Apple M5 Pro GPU (20-core) vs GeForce RTX 5090
[ VERDICT ]
Winner: GeForce RTX 5090 (96/100)
GeForce RTX 5090 leads overall with a score of 96/100 compared to Apple M5 Pro GPU (20-core) (43/100), offering superior measured performance and technical specifications.
Benchmark Performance Comparison
Normalized Lab Scores| Benchmark | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Efficiency | 94.0 Excellent WINNER | 48.0 Poor |
| Gaming | 27.0 Poor | 100.0 Excellent WINNER |
Detailed Technical Specifications
3D Mark
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Solar Bay | 46865 | 236689 |
| Wild Life Extreme | 23737 | 108751 |
| Fire Strike | — | 87569 |
| Night Raid | — | 206648 |
| Port Royal | — | 38202 |
| Time Spy | — | 46873 |
API
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| DLSS | No | DLSS 4 |
| Ray Tracing | Yes | Yes |
| CUDA | — | 12.0 |
| DirectX | — | 12.2 |
| DisplayPort | — | 2.1b |
| OpenCL | — | 3.0 |
| OpenGL | — | 4.6 |
| Vulkan | — | 1.4 |
GeekBench 6 ML
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Backend | GPU | DirectML |
| Depth Estimation (Q) | 70908 | 85572 |
| Face Detection (HP) | 55699 | 114685 |
| Framework | Core ML | ONNX |
| Image Classification (SP) | 8870 | 18948 |
| Image Segmentation (HP) | 28795 | 55109 |
| Image Super Resolution (Q) | 34820 | 58478 |
| Machine Translation (HP) | 9102 | 8184 |
| Object Detection (SP) | 8163 | 27802 |
| Pose Estimation (Q) | 212347 | 344729 |
| Style Transfer (SP) | 152297 | 687080 |
| Text Classification (SP) | 3018 | 4464 |
GeekBench 6 OpenCL
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| API | OpenCL | OpenCL |
| Background Blur | 177.6 img/sec | 333 img/sec |
| Edge Detection | 4.45 Gpixels/sec | 33.7 Gpixels/sec |
| Face Detection | 114.5 img/sec | 298.5 img/sec |
| Feature Matching | 0.96 Gpixels/sec | 2.53 Gpixels/sec |
| Gaussian Blur | 4.59 Gpixels/sec | 34.5 Gpixels/sec |
| Horizon Detection | 3.19 Gpixels/sec | 21.7 Gpixels/sec |
| Particle Physics | 12529.9 FPS | 59146.9 FPS |
| Stereo Matching | 250.4 Gpixels/sec | 2850 Gpixels/sec |
General
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Architecture | Apple M GPU | Blackwell 2.0 |
| Build | Integrated | Discrete |
| Case | Laptop | Desktop |
| GPU Codename | Custom | GB202-300 |
| Purpose | Professional | Gaming |
| Recommended CPU | -Apple M5 Pro (18-Core)or above | -Intel Core Ultra 9 285Kor above |
| Released | March 3, 2026 | January 7, 2025 |
| Segment | Mid-range | High-end |
| Used in CPUs | -Apple M5 Pro (18-Core) | — |
| Vendor | Apple | Nvidia |
| Launch price (MSRP) | — | $1999 |
Graphics Processing Unit
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Boost Clock | 1620 MHz | 2407 MHz |
| Compute Units (Pipelines) | 320 | 170 |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Render Output Units (ROPs) | 80 | 176 |
| Shading Units | 2560 | 21760 |
| Texture Mapping Units (TMUs) | 160 | 680 |
| Base Clock | — | 2017 MHz |
| L1 Cache | — | 128KB per cluster |
| L2 Cache | — | 96MB shared |
| Ray-tracing Cores | — | 170 |
| Tensor Cores | — | 680 |
Memory
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Bus | 256-bit | 512-bit |
| ECC | No | No |
| Memory Clock | 9600 MHz | 1750 MHz |
| Memory Type | System Shared | GDDR7 |
| Effective Memory Speed | — | 28000 Mbps |
| Memory Size | — | 32 GB |
Physical
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Fabrication Process | 3 nm | 4 nm |
| Interface | Custom | PCIe 5.0 x16 |
| Manufacturing | TSMC | TSMC |
| Max. Temperature | 100°C | — |
| TGP | 28 W | 575 W |
| Transistor Count | 28 billion | 92.2 billion |
| Die Size | — | 750 mm² |
| Transistor Density | — | 122.93 MTr/mm² |
Raw Performance
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| Pixel Fill Rate | 130 GPixel/s | 424 GPixel/s |
| Texture Fill Rate | 259 GTexel/s | 1637 GTexel/s |
Games
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| 1080p High | — | 299 |
| 1080p Ultra | — | 254 |
| 1440p Ultra | — | 207 |
| 4K Ultra | — | 125 |
| CoD: Modern Warfare III | — | 334322260184 |
| Counter-Strike 2 | — | 36326520299 |
| Cyberpunk 2077 | — | 26123316077 |
| Far Cry 6 | — | 237202190121 |
| Forza Horizon 5 | — | 336247233187 |
| Ghost of Tsushima | — | 221185175113 |
| Hogwarts Legacy | — | 24919916697 |
| Margin of Error | — | Low |
| Shadow of the Tomb Raider | — | 329302238128 |
| The Witcher 3 | — | 364327237123 |
Passmark Graphics
| Specification | Apple M5 Pro GPU (20-core) | GeForce RTX 5090 |
|---|---|---|
| DirectX 11 | — | 341 FPS |
| DirectX 12 | — | 179 FPS |
| G2D Mark | — | 1410 |
| GPU Compute | — | 24360 Ops/s |
Looking for More Comparisons?
Browse all available head-to-head comparisons or select new devices in the comparison hub.