Follow us
Share link
Submit benchmark
VS
Google Tensor G2 vs Apple M3 Max (16-CPU 40-GPU)
Last updated:
Benchmarks
Performance Overview
Average performance across multiple benchmarks
Single-core performance
Multi-core performance
Geekbench 6 Single-Core
Single-core performance
Google Tensor G2
46 %
8C / 8T · 2.85 GHz
16C / 16T · 4.06 GHz
Geekbench 6 Multi-Core
Multi-core performance
Google Tensor G2
16 %
8C / 8T · 2.85 GHz
16C / 16T · 3.60 GHz
Geekbench 5, 64bit Single-Core
Single-core performance
Google Tensor G2
50 %
8C / 8T · 2.85 GHz
16C / 16T · 4.06 GHz
Geekbench 5, 64bit Multi-Core
Multi-core performance
Google Tensor G2
14 %
8C / 8T · 2.85 GHz
16C / 16T · 3.60 GHz
iGPU - FP32 Performance (Single-precision GFLOPS)
Google Tensor G2
5 %
ARM Mali-G710 MP7
Apple M3 Max (40 Core)
AI performance (NPU)
Google Tensor G2
11 %
8C / 8T · 2.85 GHz
16C / 16T · 0.70 GHz
More benchmarks
Cinebench 2026 (ST)
218 entries
218 entries
Cinebench 2026 (MC)
219 entries
219 entries
Cinebench 2024 (SC)
427 entries
427 entries
Cinebench 2024 (MC)
422 entries
422 entries
Cinebench R23 (SC)
690 entries
690 entries
Cinebench R23 (MC)
665 entries
665 entries
Geekbench 6 (SC)
1,989 entries
1,989 entries
Geekbench 6 (MC)
1,927 entries
1,927 entries
Cinebench R20 (SC)
666 entries
666 entries
Geekbench 5 (SC)
2,512 entries
2,512 entries
Cinebench R20 (MC)
615 entries
615 entries
Geekbench 5 (MC)
2,483 entries
2,483 entries
FP32 SP (iGPU)
2,219 entries
2,219 entries
AnTuTu 9 Benchmark
90 entries
90 entries
Cinebench R15 (SC)
1,113 entries
1,113 entries
Cinebench R15 (MC)
1,110 entries
1,110 entries
CPU performance per watt (efficiency)
140 entries
140 entries
AI performance (NPU)
218 entries
218 entries
Specifications
At a glance
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| Family | Google Tensor (5) | Apple M series (38) |
| CPU group | Google Tensor G2 (1) | Apple M3 (6) |
| Architecture | G2 | M3 |
| Technology | 5 nm | 3 nm |
| Segment | Smartphone / Tablet | Notebook |
| Socket | ||
| Predecessor | Google Tensor | Apple M2 Max (30-GPU) |
| Successor | Apple M4 Max (16-CPU 40-GPU) |
CPU Cores and Base Frequency
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| CPU Cores / Threads | 8 / 8 | 16 / 16 |
| Hyperthreading / SMT | ✗ | ✗ |
| Core architecture | hybrid (Prime / big.LITTLE) | hybrid (big.LITTLE) |
| Core Cluster 1: | 2x Cortex-X1 2.85 GHz |
12x Palma P-Core 0.70 - 4.06 GHz |
| Core Cluster 2: | 2x Cortex-A78 2.35 GHz |
4x Palma E-Core 0.74 - 2.75 GHz |
| Core Cluster 3: | 4x Cortex-A55 1.80 GHz |
|
| L2-Cache | 8.00 MB | 36.00 MB |
| L3-Cache | 4.00 MB | |
| Overclocking | ✗ | ✗ |
Integrated graphics (iGPU)
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| GPU name | ARM Mali-G710 MP7 | Apple M3 Max (40 Core) |
| GPU frequency | 0.90 GHz | 0.39 - 1.40 GHz |
| CUs / Shader | 7 / | 640 / 5120 |
| Raytracing | ✗ | ✓ |
| Max. displays | 1 | 5 |
| Max. GPU Memory | 128 GB | |
| Technology | 4 nm | 3 nm |
| Release date | Q2/2021 | Q4/2023 |
NPU AI performance
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| AI hardware | Google Tensor AI | Apple Neural Engine |
| AI specifications | Google Edge TPU @ 4 TOPS | 16 Neural cores @ 35 TOPS |
| NPU + CPU + iGPU |
Memory & PCIe
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| Memory | LPDDR5-5500 (53.0 GB/s) | LPDDR5-6400 (409.6 GB/s) |
| Max. Memory | 12 GB | 128 GB |
| Memory channels | 2 | 4 |
| ECC | No | No |
| PCIe | 4.0 | |
| PCIe Bandwidth |
Thermal Management
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| TDP | 10 W | 57 W |
| TDP (PL2) | ||
| TDP up | ||
| TDP down | ||
| T. junction max. | 100 °C |
Technical details
|
Wischen
|
Google Tensor G2 | Apple M3 Max (16-CPU 40-GPU) |
|---|---|---|
| Chip design | Chiplet | Monolithic |
| AES-NI | ✗ | ✓ |
| Operating systems | Android | macOS, iPadOS |
| Instruction set | Armv8-A (64 bit) | Armv8-A (64 bit) |
| ISA extensions | Rosetta 2 x86-Emulation | |
| Release date | Q4/2022 | Q4/2023 |
| Release price | ||
| Documents |
User Reviews
Your rating
Here you can rate one or both of the processors. The average rating of Google Tensor G2 is 4.0 stars (86 ratings), while Apple M3 Max (16-CPU 40-GPU) has received 4.9 stars (636 ratings).
Click on the stars to rate one or both processors.
Most popular CPUs in both categories
1
Apple M5 Max (18-CPU 32-GPU)
18C / 18T · 4.61 GHz
2
Apple M5 Max (18-CPU 40-GPU)
18C / 18T · 4.61 GHz
3
Apple M2 Ultra (76-GPU)
24C / 24T · 3.50 GHz
4
Apple M1 Ultra (64-GPU)
20C / 20T · 3.20 GHz
5
Apple M1 Ultra (48-GPU)
20C / 20T · 3.20 GHz
6
Apple M2 Ultra (60-GPU)
24C / 24T · 3.50 GHz
7
Apple M1 Pro (8-CPU)
8C / 8T · 3.20 GHz
8
Apple M3 Max (16-CPU 40-GPU)
16C / 16T · 4.06 GHz
9
Google Tensor G2
8C / 8T · 0.00 GHz
Popular Comparisons
