AMD Radeon 860M vs Intel Arc A370M Comparison

Head-to-Head Benchmarks

The two GPUs split their benchmark results exactly evenly, with one win apiece across the two recorded tests. The decisive margin, however, is not symmetrical. In Geekbench OpenCL, the Intel Arc A370M posts a score of 29,676 against 22,759 for the AMD Radeon 860M, a 30.4% advantage. That is a substantial gap, one that places the Arc part firmly ahead in compute workloads that favor the OpenCL API. The AMD Radeon 860M counters in Geekbench Vulkan, scoring 30,043 versus 28,673 for the Intel part, a 4.6% lead. The Vulkan result is much closer, and it flips the overall picture: AMD wins the API that emphasizes modern graphics and cross-platform rendering, while Intel dominates the more general-purpose compute test.

Looking at the aggregate scores, the Intel Arc A370M averages 29,175 across its two benchmark entries, while the AMD Radeon 860M averages 26,401. That puts Intel ahead by roughly 10.5% on average, though the distribution of wins matters more than the simple average. The Intel part sits at the 74th percentile among all GPUs in the database, while the AMD part sits at the 72nd percentile. Both are mid-pack parts, but the Intel card edges out its rival in overall standing.

The nearest rival data reinforces the split. The Intel Arc A370M sits within 1% of the AMD Radeon RX 6800M (which trails by 1%), the AMD Radeon RX 470 (which trails by 0.6%), and essentially matches the AMD Radeon RX Vega M GH and AMD FirePro W8000 (both within 0.1%). The AMD Radeon 860M, by contrast, sits within 1.1% of the NVIDIA RTX A4000, within 0.6% of the AMD Radeon RX 5700 XT 50th Anniversary, and essentially matches the NVIDIA GeForce MX550 (0.1% difference). The NVIDIA GeForce RTX 5060 trails the AMD part by 0.3%. These comparisons show that both GPUs occupy a similar performance tier, but the Intel part has a higher ceiling in raw OpenCL throughput.

Where Each One Wins

The Intel Arc A370M wins the OpenCL benchmark by a wide margin, and that result points to its strength in general-purpose compute. OpenCL is often used for non-graphics workloads such as physics simulations, image processing, and certain productivity accelerations. A 30.4% lead in this test is not a marginal difference; it suggests the Intel architecture, with its Xe-HPG design and higher shading unit count, allocates resources more effectively for these parallel compute tasks. The Arc A370M also carries 4 GB of dedicated GDDR6 memory on a 64-bit bus, yielding 112.0 GB/s of bandwidth. Dedicated memory avoids the overhead of sharing system memory, which can matter in sustained compute loads.

The AMD Radeon 860M wins the Vulkan benchmark by 4.6%, a smaller but still meaningful margin. Vulkan is the API most associated with modern game engines and cross-platform rendering, so this result suggests the AMD part has an edge in graphics-heavy workloads that leverage Vulkan's low-level control. The Radeon 860M also benefits from a much higher boost clock: 3000 MHz versus 2050 MHz for the Intel part. Even with fewer shading units (512 versus 1024), the AMD GPU closes the gap in Vulkan, a sign that clock speed and architecture efficiency matter in this API. The Radeon 860M also uses system-shared memory, which in a laptop context can mean faster access to high-bandwidth system RAM depending on the platform, though the database records system bandwidth as system dependent.

For gaming and real-time graphics, the Vulkan win favors the AMD part. For compute-heavy tasks like rendering, encoding, or any workload that scales with raw ALU throughput, the Intel part's OpenCL dominance is the more relevant metric. The Intel part's FP32 throughput is 4.198 TFLOPS versus 3.072 TFLOPS for AMD, a 36.7% theoretical advantage, and its texture rate is 131.2 GTexel/s versus 96.00 GTexel/s. Those raw numbers align with the OpenCL result, where Intel's higher throughput translates directly into a higher score. The AMD part, meanwhile, posts a pixel rate of 48.00 GPixel/s versus 65.60 GPixel/s for Intel, so even in rasterization-related throughput, Intel holds the spec advantage. The Vulkan result, however, shows that specs alone do not decide every API.

The Verdict

The data paints a clear split verdict. Choose the Intel Arc A370M if the workload is dominated by OpenCL compute, because the 30.4% lead in that test is the largest margin recorded between the two parts. The Intel GPU also holds the higher average benchmark score (29,175 versus 26,401), the higher percentile ranking (74th versus 72nd), and the higher theoretical throughput figures across FP32, texture, and pixel rates. For users who prioritize raw compute in OpenCL-centric applications, the Intel part is the data-backed choice.

Choose the AMD Radeon 860M if Vulkan graphics performance is the priority. The 4.6% Vulkan win, combined with a 3000 MHz boost clock and a newer 4 nm process node, suggests this part is tuned for modern rendering APIs. The AMD part also draws less power on paper (15 W TDP versus 35 W for Intel), though the database does not record real-world power consumption. The Radeon 860M is also an active product, while the Arc A370M is end-of-life, which may matter for availability and driver support longevity, though the database does not track driver cadence. The AMD part's predecessor is listed as Navi II IGP, indicating a direct lineage within AMD's integrated GPU family.

For a balanced workload that mixes OpenCL and Vulkan, the Intel part wins on average score, but the margin is driven almost entirely by the OpenCL outlier. If Vulkan is the primary API, the AMD part is the safer pick. The database shows no third benchmark to break the tie, so the decision rests on which API matters more for the intended use case.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc A370M averages 29,175 across its recorded benchmarks, while the AMD Radeon 860M averages 26,401. That is a 10.5% advantage for Intel.

Q: How large is the OpenCL performance gap?

A: The Intel Arc A370M scores 29,676 in Geekbench OpenCL versus 22,759 for the AMD Radeon 860M, giving Intel a 30.4% lead in that test.

Q: Does the AMD Radeon 860M win any benchmark?

A: Yes, the AMD Radeon 860M wins Geekbench Vulkan with a score of 30,043 versus 28,673 for the Intel Arc A370M, a 4.6% margin.

Q: What are the nearest rivals for each GPU?

A: The Intel Arc A370M is within 1% of the AMD Radeon RX Vega M GH, AMD FirePro W8000, AMD Radeon RX 470, and AMD Radeon RX 6800M. The AMD Radeon 860M is within 1.1% of the NVIDIA GeForce MX550, NVIDIA GeForce RTX 5060, AMD Radeon RX 5700 XT 50th Anniversary, and NVIDIA RTX A4000.

Q: Which GPU has the higher boost clock?

A: The AMD Radeon 860M boosts to 3000 MHz, while the Intel Arc A370M boosts to 2050 MHz. The AMD part runs at a 950 MHz higher boost clock.

Q: What is the production status of each GPU?

A: The Intel Arc A370M is listed as end-of-life, while the AMD Radeon 860M is listed as active. The AMD part's release date is February 28, 2025, and the Intel part's release date is March 29, 2022.

Architecture Differences

The two GPUs come from different architectural families and process nodes. The Intel Arc A370M uses the DG2-128 chip built on Intel's Xe-HPG architecture, specifically the Alchemist generation for Arc 3 Mobile. It is fabricated on a 6 nm process at TSMC and contains 7,200 million transistors on a 157 mm² die, for a transistor density of 45.9 million per square millimeter. The AMD Radeon 860M uses the Krackan Point chip with RDNA 3.5 architecture, part of the Navi III IGP family for Strix Point Mobile. It is fabricated on a 4 nm process, also at TSMC, though its transistor count and die size are not recorded in the database.

The compute layouts differ significantly. The Intel part has 1024 shading units, 64 texture mapping units, and 32 render output units. The AMD part has 512 shading units, 32 TMUs, and 16 ROPs. Both have 8 ray tracing cores. The Intel part's FP32 throughput is 4.198 TFLOPS, while the AMD part reaches 3.072 TFLOPS. For FP16, Intel achieves 8.397 TFLOPS with a 2:1 ratio, while AMD achieves 3.072 TFLOPS with a 1:1 ratio. That means Intel has a much larger FP16 advantage, which could matter for workloads that use reduced precision.

Memory configurations are fundamentally different. The Intel Arc A370M has 4 GB of dedicated GDDR6 memory on a 64-bit bus, delivering 112.0 GB/s of bandwidth. The AMD Radeon 860M uses system-shared memory, with its type, bus width, and bandwidth all listed as system dependent. This is a key architectural distinction: dedicated memory guarantees a fixed bandwidth, while shared memory performance varies with the host platform's RAM configuration.

Clock behavior also differs. The Intel part has a base clock of 1550 MHz and a boost clock of 2050 MHz, with memory clocked at 1750 MHz (14 Gbps effective). The AMD part has a base clock of just 600 MHz but a boost clock of 3000 MHz, a much wider dynamic range. The AMD part's memory clock is listed as system shared, meaning it depends entirely on the host system's memory speed.

Power and interface details round out the differences. The Intel Arc A370M has a TDP of 35 W, while the AMD Radeon 860M has a TDP of 15 W. Both are integrated-class parts (IGP) with PCIe 4.0 x8 interfaces. The Intel part lists no power connectors, while the AMD part explicitly lists none. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs are listed as portable device dependent for both, meaning the actual ports depend on the laptop or device design. The Intel part has a release date of March 29, 2022, while the AMD part was released February 28, 2025, and the AMD part's predecessor is listed as Navi II IGP.