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 Gainward GeForce RTX 3090 Ti Phantom GS has 10752 shader units and these clock a maximum of 1.89 GHz which results in an FP32 computing power of 40.65 TFLOPS.

The PNY RTX A5500 has 10240 shader units and these clock at a maximum of 1.70 GHz and achieve an FP32 computing power of 34.71 TFLOPS.
In FP32 performance, the Gainward GeForce RTX 3090 Ti Phantom GS is 17 % faster than the PNY RTX A5500.
| GPU | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Based on | NVIDIA GeForce RTX 3090 Ti | NVIDIA RTX A5500 |
| GPU Chip | GA102-350-A1 | GA102 |
| Streaming Multiprocessors | 84 | 80 |
| Shader | 10752 | 10240 |
| Render Output Units | 112 | 96 |
| Texture Units | 336 | 320 |
| Raytracing Cores | 84 | 80 |
| Memory | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Memory Size | 24 GB | 24 GB |
| Memory Type | GDDR6X | GDDR6 |
| Memory Clock | 1.313 GHz | 2.000 GHz |
| Memory Speed | 21.0 Gbps | 16.0 Gbps |
| Memory bandwidth | 1,008 GB/s | 768 GB/s |
| Memory Interface | 384 bit | 384 bit |
| Clock Speeds | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Base Clock | 1.560 GHz | 1.170 GHz |
| Boost Clock | 1.890 GHz | 1.695 GHz |
| Overclocking | Yes | Yes |
| Thermal Design | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| TDP | 450 W | 230 W |
| Tjunction max | 92 °C | 93 °C |
| PCIe-Power | 1 x 16-Pin | 1 x 8-Pin |
| Cooler & Fans | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Fan-Type | Axial | Radial |
| Fan 1 | 3 x 100 mm | 1 x 65 mm |
| Cooler-Type | Air cooling | Air cooling |
| Noise (Idle) | 0 dB | -- |
| Connectivity | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Max. Displays | 4 | 4 |
| HDCP | 2.3 | 2.3 |
| HDMI | 1x HDMI 2.1 | -- |
| DisplayPort | 3x DP 1.4a | 4x DP 1.4a |
| Featureset | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Max. resolution | 7680x4320 | 7680x4320 |
| DirectX | 12_2 (Ultimate) | 12_2 (Ultimate) |
| Raytracing | Yes | Yes |
| DLSS / FSR | Yes | Yes |
| LED | Addressable LED | No LED lighting |
| Supported Video Codecs | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| h264 | Decode / Encode | Decode / Encode |
| h265 / HEVC | Decode / Encode | Decode / Encode |
| VP8 | Decode | Decode |
| VP9 | Decode | Decode |
| AV1 | Decode | Decode |
| Dimensions | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| Length | 314 mm | 267 mm |
| Height | 137 mm | 112 mm |
| Width (Slots) | 3 Slots | 2 Slots |
| SFF-Ready | No | No |
| Additional data | Gainward GeForce RTX 3090 Ti Phantom GS | PNY RTX A5500 |
|---|---|---|
| GPU Interface | PCIe 4.0 x 16 | PCIe 4.0 x 16 |
| Release date | Q1/2022 | Q1/2022 |
| Launch Price | 1,999 $ | 3,600 $ |
| Structure size | 8 nm | 8 nm |
| Part-no | 471056224-3208 | VCNRTXA5500-PB |
| Documents | data sheet | 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.