Tensor G2 vs A15 Bionic

We compared the 8-core Google Tensor G2 (Mali-G710 MP7) with the older 6-core Apple A15 Bionic (Apple A15 GPU) SoC. 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 Google Tensor G2
  • Supports 50% higher memory bandwidth (51.2 against 34.1 GB/s)
  • Has 2 more cores
Pros of Apple A15 Bionic
  • Performs 2.3x better in floating-point computations
  • Higher GPU frequency (~58%)
  • Shows better (up to 19%) AnTuTu 11 score – 1413K vs 1186K
  • 13% higher CPU clock speed (3230 vs 2850 MHz)
  • 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
1186373
A15 Bionic +19%
1413275
CPU 384056 410975
GPU 278383 370837
Memory 220709 164151
UX 303255 467312
Total score 1186373 1413275
Samples [54 tests] [69 tests]
AnTuTu results from iOS and Android are not directly comparable! They won't affect NanoReview scores.

GeekBench 6

The GeekBench test shows raw single-threaded and multithreaded CPU performance
Single-Core Score
1461
A15 Bionic +58%
2315
Multi-Core Score
3867
A15 Bionic +49%
5753
Asset compression 149.9 MB/sec 208.1 MB/sec
HTML 5 Browser 99.9 pages/sec 122.9 pages/sec
PDF Renderer 110.2 Mpixels/sec 139.1 Mpixels/sec
Image detection 74.2 images/sec 125.1 images/sec
HDR 105.5 Mpixels/sec 179.4 Mpixels/sec
Background blur 11.7 images/sec 22.3 images/sec
Photo processing 35.1 images/sec 53.2 images/sec
Ray tracing 4.26 Mpixels/sec 6.26 Mpixels/sec
Samples 26 tests 37 tests
Compute Score (GPU)
4715
A15 Bionic +333%
20400
Background blur 6.68 images/sec 35.4 images/sec
Face detection 3.96 images/sec 44.8 images/sec
Horizon detection 0.22 Gpixels/sec 0.62 Gpixels/sec
Edge detection 0.35 Gpixels/sec 0.82 Gpixels/sec
Gaussian blur 0.2 Gpixels/sec 0.84 Gpixels/sec
Feature matching 0.06 Gpixels/sec 0.3 Gpixels/sec
Stereo matching 11.5 Gpixels/sec 71.1 Gpixels/sec
Particle physics 972.6 FPS 2198.2 FPS
API Vulkan Metal
Samples 17 tests 19 tests
Compute results use different APIs (Metal vs Vulkan/OpenCL) and are not directly comparable!

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 Solar Bay
Score - 3765
Stability - 71%
Graphics test - 14 FPS
Section 1 - 19 FPS
Section 2 - 14 FPS
Section 3 - 9 FPS
3DMark Wild Life Extreme
1821
A15 Bionic +57%
2854
Score 1821 2854
Stability 77% 76%
Graphics test 10 FPS 17 FPS

PCMark 3.0

Benchmark for evaluating overall system performance in everyday workloads
PCMark 3.0
10994
Web score 7923 -
Video editing score 6434 -
Data manipulation score 11061 -
Photo editing score 18842 -
Writing score 15053 -
Phones tested 5 models -

Recent User Tests

The latest benchmark tests that have been submitted by users
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
Apple A15 Bionic
DateBenchmarkResult
πŸ“˜ 2026-09-25 -> op1Geekbench 6 CPU2168 / 4988
πŸ“˜ 2026-09-23 -> HotPowerAnTuTu 111184759
πŸ“˜ 2026-09-19 -> HotPowerGeekbench 6 GPU21284
πŸ“˜ 2026-09-19 (Vova)AnTuTu 111297615
πŸ“˜ 2026-09-19 -> HotPowerGeekbench 6 CPU2423 / 5985

Specifications

Full list of technical specifications of Tensor G2 and A15 Bionic

CPU

Architecture 2x 2.85 GHz – Cortex-X1
2x 2.35 GHz – Cortex-A78
4x 1.8 GHz – Cortex-A55
2x 3.23 GHz – Avalanche
4x 2.02 GHz – Blizzard
Cores 8 6
Frequency 2850 MHz 3230 MHz
Instruction set ARMv8.4-A ARMv8.5-A
L1 cache - 256 KB
L2 cache - 12 MB
L3 cache 4 MB -
Process 5 nanometers 5 nanometers
Transistor count - 15 billion
TDP (Sustained Power Limit) 7 W 6 W
Manufacturing Samsung TSMC

Graphics

GPU name Mali-G710 MP7 Apple A15 GPU
Architecture Valhall 3rd gen Apple Bionic GPU
GPU frequency 848 MHz 1338 MHz
Pipelines 7 5
Shading units 64 128
Total shaders 448 640
FLOPS 759.8 Gigaflops 1712.6 Gigaflops
Vulkan version 1.3 -
OpenCL version 2.0 -

AI Accelerator

Neural processor (NPU) Next-gen Tensor Processing Unit Apple Neural Engine
NPU theoretical performance - 15.8 TOPS

Memory

Memory type LPDDR5 LPDDR4X
Memory frequency 3200 MHz 2133 MHz
Bus 4x 16 Bit 4x 16 Bit
Max bandwidth 51.2 Gb/s 34.1 Gb/s
Max size 16 GB 6 GB

Multimedia (ISP)

Storage type UFS 3.1 NVMe
Max display resolution 3840 x 2160 2732 x 2048
Max camera resolution 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
- VP8
- VP9
- Motion JPEG
Audio codecs - AAC
- AIFF
- CAF
- MP3
- MP4
- WAV
- AAC
- AAX
- AAX+
- AC-3
- AIFF
- CAF
- E-AC-3
- MP3
- MP4
- WAV

Connectivity

Modem Exynos 5300g -
4G support LTE Cat. 24 LTE Cat. 24
5G support Yes Yes
Download speed Up to 7350 Mbps Up to 7500 Mbps
Upload speed Up to 3670 Mbps Up to 3000 Mbps
Wi-Fi 6 6
Bluetooth 5.2 5.0
Navigation GPS, GLONASS, Beidou, Galileo, QZSS, NAVIC GPS, GLONASS, Beidou, Galileo, QZSS

Info

Announced October 2022 September 2021
Class Flagship Flagship
Model number GS201 (S5P9855) APL1W07
Successor - Google Tensor G5 - Apple A19 Pro

Cast your vote

So, which SoC would you choose?
296 (36.8%)
508 (63.2%)
Total votes: 804

Comments

Please give your opinion on the comparison of A15 Bionic and Tensor G2, or ask any questions
🌐 Register your profile and become part of NanoReview community!
Avatar
Guest 3214 May 4, 2023 at 05:49 AM
It's all about the experience, and the Pixel delivers even on an older phone like the 4a 5G. If someone wants to compare iOS with Android, it's only fair that the comparison be made with the Google Pixel, as the same company creates both the software and hardware.
+16 Reply
Avatar
somedude September 27, 2023 at 03:17 AM
Just switched back to iOS but had the same mindset thought it might be the same experience cause they have the tech stack to themselves, its not even close, half-baked stuff on Google, and apps you install are not adapted for Google only, almost nonuse google's own material design platform, even APIs are general, so it doesn't even hold a candle when it comes to experience compared to iOS, but that might be true when compared to other android phones as the OS on the pixel is stock and bloat-free.
+1 Reply
Avatar
Randy chan March 15, 2023 at 12:36 AM
Regarding Google's in-house made tensor 2 chip, even though it was made virtually around the same time as Apple's A16 bionic chip, as you can see in the performance benchmarks comparison, the Google tensor 2 chip pales even to Apple's A15 bionic chip which proves how great and above Apple is and how far below Google is. Seems like Apple wins this contest by a mile.
+21 Reply