing 35.1 images/sec 30.2 images/sec
Ray tracing 4.26 Mpixels/sec 3.44 Mpixels/sec
Samples 26 tests 26 tests
Compute Score (GPU)
Tensor G2
4715
Google Tensor +89%
8918
Background blur 6.68 images/sec 13.2 images/sec
Face detection 3.96 images/sec 7.31 images/sec
Horizon detection 0.22 Gpixels/sec 0.34 Gpixels/sec
Edge detection 0.35 Gpixels/sec 0.5 Gpixels/sec
Gaussian blur 0.2 Gpixels/sec 0.55 Gpixels/sec
Feature matching 0.06 Gpixels/sec 0.09 Gpixels/sec
Stereo matching 11.5 Gpixels/sec 39.4 Gpixels/sec
Particle physics 972.6 FPS 1368.9 FPS
API Vulkan Vulkan
Samples 17 tests 11 tests

3DMark

A cross-platform benchmark that assesses graphics performance in Vulkan (Metal)
3DMark Steel Nomad Light
Score 702 704
Stability 78% 63%
Graphics test 5 FPS 5 FPS
3DMark Wild Life Extreme
Tensor G2
1821
Google Tensor +4%
1899
Score 1821 1899
Stability 77% 59%
Graphics test 10 FPS 11 FPS

PCMark 3.0

Benchmark for evaluating overall system performance in everyday workloads
PCMark 3.0
Tensor G2 +5%
10994
Google Tensor
10455
Web score 7923 7105
Video editing score 6434 5884
Data manipulation score 11061 10310
Photo editing score 18842 19072
Writing score 15053 15550
Phones tested 5 models 3 models

Recent User Tests

The latest benchmark tests that have been submitted by users
Google Tensor G2
DateBenchmarkResult
๐Ÿ“˜ 2026-09-09 -> Kimash333AnTuTu1253847
๐Ÿ“˜ 2026-09-08 (Kimash333)AnTuTu1253847
๐Ÿ“˜ 2026-09-02 -> nanamondAnTuTu1196742
๐Ÿ“˜ 2026-08-06 -> shu-AnTuTu1126520
๐Ÿ“˜ 2026-08-05 (shu-)AnTuTu1126520
Add View all (89)
Google Tensor
DateBenchmarkResult
๐Ÿ“˜ 2026-08-19 (duwi)AnTuTu774697
๐Ÿ“˜ 2026-08-17 -> Paranoid _AntostAnTuTu930801
๐Ÿ“˜ 2026-08-04 (nguyen van nguyen)AnTuTu990021
๐Ÿ“˜ 2026-07-29 (Mimo)AnTuTu1117985
๐Ÿ“˜ 2026-07-28 (Hypermini)AnTuTu1015541
Add View all (82)

Specifications

Full list of technical specifications of Tensor G2 and Google Tensor

CPU

Architecture 2x 2.85 GHz โ€“ Cortex-X1
2x 2.35 GHz โ€“ Cortex-A78
4x 1.8 GHz โ€“ Cortex-A55		 2x 2.8 GHz โ€“ Cortex-X1
2x 2.25 GHz โ€“ Cortex A76
4x 1.8 GHz โ€“ Cortex A55
Cores 8 8
Frequency 2850 MHz 2800 MHz
Instruction set ARMv8.4-A ARMv8.2-A
L2 cache - 3 MB
L3 cache 4 MB 4 MB
Process 5 nanometers 5 nanometers
TDP (Sustained Power Limit) 7 W 5.6 W
Manufacturing Samsung Samsung

Graphics

GPU name Mali-G710 MP7 Mali-G78 MP20
Architecture Valhall 3rd gen Valhall 2nd gen
GPU frequency 848 MHz 850 MHz
Pipelines 7 20
Shading units 64 32
Total shaders 448 640
FLOPS 759.8 Gigaflops 1085.4 Gigaflops
Vulkan version 1.3 1.3
OpenCL version 2.0 2.0

AI Accelerator

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

Memory

Memory type LPDDR5 LPDDR5
Memory frequency 3200 MHz 3200 MHz
Bus 4x 16 Bit 4x 16 Bit
Max bandwidth 51.2 Gb/s 51.2 Gb/s
Max size 16 GB 12 GB

Multimedia (ISP)

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

Connectivity

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

Info

Announced October 2022 October 2021
Class Flagship Flagship
Model number GS201 (S5P9855) GS101 (S5P9845)
Official page - Google Tensor official site
Successor - Google Tensor G5 - Google Tensor G5

Cast your vote

So, which SoC would you choose?
1105 (52.2%)
1011 (47.8%)
Total votes: 2116

Related Comparisons

1. Google Tensor G2 vs Google Tensor G4
2. Google Tensor G2 vs Google Tensor G3 (6)
3. Google Tensor G2 vs Qualcomm Snapdragon 888 (10)
4. Google Tensor G2 vs Qualcomm Snapdragon 8 Gen 2 (8)
5. Google Tensor G2 vs Qualcomm Snapdragon 8 Gen 1
6. Google Tensor vs Apple A17 Pro
7. Google Tensor vs Google Tensor G3
8. Google Tensor vs Qualcomm Snapdragon 8 Gen 1
9. Google Tensor vs Qualcomm Snapdragon 888 (12)
10. Google Tensor vs Apple A16 Bionic
Compare other chipsets (190+)

Comments

Please give your opinion on the comparison of Google Tensor and Tensor G2, or ask any questions
๐ŸŒ Register your profile and become part of NanoReview community!
Avatar
ะžrะฐl Sะตx Dะตะผะพn June 30, 2023 at 02:58 PM
They should've gone in this configuration instead: 2x Cortex X1 @ 2.8GHz 3x Cortex A78 @ 2.4GHz 3x Cortex A55 @ 2.0GHz 10x Mali G710 @ 800MHz
+81 Reply
Avatar
Quetzalcoatlus December 23, 2023 at 07:16 AM
It's crazy that you can find the finest experts in any field on the internet, even Systems on a Chip (SoCs) specialists superior to the ones at Google, right here on the Nano Review forum! Is there anything else they could have done better, Oral Sex Demon?
+46 Reply
Avatar
ZRRrrrr March 28, 2024 at 03:06 AM
Quetzalcoatlus, I can't tell if this is sarcasm or not
+19 Reply
Avatar
nunyabizz October 8, 2022 at 01:10 AM
what a disappointment, using tech from 2018. going the apple route of not focusing on specs, selling a bogus experience
+56 Reply
Avatar
Guest June 5, 2023 at 07:42 AM
The Apple route? Are you kidding? ๐Ÿ˜‚ Apple has had the most powerful mobile processors for a long time now. They are the best in single-core, multi-core, and GPU performance, and no processor in the world can touch their efficiency. Have you ever played a game on the iPhone 14 Pro Max? The experience is so much better than on any Android flagship.
+45 Reply
Avatar
unknowm.03 June 12, 2023 at 11:26 AM
Guest, Because iOS is lighter and more stable than Android, just try it if Apple's chip is placed on Android, it will definitely become trash.
+24 Reply
Avatar
MC Skibadee June 21, 2023 at 08:51 AM
unknowm.03, Everyone knows Apple makes better hardware. Have you heard of their M chips? A generation ahead of everything else. Even the current processors are better. Their 60hz displays feel like 90hz
+11 Reply
Avatar
Cheese July 17, 2023 at 05:15 AM
unknowm.03, No, it's cause they literally buy out every new transistor size TSMC comes out with a smaller transistor that is more efficient and also allows you to cram more power into a smaller space. They're not miracle designers, they just throw cash.
+15 Reply
Avatar
name August 11, 2023 at 09:59 AM
unknowm.03, That just proves Android is a burden. Why place Apple's chip on Android when they have iOS?
+1 Reply
Avatar
Olger August 18, 2023 at 07:20 AM
unknowm.03, Your statement is not true. iOS is very well optimized for the processors of its production, unlike Android, which must work with many processors. This struggle of which is better will be eternal. Having used both Android and iOS for a while, I came to a single vision. They are almost indistinguishable in use for ordinary people who do not use even half of the functions.
+9 Reply
Avatar
steve September 13, 2023 at 04:56 AM
Guest, Actually s23 ultra and every SD 8 Gen 2 phone play games way better than the iphone 14 pro max.
+56 Reply
Englishะ ัƒััะบะธะน