Intel Arc B570 vs GeForce RTX 3060 Ti
VS
Intel Arc B570
BMG-G21
We compared two discrete desktop gaming GPUs: the Intel Arc B570 10 GB with 18 pipelines and 2304 shaders against the 4 years and 1 month older GeForce RTX 3060 Ti 8 GB that utilizes 38 pipelines and 4864 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the Intel Arc B570
- Manufactured using a more efficient 5 nm process technology
- Includes 2 GB more video memory
Reasons to consider the GeForce RTX 3060 Ti
- Performs better (up to 23%) in 3DMark Steel Nomad Lite
- Shows 33% higher average frame rate in modern games at QHD resolution – 77 vs 58 FPS
- 41% higher maximum theoretical performance (16.2 vs 11.5 TFLOPS)
- Supports Nvidia DLSS 2 technology
- Achieves 35% more points in the GeekBench 6 Compute test (115K vs 85K)
- Has 2.1x more shading units (4864 vs 2304)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 113 66 59 38 |
132 88 75 54 |
| The Witcher 3 | 126 110 80 40 |
152 128 92 47 |
| Counter-Strike 2 | 152 108 79 39 |
226 169 121 64 |
| Far Cry 6 | 97 88 67 34 |
114 103 83 47 |
| Hogwarts Legacy | 61 50 37 18 |
86 73 55 29 |
| CoD: Modern Warfare III | 65 67 47 28 |
107 99 72 47 |
| Ghost of Tsushima | 63 53 37 21 |
82 69 48 28 |
| Cyberpunk 2077 | 76 68 45 18 |
92 81 48 22 |
| Shadow of the Tomb Raider | 108 94 68 40 |
139 132 95 53 |
| 1080p High | 96 | 126 |
| 1080p Ultra | 78 | 105 |
| 1440p Ultra | 58 | 77 |
| 4K Ultra | 31 | 43 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 12564 | 11707 |
| Solar Bay | 48698 | 54429 |
| Port Royal | 6742 | 6971 |
| Fire Strike | 31264 | 29571 |
| Wild Life Extreme | 24446 | 24417 |
| Night Raid | 112674 | 109862 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 223.7 img/sec | 185.1 img/sec |
| Face Detection | 115.2 img/sec | 108.4 img/sec |
| Horizon Detection | 2.14 Gpixels/sec | 5.35 Gpixels/sec |
| Edge Detection | 3.95 Gpixels/sec | 7.17 Gpixels/sec |
| Gaussian Blur | 4.81 Gpixels/sec | 5.54 Gpixels/sec |
| Feature Matching | 0.93 Gpixels/sec | 1.15 Gpixels/sec |
| Stereo Matching | 294.6 Gpixels/sec | 478 Gpixels/sec |
| Particle Physics | 11270.6 FPS | 15183 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 629 | 989 |
| DirectX 11 | 111 FPS | 164 FPS |
| DirectX 12 | 70 FPS | 78 FPS |
| GPU Compute | 7368 Ops/s | 9865 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 9924 | 7384 |
| Image Segmentation (HP) | 20640 | 19320 |
| Image Super Resolution (Q) | 14215 | 16108 |
| Face Detection (HP) | 39045 | 34615 |
| Pose Estimation (Q) | 56787 | 74811 |
| Text Classification (SP) | 3028 | 2638 |
| Machine Translation (HP) | 3740 | 4136 |
| Object Detection (SP) | 13018 | 8718 |
| Depth Estimation (Q) | 31035 | 25946 |
| Style Transfer (SP) | 176206 | 153275 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Intel Arc B570 and GeForce RTX 3060 TiGeneral
| Vendor | Intel | Nvidia |
| Build | Discrete | Discrete |
| Released | December 3, 2024 | December 2, 2020 |
| Launch price (MSRP) | $219 | $399 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Generation 12.7 | Ampere |
| GPU Codename | BMG-G21 | GA104 |
| Rival Equivalent | - GeForce RTX 4060 | - Radeon RX 6700 XT |
| Successor | - | - GeForce RTX 5060 Ti (8GB) |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i5 12600K or above |
Desktop GPU rating (59th and 48th place)
Graphics Processing Unit
| Base Clock | 1700 MHz | 1410 MHz |
| Boost Clock | 2500 MHz | 1665 MHz |
| Shading Units | 2304 | 4864 |
| Texture Mapping Units (TMUs) | 144 | 152 |
| Render Output Units (ROPs) | 72 | 80 |
| Compute Units (Pipelines) | 18 | 38 |
| Tensor Cores | 144 | 152 |
| Ray-tracing Cores | 18 | 38 |
| L1 Cache | 256KB per cluster | 128KB per cluster |
| L2 Cache | 10MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 180 GPixel/s | 133 GPixel/s |
| Texture Fill Rate | 360 GTexel/s | 253 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 4.0 x16 |
| TGP | 150 W | 200 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 272 mm² | 392 mm² |
| Transistor Count | 19.6 billion | 17 billion |
| Transistor Density | 72.06 MTr/mm² | 43.37 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 10 GB | 8 GB |
| Memory Clock | 2375 MHz | 1750 MHz |
| Effective Memory Speed | 19000 Mbps | 14000 Mbps |
| Bus | 160-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | No | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 2 |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 7