Tensor G6 vs Tensor G2
We compared the 7-core Google Tensor G6 (PowerVR CXTP-48-1536) with the older 8-core Tensor G2 (Mali-G710 MP7) SoC. Here you will find the pros and cons of each chip, technical specs, and comprehensive tests in benchmarks, like AnTuTu and Geekbench.
Review
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
Pros of Google Tensor G6
- Performs 2.6x better in floating-point computations
- Has 4 MB larger L3 cache size than the Tensor G2
- Has a smaller size transistor (3 versus 5 nm)
- Shows significantly better (up to 63%) AnTuTu 11 score β 1933K vs 1186K
- Higher GPU frequency (~52%)
- 44% higher CPU clock speed (4110 vs 2850 MHz)
- Supports 33% higher memory bandwidth (68.2 against 51.2 GB/s)
- Better instruction set architecture
Pros of Google Tensor G2
- Has 1 more cores
Benchmarks
Performance tests in popular benchmarksAnTuTu 11
| CPU | 876037 | 384056 |
| GPU | 288736 | 278383 |
| Memory | 304202 | 220709 |
| UX | 464561 | 303255 |
| Total score | 1933536 | 1186373 |
| Samples | [4 tests] | [54 tests] |
GeekBench 6
Single-Core Score
Multi-Core Score
| Asset compression | - | 149.9 MB/sec |
| HTML 5 Browser | - | 99.9 pages/sec |
| PDF Renderer | - | 110.2 Mpixels/sec |
| Image detection | - | 74.2 images/sec |
| HDR | - | 105.5 Mpixels/sec |
| Background blur | - | 11.7 images/sec |
| Photo processing | - | 35.1 images/sec |
| Ray tracing | - | 4.26 Mpixels/sec |
| Samples | 6 tests | 26 tests |
Compute Score (GPU)
| Background blur | - | 6.68 images/sec |
| Face detection | - | 3.96 images/sec |
| Horizon detection | - | 0.22 Gpixels/sec |
| Edge detection | - | 0.35 Gpixels/sec |
| Gaussian blur | - | 0.2 Gpixels/sec |
| Feature matching | - | 0.06 Gpixels/sec |
| Stereo matching | - | 11.5 Gpixels/sec |
| Particle physics | - | 972.6 FPS |
| API | - | Vulkan |
| Samples | 3 tests | 17 tests |
3DMark
3DMark Steel Nomad Light
| Score | - | 702 |
| Stability | - | 78% |
| Graphics test | - | 5 FPS |
3DMark Wild Life Extreme
| Score | - | 1821 |
| Stability | - | 77% |
| Graphics test | - | 10 FPS |
PCMark 3.0
PCMark 3.0
| 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
Google Tensor G6
| Date | Benchmark | Result |
|---|---|---|
| π 2026-08-23 (Roni) | Geekbench 6 CPU | 2888 / 7641 |
| π 2026-08-14 (Flxen) | Geekbench 6 CPU | 2755 / 7563 |
Google Tensor G2
| Date | Benchmark | Result |
|---|---|---|
| π 2026-10-27 (Artem buran) | AnTuTu 12 | 1515782 |
| π 2026-10-22 (Suke.) | Geekbench 7 CPU | 1298 / 3764 |
| π 2026-10-21 (Suke.) | AnTuTu 12 | 1376107 |
| π 2026-09-28 -> putkin_prosrochka59 | AnTuTu 12 | 1477460 |
| π 2026-09-09 -> Kimash333 | AnTuTu 11 | 1253847 |
Specifications
Full list of technical specifications of Tensor G6 and Tensor G2CPU
| Architecture | 1x 4.11 GHz β C1-Ultra 4x 3.38 GHz β C1-Pro 2x 2.65 GHz β C1-Pro |
2x 2.85 GHz β Cortex-X1 2x 2.35 GHz β Cortex-A78 4x 1.8 GHz β Cortex-A55 |
| Cores | 7 | 8 |
| Frequency | 4110 MHz | 2850 MHz |
| Instruction set | ARMv9.3-A | ARMv8.4-A |
| L3 cache | 8 MB | 4 MB |
| Process | 3 nanometers | 5 nanometers |
| TDP (Sustained Power Limit) | - | 7 W |
| Manufacturing | TSMC | Samsung |
Graphics
| GPU name | PowerVR CXTP-48-1536 | Mali-G710 MP7 |
| Architecture | - | Valhall 3rd gen |
| GPU frequency | 1286 MHz | 848 MHz |
| Pipelines | 6 | 7 |
| Shading units | 128 | 64 |
| Total shaders | 768 | 448 |
| FLOPS | 1975.3 Gigaflops | 759.8 Gigaflops |
| Vulkan version | 1.4 | 1.3 |
| OpenCL version | 3.0 | 2.0 |
AI Accelerator
| Neural processor (NPU) | Yes | Next-gen Tensor Processing Unit |
Memory
| Memory type | LPDDR5X | LPDDR5 |
| Memory frequency | 4266 MHz | 3200 MHz |
| Bus | 4x 16 Bit | 4x 16 Bit |
| Max bandwidth | 68.2 Gb/s | 51.2 Gb/s |
| Max size | 16 GB | 16 GB |
Multimedia (ISP)
| Storage type | UFS 4.0, UFS 4.1 | UFS 3.1 |
| Max display resolution | 3840 x 2400 | 3840 x 2160 |
| Max camera resolution | 1x 200MP | 1x 200MP, 2x 32MP |
| Video capture | 8K at 30FPS, 4K at 120FPS | 4K at 60FPS |
| Video playback | 8K at 30FPS, 4K at 120FPS | 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 | MediaTek M90 | Exynos 5300g |
| 4G support | - | LTE Cat. 24 |
| 5G support | Yes | Yes |
| Download speed | Up to 12000 Mbps | Up to 7350 Mbps |
| Upload speed | - | Up to 3670 Mbps |
| Wi-Fi | 7 | 6 |
| Bluetooth | 6.0 | 5.2 |
| Navigation | GPS, GLONASS, Beidou, Galileo, QZSS | GPS, GLONASS, Beidou, Galileo, QZSS, NAVIC |
Info
| Announced | August 2026 | October 2022 |
| Class | Flagship | Flagship |
| Model number | GS601 | GS201 (S5P9855) |
| Successor | - | - Google Tensor G6 |
Cast your vote
Total votes: 7