AMD Radeon 860M vs Intel Arc A380M Comparison

Where Each One Wins

The recorded data separates these two mobile graphics solutions primarily by their performance class and physical design. The AMD Radeon 860M holds an average benchmark score of 26401 across its Geekbench OpenCL and Vulkan tests, placing it in the 72nd percentile of all GPUs in the database. The Intel Arc A380M, by contrast, has no recorded benchmark scores, an average score of zero, and sits in the 50th percentile. That percentile gap alone indicates the AMD part occupies a distinctly higher performance tier in the database's ranking system.

The AMD Radeon 860M's wins are measured directly: it delivers 22759 in Geekbench OpenCL and 30043 in Geekbench Vulkan. These two scores bracket its average, with Vulkan showing a substantial advantage over OpenCL. The Intel Arc A380M has no comparable measurements, so its victories cannot be quantified from the database. What the Intel part does offer is a different physical and thermal envelope: it is an MXM Module with a 35 W TDP, while the AMD part is an IGP with a 15 W TDP. For systems where a modular, replaceable graphics card is required, the Intel part has a structural advantage that no benchmark score can override.

The use-case split is therefore clear from the data. The AMD Radeon 860M wins where integrated graphics performance and low power draw matter, particularly in slim portable devices where the GPU shares system memory. The Intel Arc A380M wins where a discrete, replaceable MXM module with dedicated GDDR6 memory is the requirement, even though its performance level is unmeasured in the database.

Architecture Differences

The two parts come from different architectural lineages. The AMD Radeon 860M uses RDNA 3.5, built on a 4 nm process at TSMC, and is part of the Navi III IGP generation for Strix Point Mobile, based on the Krackan Point chip. The Intel Arc A380M uses Xe-HPG, built on a 6 nm process also at TSMC, and belongs to the Alchemist generation for Arc 3 Mobile, based on the DG2-128 chip. The process node difference is significant: 4 nm versus 6 nm, which typically allows higher transistor density and lower power per transistor, though the database does not provide transistor counts for the AMD chip.

The Intel chip is fully specified in the database: 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9M per mm². The AMD chip's transistor count, die size, and density are all listed as unknown, so no direct comparison is possible on those metrics.

Core counts differ substantially. The AMD Radeon 860M has 512 shading units, 32 texture mapping units, 16 raster operation units, and 8 ray tracing cores. The Intel Arc A380M has 1024 shading units, 64 texture mapping units, 32 ROPs, and 8 ray tracing cores. The Intel part has exactly double the shading units, TMUs, and ROPs. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API-level feature parity is recorded.

Clock behavior diverges significantly. The AMD part has a base clock of 600 MHz and a boost clock of 3000 MHz, a fivefold boost range. The Intel part has a base clock of 1550 MHz and a boost clock of 2000 MHz, a much narrower range. Memory architecture is the other major split: the AMD part uses system shared memory with system-dependent bandwidth, while the Intel part has 6 GB of dedicated GDDR6 on a 96-bit bus with 186.0 GB/s of bandwidth and a 1937 MHz memory clock (15.5 Gbps effective).

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between these two parts, and the Intel Arc A380M has no individual benchmark scores recorded. The only quantifiable performance data belongs to the AMD Radeon 860M. Its Geekbench OpenCL score of 22759 and Geekbench Vulkan score of 30043 produce an average of 26401. That average places it just 0.1% below the NVIDIA GeForce MX550 (average 26421), 0.3% above the NVIDIA GeForce RTX 5060 (average 26331), 0.6% below the AMD Radeon RX 5700 XT 50th Anniversary (average 26553), and 1.1% below the NVIDIA RTX A4000 (average 26683).

These nearest-rival deltas are tight, all within a 1.4% band. The data positions the Radeon 860M as a mid-pack performer that trades blows with established discrete GPUs. The Vulkan score of 30043 is the stronger result, exceeding the OpenCL score of 22759 by roughly 32%, which suggests the RDNA 3.5 architecture responds well to Vulkan workloads. The Intel Arc A380M cannot be compared on these terms because the database has no scores for it. Its 50th percentile ranking is a database position, not a measured result.

The Intel part's theoretical throughput figures are recorded, though. It delivers 4.096 TFLOPS FP32 and 8.192 TFLOPS FP16 (2:1 ratio), plus a pixel rate of 64.00 GPixel/s and a texture rate of 128.0 GTexel/s. The AMD part delivers 3.072 TFLOPS FP32 and 3.072 TFLOPS FP16 (1:1 ratio), with a pixel rate of 48.00 GPixel/s and a texture rate of 96.00 GTexel/s. On paper, the Intel part exceeds the AMD part in every one of these throughput metrics, but no measured benchmark confirms how that translates to real workloads.

The Verdict

From the recorded data, the AMD Radeon 860M is the only one of the two with measurable performance. Its average benchmark score of 26401 and 72nd percentile ranking give it a concrete position in the database. The Intel Arc A380M has no scores, no average, and no rival comparisons, so its performance is entirely unverified. Any system builder choosing between these two based on the database would have to prioritize the AMD part for confirmed performance and the Intel part for its specific hardware attributes.

The AMD part fits into the IGP category with a 15 W TDP, PCIe 4.0 x8 interface, and no power connectors. It is a low-power solution for portable devices where the GPU is soldered to the motherboard. The Intel part is an MXM Module with a 35 W TDP and MXM-A (3.1) bus interface, meaning it is designed for modular laptops where the GPU can be replaced or upgraded. That form factor difference is the single most decisive factor for systems with modular GPU slots.

The Intel part does have dedicated memory, 6 GB of GDDR6 with 186.0 GB/s bandwidth, versus the AMD part's system-shared memory with system-dependent bandwidth. In workloads that are memory-bandwidth sensitive, the Intel part's dedicated VRAM is a structural advantage. But without benchmark scores, the database cannot confirm the magnitude of that advantage.

The AMD part also has a newer release date, 2025-02-28, versus the Intel part's 2023-01-23, and the AMD part is noted as a successor to Navi II IGP. Neither part has a launch MSRP recorded, so pricing is not a factor in this analysis.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon 860M has an average benchmark score of 26401. The Intel Arc A380M has no recorded benchmark scores and an average of zero.

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

A: It sits 0.1% below the NVIDIA GeForce MX550, 0.3% above the NVIDIA GeForce RTX 5060, 0.6% below the AMD Radeon RX 5700 XT 50th Anniversary, and 1.1% below the NVIDIA RTX A4000.

Q: What is the difference in memory configuration?

A: The AMD Radeon 860M uses system shared memory with system-dependent bandwidth. The Intel Arc A380M has 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth.

Q: Do both GPUs support ray tracing?

A: Yes, both have 8 ray tracing cores. The AMD Radeon 860M uses RDNA 3.5 architecture, and the Intel Arc A380M uses Xe-HPG architecture.

Q: What are the TDP ratings?

A: The AMD Radeon 860M has a TDP of 15 W and is an IGP. The Intel Arc A380M has a TDP of 35 W and is an MXM Module.

Q: Which GPU has more shading units?

A: The Intel Arc A380M has 1024 shading units, double the AMD Radeon 860M's 512 shading units. The Intel part also has 64 TMUs and 32 ROPs versus 32 TMUs and 16 ROPs.

Specification Differences

| Specification | AMD Radeon 860M | Intel Arc A380M |

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

| Architecture | RDNA 3.5 | Xe-HPG |

| Generation | Navi III IGP (Strix Point Mobile) | Alchemist (Arc 3 Mobile) |

| Chip | Krackan Point | DG2-128 |

| Process Node | 4 nm | 6 nm |

| Transistors | Unknown | 7,200 million |

| Die Size | Unknown | 157 mm² |

| Transistor Density | Not listed | 45.9M / mm² |

| Base Clock | 600 MHz | 1550 MHz |

| Boost Clock | 3000 MHz | 2000 MHz |

| Memory Size | System Shared | 6 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 96 bit |

| Memory Bandwidth | System Dependent | 186.0 GB/s |

| Memory Clock | System Shared | 1937 MHz (15.5 Gbps effective) |

| Shading Units | 512 | 1024 |

| TMUs | 32 | 64 |

| ROPs | 16 | 32 |

| RT Cores | 8 | 8 |

| FP32 | 3.072 TFLOPS | 4.096 TFLOPS |

| FP16 | 3.072 TFLOPS (1:1) | 8.192 TFLOPS (2:1) |

| Pixel Rate | 48.00 GPixel/s | 64.00 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 128.0 GTexel/s |

| TDP | 15 W | 35 W |

| Slot Width | IGP | MXM Module |

| Bus Interface | PCIe 4.0 x8 | MXM-A (3.1) |

| Power Connectors | None | Not listed |

| Release Date | 2025-02-28 | 2023-01-23 |

| Benchmark Average | 26401 | 0 |

| Percentile | 72 | 50 |