Quick/Comparisons
The Nvidia RTX 3000 Laptop (Ada) takes the lead in gaming with a score of 32, significantly outperforming the Intel Arc 3 A370M's 11.
The Nvidia RTX 3000 Laptop (Ada) excels in content creation with a score of 47, leaving the Intel Arc 3 A370M's 17 in its wake.
The Nvidia RTX 3000 Laptop (Ada) and Intel Arc 3 A370M are closely matched in AI & Machine Learning, with a score gap of just 23 points.
11 | Gaming | 32 |
17 | Workstation | 47 |
9 | AI/ML |
Compare with something else?
Compare Intel Arc 3 with another →32 |
78 | Energy Efficiency | 56 |
24 | Quick Comparison Final Score | 40 |
| ACM-G11 | Graphics Processor | AD106 |
| 1024 | Cores | 4608 |
| 64 / 32 | TMUs / ROPs | 144 / 48 |
| 377 | Blender GPU | 2931.27 |
| 29 | Forza Horizon 5 | 70 |
| 29 | The Witcher 3 | 98 |
| 28 | Counter-Strike 2 | 132 |
| 31 | Far Cry 6 | 83 |
| 12 | Hogwarts Legacy | 54 |
| 28 | Call of Duty | 73 |
| 17 | Ghost of Tsushima | 51 |
| 16 | Cyberpunk 2077 | 64 |
| 30 | Tomb Raider | 102 |
| 24 | Average FPS | 81 |
| 32 | 1080p High | 100 |
| 24 | 1080p Ultra | 81 |
| 17 | 1440p Ultra | 59 |
| 9 | 4K Ultra | 32 |
| Low | Margin of Error | High |
| 31544 | GB6 Compute Score | 119612 |
| 70.6 img/sec | Background Blur | 196.1 img/sec |
| 32.2 img/sec | Face Detection | 118.9 img/sec |
| 0.47 Gpixels/sec | Horizon Detection | 4.22 Gpixels/sec |
| 1.37 Gpixels/sec | Edge Detection | 5.54 Gpixels/sec |
| 2.15 Gpixels/sec | Gaussian Blur | 6.07 Gpixels/sec |
| 0.34 Gpixels/sec | Feature Matching | 1.4 Gpixels/sec |
| 138.8 Gpixels/sec | Stereo Matching | 573 Gpixels/sec |
| 7194.7 FPS | Particle Physics | 17661.3 FPS |
| OpenCL | API | OpenCL |
| 5115 | G3D Mark Score | 16040 |
| 724 | G2D Mark | 543 |
| 29 FPS | DirectX 11 | 140 FPS |
| 24 FPS | DirectX 12 | 80 FPS |
| 3014 Ops/s | GPU Compute | 5988 Ops/s |
| 5065 | GB6 ML Single Precision | 17574 |
| 5437 | GB6 ML Half Precision | 28903 |
| 3699 | GB6 ML Quantized | 13159 |
| 2580 | Image Classification (SP) | 7093 |
| 4626 | Image Segmentation (HP) | 14759 |
| 4983 | Image Super Resolution (Q) | 23321 |
| 5258 | Face Detection (HP) | 29211 |
| 16072 | Pose Estimation (Q) | 87917 |
| 669 | Text Classification (SP) | 3395 |
| 1373 | Machine Translation (HP) | 3464 |
| 3260 | Object Detection (SP) | 8181 |
| 9652 | Depth Estimation (Q) | 30150 |
| 47484 | Style Transfer (SP) | 167055 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 50-66 GPixel/s | Pixel Fill Rate | 56-104 GPixel/s |
| 99-131 GTexel/s | Texture Fill Rate | 168-311 GTexel/s |
| 3.2-4.2 TFLOPS | FLOPS (FP32) | 10.7-19.9 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 8 GB |
| 1500 MHz | Memory Clock | 2000 MHz |
| 12000 Mbps | Effective Memory Speed | 16000 Mbps |
| 64-bit | Bus | 128-bit |
| No | ECC | Yes |
| 96 GB/s | Memory Bandwidth | 256 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x16 |
| 35-50 W (configurable) | TGP | 35-140 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 6 nm | Fabrication Process | 5 nm |
| 157 mm² | Die Size | 188 mm² |
| 7.2 billion | Transistor Count | 22.9 billion |
| 45.86 MTr/mm² | Transistor Density | 121.81 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| — | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| 2 | DisplayPort | 1.4a |
| Intel | Vendor | Nvidia |
| Discrete | Build | Discrete |
| March 30, 2022 | Released | March 21, 2023 |
| Laptop | Case | Laptop |
| Generic | Purpose | Professional |
| Entry-level | Segment | Mid-range |
| Intel Xe-HPG | Architecture | Ada Lovelace |
| ACM-G11 | GPU Codename | AD106 |
| -Intel Core i5 1240Por above | Recommended CPU | -Intel Core Ultra 7 165Hor above |
| 2994 | Steel Nomad Lite Score | 9033 |
| 3438 | Time Spy | 8756 |
| 11630 | Solar Bay | 36647 |
| 386 | Port Royal | 5210 |
| 7938 | Fire Strike | 20658 |
| 5456 | Wild Life Extreme | 14961 |
| 36312 | Night Raid | 51077 |
| 1150-1550 MHz (configurable) | Base Clock | — |
| 1550-2050 MHz (configurable) | Boost Clock | 1165-2160 MHz (configurable) |
| 1024 | Shading Units | 4608 |
| 64 | Texture Mapping Units (TMUs) | 144 |
| 32 | Render Output Units (ROPs) | 48 |
| 128 | Compute Units (Pipelines) | 36 |
| — | Tensor Cores | 144 |
| 8 | Ray-tracing Cores | 36 |
| 1536KB shared | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |