AMD Radeon Pro Vega 16 vs Intel Arc B570 Comparison

Head-to-Head Benchmarks

The recorded benchmark data presents a stark contrast between these two GPUs. The Intel Arc B570 wins both head-to-head tests decisively. In Geekbench OpenCL, the Arc B570 scores 83,514 against the Radeon Pro Vega 16's 18,268. That is a 78.1% advantage for Intel. The Vulkan test tells a similar story: Intel posts 96,844 while AMD manages 21,832, a 77.5% gap. Both deltas are recorded from the AMD card's perspective, meaning the negative percentages reflect how far behind the Radeon Pro Vega 16 sits.

The Arc B570's average benchmark score across all recorded tests is 20,556. The Radeon Pro Vega 16's average is 23,250. Despite losing both direct comparisons, the AMD part holds a higher average because its three recorded benchmarks (Geekbench Metal at 29,650, OpenCL at 18,268, Vulkan at 21,832) are all fairly close to each other, while the Intel card's average is pulled down by low Passmark legacy scores. The Arc B570 records Passmark DirectX 9 at 164, DirectX 10 at 65, DirectX 11 at 118, and DirectX 12 at 72. Its Passmark G2D score is 661, its G3D score is 14,195, and its GPU compute score is 7,281. The lone 3DMark Steel Nomad DX12 result for Intel is 2,649.

Percentile rankings place the AMD part at the 68th percentile against all GPUs, while Intel sits at the 65th percentile. The Radeon Pro Vega 16's nearest rivals include the NVIDIA P106-100 with an average score of 23,249 (0% delta), the AMD Radeon RX 6600M at 23,273 (-0.1%), the AMD Radeon R9 M290X at 23,276 (-0.1%), and the AMD Radeon AI PRO R9700 at 23,315 (-0.3%). The Intel Arc B570's nearest rivals are the NVIDIA GeForce RTX 3070 Mobile at 20,534 (0.1% delta), the Intel Arc A750 at 20,582 (-0.1%), the NVIDIA Quadro M4000M at 20,480 (0.4%), and the AMD Radeon R9 M390X at 20,662 (-0.5%).

Where Each One Wins

The Radeon Pro Vega 16 wins in exactly one measurable category among the head-to-head tests, and that is the average benchmark score, where it leads 23,250 to 20,556. This is not a performance win in any single workload; it reflects the different benchmark suites recorded for each product. The AMD card's scores cluster between 18,268 and 29,650 across Metal, OpenCL, and Vulkan. The Intel card's scores range from 65 in Passmark DirectX 10 to 96,844 in Geekbench Vulkan. The wide spread on the Intel side includes several low legacy DirectX results that suppress its average.

For modern compute workloads, the Intel Arc B570 wins outright. The Geekbench OpenCL and Vulkan results are both more than four times higher than the AMD part's corresponding scores. The Arc B570 also records a 3DMark Steel Nomad DX12 score of 2,649, a test the AMD card has no recorded result for. The Intel card additionally supports DirectX 12 Ultimate (12_2), while the AMD part only reaches DirectX 12 (12_1). For Vulkan API support, Intel lists 1.4 against AMD's 1.3.

The Radeon Pro Vega 16's strengths lie in its integrated form factor and its portability characteristics. It is an IGP with no power connectors, draws 75 W, and uses PCIe 3.0 x16. The Intel card is a dual-slot discrete solution requiring a 1x 8-pin connector and a 450 W suggested power supply. The AMD part's display outputs are listed as portable device dependent, meaning it is designed for laptops where the display path is determined by the host system. The Intel card offers 1x HDMI 2.1a and 3x DisplayPort 2.1 outputs.

Architecture Differences

The Radeon Pro Vega 16 uses the Vega 12 chip built on GCN 5.0 architecture, fabricated by GlobalFoundries on a 14 nm process. The Intel Arc B570 uses the BMG-G21 chip on Xe2-HPG architecture, fabricated by TSMC on a 5 nm node. The process node difference is substantial: 14 nm versus 5 nm. Intel's chip packs 19,600 million transistors into a 272 mm² die, yielding a transistor density of 72.1 million per mm². The AMD chip's transistor count and die size are not recorded.

Memory configurations differ fundamentally. The AMD card uses 4 GB of HBM2 on a 1024-bit bus, delivering 307.2 GB/s bandwidth. The Intel card uses 10 GB of GDDR6 on a 160-bit bus, delivering 380.0 GB/s bandwidth. Despite the narrower bus, the Intel card's higher memory clock (2375 MHz, 19 Gbps effective versus 1200 MHz, 2.4 Gbps effective) gives it more bandwidth. The AMD card's memory clock is listed as 1200 MHz with 2.4 Gbps effective.

Compute resources favor Intel heavily. The Arc B570 has 2,304 shading units, 144 texture mapping units, and 80 raster operation units. The Radeon Pro Vega 16 has 1,024 shading units, 64 TMUs, and 32 ROPs. Intel also includes 18 ray tracing cores, while AMD lists none. The Intel card's pixel rate is 200.0 GPixel/s against 38.08 GPixel/s for AMD. Texture rate is 360.0 GTexel/s versus 76.16 GTexel/s. FP32 throughput is 11.52 TFLOPS for Intel and 2.437 TFLOPS for AMD. FP16 rates are 23.04 TFLOPS (2:1) and 4.874 TFLOPS (2:1) respectively.

Clock speeds tell a complementary story. The Intel card runs at 2500 MHz base and 2500 MHz boost. The AMD card runs at 815 MHz base and 1190 MHz boost. The combination of higher clocks, more execution units, and a newer architecture explains the benchmark gap. The Intel card uses PCIe 4.0 x8, while AMD uses PCIe 3.0 x16. The interface difference matters less for raw throughput in most workloads, but the newer standard offers higher per-lane bandwidth.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro Vega 16 has an average benchmark score of 23,250, while the Intel Arc B570 averages 20,556. However, this reflects different benchmark suites, not overall performance superiority.

Q: How large is the performance gap in Geekbench OpenCL?

A: The Intel Arc B570 scores 83,514 against the Radeon Pro Vega 16's 18,268, a 78.1% advantage for Intel.

Q: Does the Intel Arc B570 support ray tracing?

A: Yes, the Intel Arc B570 includes 18 ray tracing cores. The AMD Radeon Pro Vega 16 lists no ray tracing cores.

Q: What memory types do these cards use?

A: The Radeon Pro Vega 16 uses 4 GB of HBM2 on a 1024-bit bus. The Intel Arc B570 uses 10 GB of GDDR6 on a 160-bit bus.

Q: What DirectX versions do they support?

A: The Intel Arc B570 supports DirectX 12 Ultimate (12_2), while the AMD Radeon Pro Vega 16 supports DirectX 12 (12_1).

Q: What is the process node difference?

A: The AMD Radeon Pro Vega 16 is built on a 14 nm process by GlobalFoundries. The Intel Arc B570 is built on a 5 nm process by TSMC.

Specification Differences

| Specification | AMD Radeon Pro Vega 16 | Intel Arc B570 |

|---|---|---|

| Chip | Vega 12 | BMG-G21 |

| Architecture | GCN 5.0 | Xe2-HPG |

| Generation | Radeon Pro Mac (Vega Series) | Battlemage (Arc 5) |

| Process Node | 14 nm | 5 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | Not recorded | 19,600 million |

| Die Size | Not recorded | 272 mm² |

| Transistor Density | Not recorded | 72.1M / mm² |

| Base Clock | 815 MHz | 2500 MHz |

| Boost Clock | 1190 MHz | 2500 MHz |

| Memory Clock | 1200 MHz, 2.4 Gbps effective | 2375 MHz, 19 Gbps effective |

| Memory Size | 4 GB | 10 GB |

| Memory Type | HBM2 | GDDR6 |

| Memory Bus Width | 1024 bit | 160 bit |

| Memory Bandwidth | 307.2 GB/s | 380.0 GB/s |

| Shading Units | 1024 | 2304 |

| TMUs | 64 | 144 |

| ROPs | 32 | 80 |

| Ray Tracing Cores | None | 18 |

| Pixel Rate | 38.08 GPixel/s | 200.0 GPixel/s |

| Texture Rate | 76.16 GTexel/s | 360.0 GTexel/s |

| FP32 | 2.437 TFLOPS | 11.52 TFLOPS |

| FP16 | 4.874 TFLOPS (2:1) | 23.04 TFLOPS (2:1) |

| TDP | 75 W | 150 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 8-pin |

| Suggested PSU | Not recorded | 450 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1a, 3x DisplayPort 2.1 |

| DirectX | 12 (12_1) | 12 Ultimate (12_2) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.3 | 1.4 |

| Dimensions | Not recorded | 272 mm length, 115 mm height |

| Production Status | End-of-life | Active |

| Release Date | 2018-11-13 | 2025-01-15 |

| Predecessor | None | Alchemist |

| Launch MSRP | None | 219 USD |