3DMark Benchmark (DirectX, Raytracing)
3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value.

The PNY GeForce GTX 1070 has 1920 shader units and these clock a maximum of 1.68 GHz which results in an FP32 computing power of 6.46 TFLOPS.

The GIGABYTE GeForce RTX 3080 Vision OC 10G has 8704 shader units and these clock at a maximum of 1.80 GHz and achieve an FP32 computing power of 31.34 TFLOPS.
In FP32 performance, the GIGABYTE GeForce RTX 3080 Vision OC 10G is 385 % faster than the PNY GeForce GTX 1070.
| GPU | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Based on | NVIDIA GeForce GTX 1070 | NVIDIA GeForce RTX 3080 |
| GPU Chip | GP104-200-A1 | GA102-200-K1-A1 |
| Streaming Multiprocessors | 15 | 68 |
| Shader | 1920 | 8704 |
| Render Output Units | 64 | 96 |
| Texture Units | 120 | 272 |
| Raytracing Cores | -- | 68 |
| Memory | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Memory Size | 8 GB | 10 GB |
| Memory Type | GDDR5 | GDDR6X |
| Memory Clock | 2.002 GHz | 1.188 GHz |
| Memory Speed | 8.0 Gbps | 19.0 Gbps |
| Memory bandwidth | 256 GB/s | 760 GB/s |
| Memory Interface | 256 bit | 320 bit |
| Clock Speeds | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Base Clock | 1.506 GHz | 1.440 GHz |
| Boost Clock | 1.683 GHz | 1.800 GHz |
| Overclocking | Yes | Yes |
| Thermal Design | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| TDP | 150 W | 320 W |
| TDP (up) | -- | 370 W |
| Tjunction max | 94 °C | 93 °C |
| PCIe-Power | 1 x 8-Pin | 2 x 8-Pin |
| Cooler & Fans | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Fan-Type | Axial | Axial |
| Fan 1 | 2 x 90 mm | 2 x 90 mm |
| Fan 2 | -- | 1 x 80 mm |
| Cooler-Type | Air cooling | Air cooling |
| Noise (Idle) | -- | 0 dB |
| Noise (Load) | -- | 42-45 dB |
| Connectivity | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Max. Displays | 4 | 4 |
| HDCP | 2.2 | 2.3 |
| HDMI | 1x HDMI 2.0b | 2x HDMI 2.1 |
| DisplayPort | 3x DP 1.4 | 3x DP 1.4a |
| DVI | 1 | -- |
| Featureset | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Max. resolution | 7680x4320 | 7680x4320 |
| DirectX | 12_1 | 12_2 (Ultimate) |
| Raytracing | No | Yes |
| DLSS / FSR | Yes | Yes |
| LED | No LED lighting | GIGABYTE RGB Fusion |
| Supported Video Codecs | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| h264 | Decode / Encode | Decode / Encode |
| h265 / HEVC | Decode / Encode | Decode / Encode |
| VP8 | Decode | Decode |
| VP9 | Decode | Decode |
| AV1 | No | Decode |
| Dimensions | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| Length | 252 mm | 320 mm |
| Height | 112 mm | 126 mm |
| Width | 42 mm | 55 mm |
| Width (Slots) | 2 Slots | 3 Slots |
| SFF-Ready | No | No |
| Additional data | PNY GeForce GTX 1070 | GIGABYTE GeForce RTX 3080 Vision OC 10G |
|---|---|---|
| GPU Interface | PCIe 3.0 x 16 | PCIe 4.0 x 16 |
| Release date | Q2/2016 | Q4/2020 |
| Launch Price | 379 $ | 749 $ |
| Structure size | 16 nm | 8 nm |
| Part-no | GF1070GTXCR8GEPB | GV-N3080VISION OC-10GD |
| Documents | -- | data sheet |
3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value.
Cyberpunk 2077 was developed by CD Projekt Red and is based on the development studio's own REDengine 4. Ray tracing is switched off in our benchmarks.
The Last of Us Part One is a game released by Sony in June 2013 exclusively for the Playstation and released for the PC in early 2023. The benchmark values here were determined at high details.
Battlefield 5 is a visually stunning game that is ideal as a graphics card benchmark. We test the game with maximum details on Windows 10.
Geekbench 6 is a cross-platform benchmark for main processors, which also carries out 3 different graphics benchmarks and outputs them in the form of a numerical value.
The theoretical computing power of the graphics card with single precision (32 bit) in TFLOPS indicates how many trillion FP32 floating point operations the graphics card (GPU) can perform per second.