Arc A750 VS Arc B580
We are comparing the Arc A750 (Intel) with the Arc B580 (Intel). Scroll down to the pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Last Updated: September 14, 2026
Overall Comparison
KEY DIFFERENCES OF Arc A750 AND Arc B580
Here’s how Arc A750 and Arc B580 stack up against each other in their most impactful areas.
Reasons to consider the Arc A750
-
26% higher FP32 Compute (17.2 TFLOPS vs 13.67 TFLOPS)
-
12% more memory bandwidth (512 GB/s vs 456 GB/s)
-
33% higher Memory Bus Width (256 Bit vs 192 Bit)
-
Higher bandwidth bus link (PCIe 4.0 x16)
-
2.8× higher Tensor Cores (448 vs 160)
Reasons to consider the Arc B580
-
19% higher 4K Ultra FPS (38 vs 32)
-
14% higher 1440p Ultra FPS (67 vs 59)
-
14% higher 1080p Ultra FPS (90 vs 79)
-
11% higher Boost Clock (2670 MHz vs 2400 MHz)
-
18% higher 3DMark Time Spy score (14656 vs 12427)
SPECIFICATION TABLE COMPARISON OF Arc A750 AND Arc B580
Below is the detailed specification table comparing Arc A750 and Arc B580.
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 A750 | Arc B580 |
|---|---|---|
|
General Info
|
||
| GPU Name: | Arc A750 | Arc B580 |
| GPU Type: | Discrete | Discrete |
| Codename: | DG2-512 | BMG-G21 |
| Vendor: | Intel | Intel |
| Foundry: | TSMC | TSMC |
| Architecture: | Xe-HPG | Xe2-HPG |
| Generation: | Alchemist (Arc 7) | Battlemage (Arc 5) |
| Release Date: | October 12, 2022 | December 13, 2024 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x16 | PCIe 4.0 x8 |
| PCIe Version: | 4.0 | 4.0 |
| PCIe Lanes: | 16 | 8 |
| Process Size: | 6 nm | 5 nm |
| Transistors: | 21.7 billion | 19.6 billion |
| Density: | 53.4 MTr/mm² | 72.1 MTr/mm² |
| Die Size: | 406 mm² | 272 mm² |
| Board Length: | — | 272 mm |
| Board Width: | — | 45 mm |
| Board Height: | — | 115 mm |
| Total Graphics Power (TGP): | 225 W | 190 W |
|
Graphics Processor
|
||
| Compute Units: | 28 | 20 |
| Shading Units: | 3584 | 2560 |
| Texture Mapping Units (TMUs): | 224 | 160 |
| Render Output Units (ROPs): | 112 | 80 |
| Tensor Cores: | 448 | 160 |
| Ray Tracing Cores: | 28 | 20 |
| Base Clock: | 2050 MHz | 2670 MHz |
| Boost Clock: | 2400 MHz | 2670 MHz |
| L1 Cache: | — | 256 KB (per EU) |
| L2 Cache: | 16 MB | 18 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 268.8 GPixel/s | 213.6 GPixel/s |
| Texture Fill Rate: | 537.6 GTexel/s | 427.2 GTexel/s |
| FP32 Performance: | 17.20 TFLOPs | 13.67 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6 |
| Memory Size: | 8 GB | 12 GB |
| Memory Bus Width: | 256-bit | 192-bit |
| Memory Clock: | 2000 MHz | 2375 MHz |
| Effective Memory Speed: | 16000 Mbps | 19000 Mbps |
| Bandwidth: | 512 GB/s | 456 GB/s |
|
APIs
|
||
| DirectX: | 12.2 | 12.2 |
| Vulkan: | 1.4 | 1.4 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 3.0 |
| Ray Tracing: | 1 | 1 |
| DisplayPort: | 2.0 | 2.1 |
| HDMI: | 2.1 | 2.1a |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 79 | 90 |
| 1440p Ultra (FPS): | 59 | 67 |
| 4K Ultra (FPS): | 32 | 38 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 10857 | 11172 |
| Time Spy | 12427 | 14656 |
| Solar Bay | 45632 | 55492 |
| Port Royal | 6591 | 7909 |
| Fire Strike | 30560 | 36724 |
| Wild Life Extreme | 23654 | 28289 |
| Night Raid | 110821 | 123401 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 99280 | 111561 |
| Background Blur | 145.2 img/sec | 284.6 img/sec |
| Face Detection | 82 img/sec | 150 img/sec |
| Horizon Detection | 3.35 Gpixels/sec | 2.67 Gpixels/sec |
| Edge Detection | 5.01 Gpixels/sec | 5.22 Gpixels/sec |
| Gaussian Blur | 7.59 Gpixels/sec | 6.35 Gpixels/sec |
| Feature Matching | 0.81 Gpixels/sec | 1.18 Gpixels/sec |
| Stereo Matching | 462.4 Gpixels/sec | 397 Gpixels/sec |
| Particle Physics | 18623.1 | 15177.3 |
|
Passmark Graphics
|
||
| G3D Mark | 12620 | 15906 |
| G2D Mark | 737 | 700 |
| DirectX 11 | 73 | 126 |
| DirectX 12 | 70 | 77 |
| GPU Compute | 5307 | 7888 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 137.90 | 152.90 |
| Aztec Ruins Normal | 732.40 | 847.70 |
| Car Chase | 471.70 | 779.30 |
| Manhattan 3.1.1 (1440p) | 465.40 | 608.20 |
| T-Rex | 2668.40 | 2266.10 |
| Tessellation | 3725.60 | 4148.90 |
| ALU 2 | 3065.60 | 3674.60 |
| Driver Overhead 2 | 170.60 | 184.20 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 1924 | 1928 |
|
GeekBench 6 ML
|
||
| Single Precision | 12178 | 21661 |
| Half Precision | 12796 | 34463 |
| Quantized | 9086 | 14366 |
| Image Classification | 5475 | 10654 |
| Image Segmentation | 13781 | 18608 |
| Image Super Resolution | 11612 | 16715 |
| Face Detection | 18556 | 40348 |
| Pose Estimation | 58801 | 64494 |
| Text Classification | 824 | 3091 |
| Machine Translation | 2397 | 3530 |
| Object Detection | 6895 | 13690 |
| Depth Estimation | 22219 | 36797 |
| Style Transfer | 161148 | 197057 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 9414 | 9028 |
| 1440p Vulkan | 5690 | 6544 |
| 2160p Vulkan | 2871 | 3434 |
| 1080p OpenGL | 8547 | 8421 |
| 1440p OpenGL | 5580 | 6278 |
| 2160p OpenGL | 2701 | 3146 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF Arc A750 AND Arc B580
The charts below visualize how Arc A750 and Arc B580 stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Release Timeline of Arc A750 and Arc B580
Arc A750 was released 2 years, 2 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 A750
Arc B580
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 Arc B580 dominates overall compared to the Arc A750. Its strongest advantages are in Gaming Performance, AI & Machine Learning, Workstation and Energy Efficiency. They are still fairly close in Hardware Architecture.
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.