Intel Arc B580 vs GeForce RTX 4070
VS
Intel Arc B580
BMG-G21
Nvidia GeForce RTX 4070
AD104
We compared two discrete desktop gaming GPUs: the Intel Arc B580 with 20 pipelines and 2560 shaders against the 1 year and 8 months older GeForce RTX 4070 that utilizes 46 pipelines and 5888 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
DeviceFacts Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 4070
- Performs significantly better (up to 62%) in 3DMark Steel Nomad Lite
- 2.1x higher maximum theoretical performance (29.1 vs 13.7 TFLOPS)
- Shows 58% higher average frame rate in modern games at QHD resolution – 106 vs 67 FPS
- Supports Nvidia DLSS 3 technology
- Achieves 50% more points in the GeekBench 6 Compute test (167K vs 111K)
- Has 2.3x more shading units (5888 vs 2560)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 123 78 67 51 |
172 115 102 79 |
| The Witcher 3 | 147 128 91 46 |
194 159 114 61 |
| Counter-Strike 2 | 162 116 83 40 |
272 205 149 81 |
| Far Cry 6 | 108 98 76 43 |
149 133 115 68 |
| Hogwarts Legacy | 71 57 44 26 |
117 97 77 39 |
| CoD: Modern Warfare III | 82 85 61 38 |
149 145 107 69 |
| Ghost of Tsushima | 72 61 42 25 |
106 88 72 43 |
| Cyberpunk 2077 | 90 82 55 26 |
129 119 75 37 |
| Shadow of the Tomb Raider | 124 107 83 43 |
211 190 145 80 |
| 1080p High | 109 | 167 |
| 1080p Ultra | 90 | 139 |
| 1440p Ultra | 67 | 106 |
| 4K Ultra | 38 | 62 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 14685 | 17799 |
| Solar Bay | 55846 | 82861 |
| Port Royal | 7939 | 11156 |
| Fire Strike | 36801 | 44067 |
| Wild Life Extreme | 28331 | 35472 |
| Night Raid | 125066 | 153385 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 284.6 img/sec | 233 img/sec |
| Face Detection | 150 img/sec | 141.7 img/sec |
| Horizon Detection | 2.67 Gpixels/sec | 6.62 Gpixels/sec |
| Edge Detection | 5.22 Gpixels/sec | 9.19 Gpixels/sec |
| Gaussian Blur | 6.35 Gpixels/sec | 9.2 Gpixels/sec |
| Feature Matching | 1.18 Gpixels/sec | 1.78 Gpixels/sec |
| Stereo Matching | 397 Gpixels/sec | 845.4 Gpixels/sec |
| Particle Physics | 15177.3 FPS | 25043.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 702 | 1165 |
| DirectX 11 | 125 FPS | 243 FPS |
| DirectX 12 | 78 FPS | 103 FPS |
| GPU Compute | 8018 Ops/s | 14561 Ops/s |
Blender
Blender GPU
Recent User Tests
Intel Arc B580
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-07-07 (Mike) | Geekbench 6 OpenCL | 113977 |
| 📘 2026-07-07 (Mike) | Steel Nomad Light | 11944 |
| 📘 2026-06-17 (Mike) | Geekbench 6 OpenCL | 103868 |
GeForce RTX 4070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-14 (kashitsu) | Cinebench 2024 | 18051 |
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) | 10654 | 10246 |
| Image Segmentation (HP) | 18608 | 26153 |
| Image Super Resolution (Q) | 16715 | 32054 |
| Face Detection (HP) | 40348 | 51337 |
| Pose Estimation (Q) | 64494 | 124617 |
| Text Classification (SP) | 3091 | 3703 |
| Machine Translation (HP) | 3530 | 5484 |
| Object Detection (SP) | 13690 | 13134 |
| Depth Estimation (Q) | 36797 | 50548 |
| Style Transfer (SP) | 197057 | 263477 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Intel Arc B580 and GeForce RTX 4070General
| Vendor | Intel | Nvidia |
| Build | Discrete | Discrete |
| Released | December 3, 2024 | April 13, 2023 |
| Launch price (MSRP) | $249 | $599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Generation 12.7 | Ada Lovelace |
| GPU Codename | BMG-G21 | AD104 |
| Rival Equivalent | - GeForce RTX 4060 | - Radeon RX 7900 XT |
| Successor | - | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i7 14700K or above |
Desktop GPU rating (50th and 30th place)
Graphics Processing Unit
| Base Clock | 1700 MHz | 1920 MHz |
| Boost Clock | 2670 MHz | 2475 MHz |
| Shading Units | 2560 | 5888 |
| Texture Mapping Units (TMUs) | 160 | 184 |
| Render Output Units (ROPs) | 80 | 64 |
| Compute Units (Pipelines) | 20 | 46 |
| Tensor Cores | 160 | 184 |
| Ray-tracing Cores | 20 | 46 |
| L1 Cache | 256KB per cluster | 128KB per cluster |
| L2 Cache | 12MB shared | 36MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 214 GPixel/s | 158 GPixel/s |
| Texture Fill Rate | 427 GTexel/s | 455 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 4.0 x16 |
| TGP | 190 W | 200 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 272 mm² | 294 mm² |
| Transistor Count | 19.6 billion | 35 billion |
| Transistor Density | 72.06 MTr/mm² | 119.05 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 12 GB | 12 GB |
| Memory Clock | 2375 MHz | 1313 MHz |
| Effective Memory Speed | 19000 Mbps | 21000 Mbps |
| Bus | 192-bit | 192-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 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 3 |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 17