Intel Arc B580 vs Arc A770
VS
Intel Arc B580
BMG-G21
Intel Arc A770
DG2-512
We compared two discrete desktop gaming GPUs: the Intel Arc B580 12 GB with 20 pipelines and 2560 shaders against the 2 years and 2 months older Arc A770 16 GB that utilizes 4096 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 B580
- Manufactured using a more efficient 5 nm process technology
Reasons to consider the Intel Arc A770
- Performs slightly better (up to 13%) in 3DMark Steel Nomad Lite
- 44% higher maximum theoretical performance (19.7 vs 13.7 TFLOPS)
- Includes 4 GB more video memory
- Features 352 more tensor cores for effective ML and AI workloads
- Has 60% more shading units (4096 vs 2560)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 123 78 67 51 |
119 77 64 50 |
| The Witcher 3 | 147 128 91 46 |
147 126 91 46 |
| Counter-Strike 2 | 162 116 83 40 |
162 114 82 42 |
| Far Cry 6 | 108 98 76 43 |
108 98 75 41 |
| Hogwarts Legacy | 71 57 44 26 |
69 57 45 22 |
| CoD: Modern Warfare III | 82 85 61 38 |
80 81 58 37 |
| Ghost of Tsushima | 72 61 42 25 |
69 58 45 25 |
| Cyberpunk 2077 | 90 82 55 26 |
86 77 53 24 |
| Shadow of the Tomb Raider | 124 107 83 43 |
118 105 81 43 |
| 1080p High | 109 | 106 |
| 1080p Ultra | 90 | 88 |
| 1440p Ultra | 67 | 66 |
| 4K Ultra | 38 | 37 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 14685 | 13554 |
| Solar Bay | 55846 | 51133 |
| Port Royal | 7939 | 7236 |
| Fire Strike | 36801 | 34120 |
| Wild Life Extreme | 28331 | 26276 |
| Night Raid | 125066 | 122449 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 284.6 img/sec | 175 img/sec |
| Face Detection | 150 img/sec | 98 img/sec |
| Horizon Detection | 2.67 Gpixels/sec | 3.63 Gpixels/sec |
| Edge Detection | 5.22 Gpixels/sec | 5.51 Gpixels/sec |
| Gaussian Blur | 6.35 Gpixels/sec | 8.51 Gpixels/sec |
| Feature Matching | 1.18 Gpixels/sec | 0.89 Gpixels/sec |
| Stereo Matching | 397 Gpixels/sec | 492.6 Gpixels/sec |
| Particle Physics | 15177.3 FPS | 24819.2 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 702 | 760 |
| DirectX 11 | 126 FPS | 78 FPS |
| DirectX 12 | 78 FPS | 74 FPS |
| GPU Compute | 8003 Ops/s | 5820 Ops/s |
Blender
Blender GPU
Recent User Tests
Intel Arc B580
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-07-07 (Mike) | GeekBench | 113977 |
| 📘 2026-07-07 (Mike) | Steel Nomad Light | 11944 |
| 📘 2026-06-17 (Mike) | GeekBench | 103868 |
Intel Arc A770
No benchmark results yet
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 | 5750 |
| Image Segmentation (HP) | 18608 | 16175 |
| Image Super Resolution (Q) | 16715 | 12997 |
| Face Detection (HP) | 40348 | 21409 |
| Pose Estimation (Q) | 64494 | 67820 |
| Text Classification (SP) | 3091 | 849 |
| Machine Translation (HP) | 3530 | 2627 |
| Object Detection (SP) | 13690 | 7465 |
| Depth Estimation (Q) | 36797 | 24186 |
| Style Transfer (SP) | 197057 | 183238 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Intel Arc B580 and Arc A770General
| Vendor | Intel | Intel |
| Build | Discrete | Discrete |
| Released | December 3, 2024 | October 12, 2022 |
| Launch price (MSRP) | $249 | $329 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Generation 12.7 | Generation 12.7 |
| GPU Codename | BMG-G21 | DG2-512 |
| Rival Equivalent | - GeForce RTX 4060 | - GeForce RTX 3050 |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i5 12500 or above |
Desktop GPU rating (49th and 51st place)
Graphics Processing Unit
| Base Clock | 1700 MHz | 2100 MHz |
| Boost Clock | 2670 MHz | 2400 MHz |
| Shading Units | 2560 | 4096 |
| Texture Mapping Units (TMUs) | 160 | 256 |
| Render Output Units (ROPs) | 80 | 128 |
| Compute Units (Pipelines) | 20 | - |
| Tensor Cores | 160 | 512 |
| Ray-tracing Cores | 20 | 32 |
| L1 Cache | 256KB per cluster | - |
| L2 Cache | 12MB shared | 16MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 214 GPixel/s | 307 GPixel/s |
| Texture Fill Rate | 427 GTexel/s | 614 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 4.0 x16 |
| TGP | 190 W | 225 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 6 nm |
| Die Size | 272 mm² | 406 mm² |
| Transistor Count | 19.6 billion | 21 billion |
| Transistor Density | 72.06 MTr/mm² | 51.72 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 12 GB | 16 GB |
| Memory Clock | 2375 MHz | 2000 MHz |
| Effective Memory Speed | 19000 Mbps | 16000 Mbps |
| Bus | 192-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 | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | - |
Cast your vote
Total votes: 208