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 RTX 4000 Ada has 6144 shader units and these clock a maximum of 2.18 GHz which results in an FP32 computing power of 26.73 TFLOPS.

The MSI GeForce RTX 4080 SUPER 16G EXPERT has 10240 shader units and these clock at a maximum of 2.63 GHz and achieve an FP32 computing power of 53.76 TFLOPS.
In FP32 performance, the MSI GeForce RTX 4080 SUPER 16G EXPERT is 101 % faster than the PNY RTX 4000 Ada.
| GPU | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Based on | NVIDIA RTX 4000 Ada | NVIDIA GeForce RTX 4080 SUPER |
| GPU Chip | AD104 | AD103-400-A1 |
| Streaming Multiprocessors | 48 | 80 |
| Shader | 6144 | 10240 |
| Render Output Units | 80 | 112 |
| Texture Units | 192 | 320 |
| Raytracing Cores | 48 | 80 |
| Memory | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Memory Size | 20 GB | 16 GB |
| Memory Type | GDDR6 | GDDR6X |
| Memory Clock | 1.750 GHz | 1.438 GHz |
| Memory Speed | 14.0 Gbps | 23.0 Gbps |
| Memory bandwidth | 360 GB/s | 736 GB/s |
| Memory Interface | 160 bit | 256 bit |
| Clock Speeds | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Base Clock | 1.500 GHz | 2.295 GHz |
| Boost Clock | 2.175 GHz | 2.625 GHz |
| Overclocking | Yes | Yes |
| Thermal Design | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| TDP | 130 W | 320 W |
| Tjunction max | Unknown | 90 °C |
| PCIe-Power | 1 x 16-Pin | 1 x 16-Pin |
| Cooler & Fans | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Fan-Type | Radial | Axial |
| Fan 1 | 1 x 70 mm | 2 x 120 mm |
| Cooler-Type | Air cooling | Air cooling |
| Noise (Idle) | 0 dB | 0 dB |
| Connectivity | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Max. Displays | 4 | 4 |
| HDCP | 2.3 | 2.3 |
| HDMI | -- | 1x HDMI 2.1a |
| DisplayPort | 4x DP 1.4a | 3x DP 1.4a |
| Featureset | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Max. resolution | 7680x4320 | 7680x4320 |
| DirectX | 12_2 (Ultimate) | 12_2 (Ultimate) |
| Raytracing | Yes | Yes |
| DLSS / FSR | Yes | Yes |
| LED | No LED lighting | No LED lighting |
| Supported Video Codecs | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| h264 | Decode / Encode | Decode / Encode |
| h265 / HEVC | Decode / Encode | Decode / Encode |
| VP8 | Decode | Decode |
| VP9 | Decode | Decode |
| AV1 | Decode / Encode | Decode |
| Dimensions | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| Length | 241 mm | 312 mm |
| Height | 112 mm | 141 mm |
| Width | -- | 61 mm |
| Width (Slots) | 1 Slots | 3 Slots |
| Weight | -- | 1,909 g |
| SFF-Ready | No | No |
| Additional data | PNY RTX 4000 Ada | MSI GeForce RTX 4080 SUPER 16G EXPERT |
|---|---|---|
| GPU Interface | PCIe 4.0 x 16 | PCIe 4.0 x 16 |
| Release date | Q3/2023 | Q1/2024 |
| Launch Price | 1,249 $ | 999 $ |
| Structure size | 5 nm | 5 nm |
| Part-no | VCNRTX4000ADA-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.