GPU Comparison

The AMD Radeon RX 6800 and Intel Arc A370M represent two vastly different approaches to graphics hardware, separated by target platform, power envelope, and performance tier. The data shows a 1-1 split in their head-to-head benchmark wins, but the magnitude of those wins is profoundly asymmetric, revealing a decisive performance gulf in most workloads. The RX 6800, a desktop flagship from the Radeon RX 6000 series, carries an average benchmark score of 30095 against the Arc A370M’s 29175, a modest 3.2% overall advantage that masks the extreme variance between individual tests. The Arc A370M, an entry-level mobile part from Intel’s Alchemist generation, manages to outperform the RX 6800 in one compute-oriented test by a substantial margin, while the RX 6800 delivers a crushing response in a modern graphics API benchmark.

Head-to-Head Benchmarks

The two GPUs were directly compared in only two benchmark suites: Geekbench OpenCL and Geekbench Vulkan. In the OpenCL compute test, the Intel Arc A370M scores 29676, defeating the AMD Radeon RX 6800’s 24508 by a delta of -17.4% (negative indicating the Intel part’s advantage). This is a remarkable outlier, as the Arc A370M is a 35 W mobile integrated graphics processor with 1024 shading units, while the RX 6800 is a 250 W desktop card with 3840 shading units. The result suggests that Intel’s Xe-HPG architecture handles this specific OpenCL workload with exceptional efficiency, or that the driver optimization for this test heavily favors the newer Intel design.

The Vulkan test tells a completely different story. The AMD Radeon RX 6800 scores 115107, which is 301.4% higher than the Intel Arc A370M’s 28673. This is not a marginal win; it is a four-fold performance advantage that reflects the fundamental disparity in raw graphics throughput between the two chips. The RX 6800’s 16.17 TFLOPS of FP32 compute and 512.0 GB/s of memory bandwidth completely overwhelm the Arc A370M’s 4.198 TFLOPS and 112.0 GB/s. While the OpenCL result might suggest the Arc A370M is competitive in compute tasks, the Vulkan benchmark demonstrates that in real-world graphics rendering, the RX 6800 operates in an entirely different performance class.

Looking at the broader benchmark landscape, the RX 6800’s average score of 30095 places it at the 75th percentile of all GPUs, while the Arc A370M’s 29175 sits at the 74th percentile. The RX 6800’s nearest rival is the AMD Radeon RX 6700, which scores 30433, a -1.1% delta, meaning the RX 6800 is actually slightly behind its sibling part. The NVIDIA GeForce RTX 3070 Ti trails by a mere 0.5% with a score of 29945, indicating the RX 6800 is firmly in the upper-midrange desktop tier. For the Arc A370M, its closest competitor is the AMD Radeon RX Vega M GH at 29197 (-0.1%), with the AMD Radeon RX 470 close behind at 28996 (0.6% ahead of the Intel part). Notably, the Arc A370M’s rivals include the AMD Radeon RX 6800M, a mobile flagship that it beats by 1%, showing that the Intel part is competitive within its mobile niche despite the massive gap to the desktop RX 6800.

Where Each One Wins

The AMD Radeon RX 6800 is the clear winner in modern graphics API workloads, as evidenced by its 301.4% advantage in Geekbench Vulkan. This test is a strong indicator of DirectX 12 and Vulkan gaming performance, suggesting the RX 6800 will dominate in contemporary titles that leverage these APIs. Its 16 GB of GDDR6 memory on a 256-bit bus provides 512.0 GB/s of bandwidth, enabling high-resolution texture streaming and complex scene rendering that the Arc A370M’s 4 GB frame buffer cannot accommodate. The RX 6800 also holds a commanding lead in pixel and texture throughput, with 202.1 GPixel/s and 505.2 GTexel/s, respectively, versus the Arc A370M’s 65.60 GPixel/s and 131.2 GTexel/s. For gamers or professionals running Vulkan-based applications, the RX 6800 is unequivocally the superior choice.

The Intel Arc A370M wins specifically in the Geekbench OpenCL compute test, a workload that measures general-purpose GPU compute rather than graphics rendering. Its 29676 score versus the RX 6800’s 24508 represents a 17.4% advantage, which is significant for tasks like machine learning inference, video encoding, or scientific simulations that rely heavily on OpenCL. However, this win is narrow in context: the Arc A370M only has two benchmark scores in its entire profile (OpenCL and Vulkan), while the RX 6800 has eleven diverse scores including PassMark DirectX tests and 3DMark Steel Nomad. The RX 6800’s PassMark G3D score of 22067 and GPU Compute score of 10864 indicate broad strength across many workloads, whereas the Arc A370M’s single strong result may be an anomaly rather than a trend.

For use-case selection, the RX 6800 is the choice for desktop gaming, VR, or any Vulkan/DirectX 12 workload where raw graphics power matters. Its 60 ray tracing cores and 96 ROPs provide hardware-accelerated ray tracing and high fill rates. The Arc A370M, despite its OpenCL victory, is a mobile integrated part with 8 ray tracing cores and 32 ROPs, making it suitable for lightweight laptops where power efficiency (35 W TDP) is paramount. Its 4 GB memory capacity limits it to 1080p gaming with reduced texture quality, while the RX 6800’s 16 GB allows for 4K gaming with maximum settings in most titles.

Architecture Differences

The architectural divide between these two GPUs is stark. The AMD Radeon RX 6800 uses the Navi 21 chip built on RDNA 2.0 architecture, manufactured on TSMC’s 7 nm process. This is a massive die at 520 mm² containing 26,800 million transistors, yielding a transistor density of 51.5M per mm². The Intel Arc A370M uses the DG2-128 chip based on Xe-HPG architecture, fabricated on TSMC’s 6 nm node. Its die is 157 mm² with 7,200 million transistors, giving a density of 45.9M per mm². The RX 6800’s die is over three times larger, reflecting its role as a high-end desktop part, while the Arc A370M’s smaller die is optimized for mobile integration.

Both architectures support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so feature-level API support is identical. However, the internal resources differ drastically. The RX 6800 has 3840 shading units, 240 TMUs, and 96 ROPs, while the Arc A370M has 1024 shading units, 64 TMUs, and 32 ROPs. The ray tracing capabilities also scale accordingly: 60 RT cores on the AMD part versus 8 on the Intel part. Neither GPU features tensor cores, so AI acceleration relies on standard shader compute. The RX 6800’s FP32 throughput is 16.17 TFLOPS, nearly four times the Arc A370M’s 4.198 TFLOPS, and its FP16 performance is 32.33 TFLOPS versus 8.397 TFLOPS, both using a 2:1 ratio.

The memory architecture is another key differentiator. The RX 6800 uses 16 GB of GDDR6 on a 256-bit bus, achieving 512.0 GB/s bandwidth. The Arc A370M uses 4 GB of GDDR6 on a 64-bit bus, delivering only 112.0 GB/s. This 4.5x bandwidth advantage for the AMD card is critical for texture-heavy workloads and high-resolution rendering. Clock speeds are similar: the RX 6800 has a base clock of 1700 MHz and boost of 2105 MHz, while the Arc A370M has a base of 1550 MHz and boost of 2050 MHz. The RX 6800’s game clock of 1815 MHz has no equivalent on the Intel part.

Specification Differences

The two GPUs differ in nearly every measurable specification. The RX 6800 is a dual-slot desktop card with 2x 8-pin power connectors and a 250 W TDP, requiring a 600 W suggested PSU. The Arc A370M is an integrated graphics processor (IGP) with a 35 W TDP, no power connectors, and no suggested PSU. The RX 6800 uses a PCIe 4.0 x16 interface, while the Arc A370M uses PCIe 4.0 x8. Display outputs also differ: the RX 6800 provides 1x HDMI 2.1, 2x DisplayPort 1.4a, and 1x USB Type-C, whereas the Arc A370M’s outputs are portable device dependent. The RX 6800 measures 267 mm in length, 120 mm in height, and 40 mm in width, while the Arc A370M has no listed dimensions. Memory clocks differ: the RX 6800 runs at 2000 MHz (16 Gbps effective), and the Arc A370M at 1750 MHz (14 Gbps effective). The RX 6800 has a launch MSRP of 579 USD for its 2020 release, while the Arc A370M has no launch MSRP data.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 6800 has an average benchmark score of 30095, which is 3.2% higher than the Intel Arc A370M’s 29175. The RX 6800 also ranks at the 75th percentile of all GPUs, versus the Arc A370M’s 74th percentile.

Q: How much faster is the RX 6800 in Vulkan performance?

A: In Geekbench Vulkan, the RX 6800 scores 115107 compared to the Arc A370M’s 28673, a 301.4% advantage. This represents a roughly four-fold performance difference in this graphics API workload.

Q: Does the Intel Arc A370M win any benchmark against the RX 6800?

A: Yes, the Arc A370M wins the Geekbench OpenCL test with a score of 29676 against the RX 6800’s 24508, a 17.4% advantage. This suggests the Intel part has a strength in certain general-purpose compute workloads.

Q: What are the memory specifications of each GPU?

A: The RX 6800 has 16 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth. The Arc A370M has 4 GB of GDDR6 on a 64-bit bus with 112.0 GB/s bandwidth. The RX 6800 also runs its memory at 2000 MHz (16 Gbps effective) versus 1750 MHz (14 Gbps effective) on the Intel part.

Q: How do their power requirements compare?

A: The RX 6800 has a 250 W TDP and requires a 600 W suggested PSU with 2x 8-pin power connectors. The Arc A370M has a 35 W TDP, no power connectors, and no suggested PSU, reflecting its integrated mobile design.

Q: Which GPU supports ray tracing, and how many RT cores does each have?

A: Both GPUs support ray tracing. The RX 6800 has 60 ray tracing cores, while the Arc A370M has 8 ray tracing cores. Both support DirectX 12 Ultimate (12_2), which includes hardware ray tracing requirements.