AMD Radeon RX 6800M vs Intel Arc A370M Comparison

Intel Arc A370M and AMD Radeon RX 6800M are both end-of-life mobile GPUs, but they occupy completely different performance tiers. The benchmark data is unambiguous: the RX 6800M wins every head-to-head test by a massive margin, while the Arc A370M’s only statistical advantage is a negligible 1% higher aggregate score in the database’s average. This is not a close contest; it is a comparison between a low-power entry-level part and a high-end mobile flagship.

Head-to-Head Benchmarks

The two available direct comparisons show an overwhelming victory for the AMD Radeon RX 6800M. In Geekbench OpenCL, the RX 6800M scores 87,621 against the Arc A370M’s 29,676. That is a delta of -66.1% for the Intel part, meaning the AMD GPU delivers roughly three times the compute throughput in this API. The result is not close to being competitive; it is a categorical difference in raw processing capability.

The Geekbench Vulkan test tells the same story with an even larger gap. The RX 6800M reaches 94,766 points, while the Arc A370M manages only 28,673. This represents a -69.7% delta for the Intel GPU. In practical terms, the AMD part outperforms the Intel part by a factor of over 3.3x in Vulkan workloads. The Arc A370M’s architecture, while modern, simply cannot match the sheer execution resource count of the Navi 22 chip.

Looking at the aggregate average benchmark score, the Arc A370M actually posts 29,175 versus the RX 6800M’s 28,874. This gives the Intel GPU a 1% edge in the database’s averaged metric. However, this is misleading. The RX 6800M’s average is dragged down by its inclusion of a broader set of tests, including low-level DirectX and Passmark scores that are not present in the Arc A370M’s limited benchmark suite. The Arc A370M only has two recorded benchmarks (OpenCL and Vulkan), both of which it loses decisively. The 1% “win” is a statistical artifact, not a performance advantage.

In the nearest rival comparisons, the Arc A370M sits within 0.6% of the AMD Radeon RX 470 and 1% above the RX 6800M in average score. The RX 6800M, conversely, is within 0.4% of the RX 570 and 1% below the Arc A370M. This places both GPUs in the same 74th percentile of all GPUs, but the head-to-head data clarifies that this percentile ranking is driven by different benchmark subsets and does not reflect direct performance equivalence.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The AMD Radeon RX 6800M is significantly faster, scoring 87,621 versus the Intel Arc A370M’s 29,676, a -66.1% delta for the Intel part.

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

A: No. The Arc A370M loses both recorded head-to-head tests (OpenCL and Vulkan). Its only statistical edge is a 1% higher average benchmark score, which is based on a different and smaller set of tests.

Q: How do these GPUs compare in Vulkan performance?

A: The RX 6800M dominates, scoring 94,766 in Geekbench Vulkan versus 28,673 for the Arc A370M. This is a -69.7% delta, making the AMD GPU over three times faster.

Q: Are these GPUs in the same performance class?

A: No. Despite both being at the 74th percentile of all GPUs, the direct benchmark results show a massive gap. The RX 6800M is a high-end part with roughly three times the raw score in every shared test.

Q: What is the average benchmark score for each GPU?

A: The Intel Arc A370M has an average score of 29,175, while the AMD Radeon RX 6800M averages 28,874. The Intel GPU holds a 1% lead in this aggregate metric.

Q: Which GPU has more shading units?

A: The AMD Radeon RX 6800M has 2,560 shading units, while the Intel Arc A370M has 1,024. This 2.5x difference explains the large performance gap in compute-heavy workloads.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. Intel’s Arc A370M uses the Xe-HPG architecture on a 6 nm TSMC process, while AMD’s RX 6800M uses RDNA 2.0 on a 7 nm TSMC process. Despite the Intel part being on a smaller node, it has far fewer transistors: 7,200 million versus 17,200 million for the AMD chip. The die size reflects this, with Intel’s DG2-128 at 157 mm² and AMD’s Navi 22 at 335 mm². The transistor density is higher on the AMD chip at 51.3M per mm² versus 45.9M per mm² for Intel.

Core counts diverge dramatically. The RX 6800M has 2,560 shading units, 160 texture mapping units, and 64 render output units. The Arc A370M has 1,024 shading units, 64 TMUs, and 32 ROPs. Ray tracing cores follow suit: 40 for AMD versus 8 for Intel. This 5x difference in RT hardware is a major architectural gap.

Memory configurations are also vastly different. The RX 6800M features 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. The Arc A370M has only 4 GB of GDDR6 on a 64-bit bus, yielding 112.0 GB/s. Clock speeds favor AMD as well: the RX 6800M boosts to 2390 MHz with a base of 2116 MHz, while the Arc A370M boosts to 2050 MHz with a base of 1550 MHz.

Theoretical throughput numbers quantify the gap. The RX 6800M delivers 12.24 TFLOPS FP32 and 24.47 TFLOPS FP16, while the Arc A370M manages 4.198 TFLOPS FP32 and 8.397 TFLOPS FP16. Pixel and texture rates follow the same pattern: 153.0 GPixel/s and 382.4 GTexel/s for AMD versus 65.60 GPixel/s and 131.2 GTexel/s for Intel.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs, with the RX 6800M using PCIe 4.0 x16 and the Arc A370M using PCIe 4.0 x8. Power consumption is drastically different: the RX 6800M has a 145 W TDP, while the Arc A370M is rated at 35 W. This explains the form factor difference, though both are listed as IGP (integrated graphics package) for mobile devices.

The Verdict

The data supports only one conclusion: the AMD Radeon RX 6800M is the superior GPU by a wide margin. In every direct benchmark, it outperforms the Intel Arc A370M by 66% to 70%. The RX 6800M has more than double the shading units, 5x the ray tracing cores, 3x the memory capacity, and over 3x the memory bandwidth. It also has higher clock speeds, more transistors, and a larger die.

The Intel Arc A370M’s only statistical claim is a 1% higher average benchmark score, but this is based on a benchmark suite that lacks the extensive DirectX and Passmark tests the AMD part undergoes. When both GPUs run the same test, the AMD part wins comprehensively.

For users who need raw graphics performance, the RX 6800M is the clear choice. It delivers approximately 3x the compute throughput and 2.9x the FP32 performance. The Arc A370M is not competitive in any shared workload, and its lower TDP (35 W versus 145 W) is its only practical advantage, allowing for thinner and cooler laptop designs.

Specification Differences

The key differences between the two GPUs are stark:

• Process Node: 6 nm (Intel) vs 7 nm (AMD)
• Transistors: 7,200 million vs 17,200 million
• Die Size: 157 mm² vs 335 mm²
• Base Clock: 1550 MHz vs 2116 MHz
• Boost Clock: 2050 MHz vs 2390 MHz
• Game Clock: Not specified vs 2300 MHz
• Memory Size: 4 GB vs 12 GB
• Memory Bus: 64 bit vs 192 bit
• Memory Bandwidth: 112.0 GB/s vs 384.0 GB/s
• Shading Units: 1024 vs 2560
• TMUs: 64 vs 160
• ROPs: 32 vs 64
• Ray Tracing Cores: 8 vs 40
• Pixel Rate: 65.60 GPixel/s vs 153.0 GPixel/s
• Texture Rate: 131.2 GTexel/s vs 382.4 GTexel/s
• FP32 Performance: 4.198 TFLOPS vs 12.24 TFLOPS
• FP16 Performance: 8.397 TFLOPS vs 24.47 TFLOPS
• TDP: 35 W vs 145 W
• Bus Interface: PCIe 4.0 x8 vs PCIe 4.0 x16
• Release Date: 2022-03-29 vs 2021-05-30

Where Each One Wins

The AMD Radeon RX 6800M wins in every measurable performance category. It dominates in OpenCL and Vulkan benchmarks, with scores 2.9x to 3.3x higher. It has superior memory bandwidth (3.4x), higher pixel and texture fill rates (2.3x and 2.9x), and more than double the FP32 compute throughput. For gaming, ray tracing, or compute workloads, the RX 6800M is the only viable option between the two.

The Intel Arc A370M has no benchmark wins, but it does have a structural advantage in power efficiency. At 35 W versus 145 W, it consumes roughly a quarter of the power. This makes it suitable for ultra-thin laptops where thermal and battery constraints are paramount. It also has a smaller die (157 mm² vs 335 mm²), which could lower manufacturing costs per wafer, though this is not reflected in any pricing data.

For users prioritizing performance, the RX 6800M is the definitive choice. For users prioritizing portability and battery life, the Arc A370M offers a functional, if much slower, alternative. The data does not support any scenario where the Arc A370M provides better performance than the RX 6800M in a shared workload.