Arc B580 VS GeForce RTX 4070
We are comparing the Arc B580 (Intel) with the GeForce RTX 4070 (NVIDIA). Scroll down to the pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Last Updated: September 22, 2026
Overall Comparison
KEY DIFFERENCES OF Arc B580 AND GeForce RTX 4070
Here’s how Arc B580 and GeForce RTX 4070 stack up against each other in their most impactful areas.
Reasons to consider the Arc B580
-
8% higher Boost Clock (2670 MHz vs 2475 MHz)
-
Newer DisplayPort Version (2.1)
Reasons to consider the GeForce RTX 4070
-
63% higher 4K Ultra FPS (62 vs 38)
-
58% higher 1440p Ultra FPS (106 vs 67)
-
56% higher 1080p Ultra FPS (140 vs 90)
-
22% higher 3DMark Time Spy score (17811 vs 14656)
-
41% higher 3DMark Port Royal score (11154 vs 7909)
SPECIFICATION TABLE COMPARISON OF Arc B580 AND GeForce RTX 4070
Below is the detailed specification table comparing Arc B580 and GeForce RTX 4070.
Note: Highlighted specs mean that GPU wins that spec row.
If neither side is highlighted, it is a tie or there is not enough data for both specs.
| Specification | Arc B580 | GeForce RTX 4070 |
|---|---|---|
|
General Info
|
||
| GPU Name: | Arc B580 | GeForce RTX 4070 |
| GPU Type: | Discrete | Discrete |
| Codename: | BMG-G21 | AD104 |
| Vendor: | Intel | NVIDIA |
| Foundry: | TSMC | TSMC |
| Architecture: | Xe2-HPG | Ada Lovelace |
| Generation: | Battlemage (Arc 5) | GeForce 40 |
| Release Date: | December 13, 2024 | April 12, 2023 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x8 | PCIe 4.0 x16 |
| PCIe Version: | 4.0 | 4.0 |
| PCIe Lanes: | 8 | x16 |
| Process Size: | 5 nm | 5 nm |
| Transistors: | 19.6 billion | 35.8 billion |
| Density: | 72.1 MTr/mm² | 121.8 MTr/mm² |
| Die Size: | 272 mm² | 294 mm² |
| Board Length: | 272 mm | 240 mm |
| Board Width: | 45 mm | 40 mm |
| Board Height: | 115 mm | 110 mm |
| Total Graphics Power (TGP): | 190 W | 200 W |
|
Graphics Processor
|
||
| Compute Units: | 20 | 46 |
| Shading Units: | 2560 | 5888 |
| Texture Mapping Units (TMUs): | 160 | 184 |
| Render Output Units (ROPs): | 80 | 64 |
| Tensor Cores: | 160 | 184 |
| Ray Tracing Cores: | 20 | 46 |
| Base Clock: | 2670 MHz | 1920 MHz |
| Boost Clock: | 2670 MHz | 2475 MHz |
| L1 Cache: | 256 KB (per EU) | 128 KB per SM |
| L2 Cache: | 18 MB | 36 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 213.6 GPixel/s | 158.4 GPixel/s |
| Texture Fill Rate: | 427.2 GTexel/s | 455.4 GTexel/s |
| FP32 Performance: | 13.67 TFLOPs | 29.15 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6X |
| Memory Size: | 12 GB | 12 GB |
| Memory Bus Width: | 192-bit | 192-bit |
| Memory Clock: | 2375 MHz | 1313 MHz |
| Effective Memory Speed: | 19000 Mbps | 21000 Mbps |
| Bandwidth: | 456 GB/s | 504.2 GB/s |
|
APIs
|
||
| DirectX: | 12.2 | 12.2 |
| Vulkan: | 1.4 | 1.4 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 3.0 |
| CUDA: | — | 8.9 |
| Ray Tracing: | 1 | Yes |
| DLSS: | 0 | DLSS 3 |
| DisplayPort: | 2.1 | 1.4a |
| HDMI: | 2.1a | 2.1 |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 90 | 140 |
| 1440p Ultra (FPS): | 67 | 106 |
| 4K Ultra (FPS): | 38 | 62 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 11172 | 18093 |
| Time Spy | 14656 | 17811 |
| Solar Bay | 55492 | 82720 |
| Port Royal | 7909 | 11154 |
| Fire Strike | 36724 | 44071 |
| Wild Life Extreme | 28289 | 35487 |
| Night Raid | 123401 | 153448 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 111561 | 167522 |
| Background Blur | 284.6 img/sec | 233 |
| Face Detection | 150 img/sec | 141.7 |
| Horizon Detection | 2.67 Gpixels/sec | 6.62 |
| Edge Detection | 5.22 Gpixels/sec | 9.19 |
| Gaussian Blur | 6.35 Gpixels/sec | 9.2 |
| Feature Matching | 1.18 Gpixels/sec | 1.78 |
| Stereo Matching | 397 Gpixels/sec | 845.4 |
| Particle Physics | 15177.3 | 25043.9 |
|
Passmark Graphics
|
||
| G3D Mark | 15906 | 26914 |
| G2D Mark | 700 | 1168 |
| DirectX 11 | 126 | 243 |
| DirectX 12 | 77 | 103 |
| GPU Compute | 7888 | 14633 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 152.90 | 192.00 |
| Aztec Ruins Normal | 847.70 | 1039.00 |
| Car Chase | 779.30 | 900.00 |
| Manhattan 3.1.1 (1440p) | 608.20 | 761.20 |
| T-Rex | 2266.10 | 3848.10 |
| Tessellation | 4148.90 | 6200.70 |
| ALU 2 | 3674.60 | 5980.80 |
| Driver Overhead 2 | 184.20 | 296.70 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 1928 | 5425 |
|
GeekBench 6 ML
|
||
| Single Precision | 21661 | 27166 |
| Half Precision | 34463 | 40963 |
| Quantized | 14366 | 20332 |
| Image Classification | 10654 | 10246 |
| Image Segmentation | 18608 | 26153 |
| Image Super Resolution | 16715 | 32054 |
| Face Detection | 40348 | 51337 |
| Pose Estimation | 64494 | 124617 |
| Text Classification | 3091 | 3703 |
| Machine Translation | 3530 | 5484 |
| Object Detection | 13690 | 13134 |
| Depth Estimation | 36797 | 50548 |
| Style Transfer | 197057 | 263477 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 9028 | 12540 |
| 1440p Vulkan | 6544 | 8652 |
| 2160p Vulkan | 3434 | 3650 |
| 1080p OpenGL | 8421 | 11999 |
| 1440p OpenGL | 6278 | 9077 |
| 2160p OpenGL | 3146 | 4084 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF Arc B580 AND GeForce RTX 4070
The charts below visualize how Arc B580 and GeForce RTX 4070 stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Release Timeline of Arc B580 and GeForce RTX 4070
GeForce RTX 4070 was released 1 year, 8 months, 1 day earlier than Arc B580.
Value For Money Calculator
Prices use available launch or current data. Enter your own prices to see which GPU gives better value.
Arc B580
GeForce RTX 4070
Calculating...
Domain Score Summary
Scores are generated by Comparigon's scoring algorithm and are intended as a high-level guide. They may not map 1-to-1 with the individual spec-by-spec comparisons shown in the table.
Our Verdict
In conclusion, the GeForce RTX 4070 is slightly better overall compared to the Arc B580. It comes out ahead across every comparable key area.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.
Disclaimer: Specs, pricing, and benchmarks are sourced from official manufacturer data and verified test results. While we strive for precision, product details and pricing may change. Comparigon may earn an affiliate commission on qualifying purchases.