AMD Radeon 860M vs Intel Arc Graphics 64EU Mobile Comparison

The Verdict

The database places the AMD Radeon 860M in the 72nd percentile of all GPUs, with an average benchmark score of 26,401. The Intel Arc Graphics 64EU Mobile sits in the 50th percentile, with no recorded benchmark scores. The AMD part delivers 3.072 TFLOPS of FP32 compute against Intel's 1.792 TFLOPS, a 71% raw throughput advantage. The 860M also boosts to 3000 MHz versus 1750 MHz on the Intel part, with a 4 nm TSMC process versus Intel's 10 nm node.

For users choosing between these two integrated GPUs, the recorded data points clearly to the AMD Radeon 860M as the higher-performing option. Its nearest rivals in the database include the NVIDIA GeForce MX550 (average score 26,421, delta of -0.1%), the NVIDIA GeForce RTX 5060 (26,331, delta of 0.3%), and the AMD Radeon RX 5700 XT 50th Anniversary (26,553, delta of -0.6%). The Intel Arc Graphics 64EU Mobile has no comparable benchmark records, so it cannot be positioned against these figures.

The 860M's 512 shading units, 32 texture mapping units, and 16 render output units match the Intel part's counts exactly. However, AMD's clock speed advantage (3000 MHz boost versus 1750 MHz) and its 8 ray tracing cores (Intel lists none) create a significant performance gap. The AMD part's pixel rate of 48.00 GPixel/s and texture rate of 96.00 GTexel/s more than double Intel's rates of 28.00 GPixel/s and 56.00 GTexel/s. Any workload that depends on fill rate or texturing will show a decisive AMD advantage.

The Intel Arc Graphics 64EU Mobile does hold one advantage: its FP16 throughput. Intel lists 3.584 TFLOPS (2:1 ratio) versus AMD's 3.072 TFLOPS (1:1 ratio). This means Intel's part processes half-precision data faster than its FP32 rate, while AMD's FP16 matches its FP32 rate. Applications that leverage FP16 compute could see Intel perform closer to parity, but the lack of benchmark data prevents confirmation.

The 860M also supports DirectX 12 Ultimate (12_2), while Intel only lists DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The AMD part uses a PCIe 4.0 x8 interface, while Intel uses a Ring Bus. Neither part lists a launch MSRP in the database.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 860M has an average benchmark score of 26,401. The Intel Arc Graphics 64EU Mobile has no recorded average score (0 in the database).

Q: How does the AMD Radeon 860M compare to its nearest rivals?

A: The 860M sits within 1.1% of several discrete GPUs: it is 0.1% behind the NVIDIA GeForce MX550 (26,421), 0.3% ahead of the NVIDIA GeForce RTX 5060 (26,331), 0.6% behind the AMD Radeon RX 5700 XT 50th Anniversary (26,553), and 1.1% behind the NVIDIA RTX A4000 (26,683).

Q: What are the clock speed differences?

A: The AMD Radeon 860M has a base clock of 600 MHz and a boost clock of 3000 MHz. The Intel Arc Graphics 64EU Mobile has a base clock of 300 MHz and a boost clock of 1750 MHz.

Q: Do both GPUs have the same core counts?

A: Yes, both have 512 shading units, 32 TMUs, and 16 ROPs. However, the AMD Radeon 860M has 8 ray tracing cores, while the Intel Arc Graphics 64EU Mobile lists none.

Q: Which GPU has higher FP32 compute?

A: The AMD Radeon 860M delivers 3.072 TFLOPS of FP32, versus 1.792 TFLOPS for the Intel Arc Graphics 64EU Mobile.

Q: Which GPU supports higher DirectX features?

A: The AMD Radeon 860M supports DirectX 12 Ultimate (12_2), while the Intel Arc Graphics 64EU Mobile supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Architecture Differences

The AMD Radeon 860M uses the RDNA 3.5 architecture on a 4 nm TSMC process, part of the Krackan Point chip in the Navi III IGP generation (Strix Point Mobile). The Intel Arc Graphics 64EU Mobile uses the Xe-LPG architecture on a 10 nm Intel process, part of the Meteor Lake chip in the Arc Graphics-M generation. The manufacturing process difference is substantial: 4 nm versus 10 nm, which directly influences transistor density and power efficiency.

Both parts share identical shading unit counts (512), TMU counts (32), and ROP counts (16). The AMD part adds 8 ray tracing cores, a feature absent from the Intel specification. This gives the 860M hardware-accelerated ray tracing capability, while the Intel part relies on software-based approaches. The ray tracing cores also affect the DirectX feature level: AMD supports 12 Ultimate (12_2) which includes DXR and other RT-related features, while Intel only lists 12 (12_1).

The memory architecture is identical in concept: both use System Shared memory with System Dependent bandwidth. Neither has dedicated VRAM. This means actual memory performance depends entirely on the host system's RAM configuration, not on the GPU itself.

The FP16 implementation differs significantly. AMD lists 3.072 TFLOPS FP16 (1:1 ratio), meaning it processes half-precision at the same rate as FP32. Intel lists 3.584 TFLOPS FP16 (2:1 ratio), meaning it processes half-precision at twice its FP32 rate. This indicates Intel's Xe-LPG architecture has dedicated FP16 execution paths that AMD's RDNA 3.5 does not match.

The power envelope also differs: AMD lists 15 W TDP, while Intel lists 65 W TDP. This is a major architectural tradeoff, as the AMD part achieves higher FP32 throughput while consuming less power. The Intel part's higher TDP may allow for sustained clocks in some scenarios, but the recorded data shows it cannot match AMD's peak performance.

Both parts are classified as IGP (integrated graphics processor) with Portable Device Dependent display outputs. Neither has a dedicated power connector. The AMD part uses a PCIe 4.0 x8 bus interface, while Intel uses a Ring Bus, reflecting their different integration approaches in mobile chipsets.

Specification Differences

| Specification | AMD Radeon 860M | Intel Arc Graphics 64EU Mobile |

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

| Architecture | RDNA 3.5 | Xe-LPG |

| Chip | Krackan Point | Meteor Lake |

| Generation | Navi III IGP (Strix Point Mobile) | Arc Graphics-M (Meteor Lake) |

| Process Node | 4 nm (TSMC) | 10 nm (Intel) |

| Base Clock | 600 MHz | 300 MHz |

| Boost Clock | 3000 MHz | 1750 MHz |

| Shading Units | 512 | 512 |

| TMUs | 32 | 32 |

| ROPs | 16 | 16 |

| Ray Tracing Cores | 8 | None |

| Pixel Rate | 48.00 GPixel/s | 28.00 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 56.00 GTexel/s |

| FP32 | 3.072 TFLOPS | 1.792 TFLOPS |

| FP16 | 3.072 TFLOPS (1:1) | 3.584 TFLOPS (2:1) |

| TDP | 15 W | 65 W |

| Bus Interface | PCIe 4.0 x8 | Ring Bus |

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

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.4 |

| Release Date | 2025-02-28 | 2023-12-13 |

| Predecessor | Navi II IGP | HD Graphics-M |

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two GPUs, and the Intel Arc Graphics 64EU Mobile has no recorded benchmark scores at all. The AMD Radeon 860M, however, has two specific benchmark results: 22,759 in Geekbench OpenCL and 30,043 in Geekbench Vulkan. These scores contribute to its average of 26,401 and its 72nd percentile ranking.

Comparing the two parts requires using the 860M's recorded benchmarks against the Intel part's theoretical specifications. The 860M's Geekbench Vulkan score of 30,043 places it in a performance tier that includes discrete GPUs like the NVIDIA GeForce MX550 (26,421 average, -0.1% delta) and the NVIDIA RTX A4000 (26,683 average, -1.1% delta). The Intel part has no such data points.

The fill rate comparison is stark: the AMD part's 48.00 GPixel/s pixel rate and 96.00 GTexel/s texture rate are both 71% higher than Intel's 28.00 GPixel/s and 56.00 GTexel/s. This translates directly to performance in resolution-heavy workloads and texturing operations. The AMD part's FP32 throughput of 3.072 TFLOPS is 71% higher than Intel's 1.792 TFLOPS. These ratios match exactly, indicating the clock speed difference (3000 MHz versus 1750 MHz) is the primary driver of performance disparity.

The one area where Intel shows a numerical advantage is FP16 compute: 3.584 TFLOPS versus AMD's 3.072 TFLOPS, a 17% margin. However, without benchmark data for the Intel part, it is impossible to determine whether this translates into real-world application performance. The AMD part's FP16 at 1:1 ratio indicates its shader cores handle both FP32 and FP16 at the same rate, while Intel's 2:1 ratio allows double-rate FP16 execution.

The AMD part's 8 ray tracing cores provide a feature advantage in supported titles. The DirectX 12 Ultimate (12_2) support enables hardware ray tracing, mesh shaders, and variable rate shading, features that the Intel part's DirectX 12 (12_1) does not list. The higher TDP on the Intel part (65 W versus 15 W) suggests it may sustain performance under continuous load, but the recorded data shows no benchmark evidence to confirm this.

The release dates differ by over a year: the Intel part launched on 2023-12-13, while the AMD part launched on 2025-02-28. This generational gap explains the process node advantage (4 nm versus 10 nm) and the architectural improvements in RDNA 3.5 over Xe-LPG. The AMD part's predecessor is Navi II IGP, while Intel's predecessor is HD Graphics-M, indicating both are successors to older integrated graphics lines.

Given the available data, the AMD Radeon 860M is the clear performance leader. Its 3000 MHz boost clock, 3.072 TFLOPS FP32, 48.00 GPixel/s pixel rate, and 96.00 GTexel/s texture rate all exceed the Intel Arc Graphics 64EU Mobile's corresponding figures. The Intel part's only numerical win is FP16 throughput, and even that advantage is modest. The 860M's 72nd percentile ranking against all GPUs, supported by its nearest rival deltas (within 1.1% of several discrete GPUs), positions it as a genuinely capable integrated solution. The Intel part, with its 50th percentile and no recorded benchmarks, remains an unproven quantity in this comparison.