AMD Radeon RX 6700S vs Intel Arc A350M Comparison

Where Each One Wins

The benchmark data splits the two mobile GPUs along clear lines. The AMD Radeon RX 6700S wins every recorded head-to-head comparison in the database. In the Geekbench OpenCL test, the RX 6700S scores 70,965 against the Intel Arc A350M's 24,546, a delta of 65.4 percent in AMD's favor. The Geekbench Vulkan test shows a similar story: AMD scores 76,150, Intel scores 24,747, and the delta widens to 67.5 percent. Out of two head-to-head benchmarks, the Intel part claims zero wins.

The wins are not narrow margins. They are substantial gaps that place the two products in different performance tiers entirely. The RX 6700S also holds a larger benchmark footprint in the database, with results across 3DMark Steel Nomad DX12, Geekbench Metal, OpenCL, Vulkan, and multiple Passmark tests. The Arc A350M only has recorded Geekbench OpenCL and Vulkan results. This means the RX 6700S can be evaluated across a broader set of workload types, while the Arc A350M's profile is limited to two compute-oriented tests.

For use-case selection, the data points to the RX 6700S for any task that benefits from raw compute throughput in OpenCL or Vulkan. The Arc A350M, by contrast, does not appear competitive in either of the two recorded cross-GPU tests. Its percentile standing among all GPUs is 70, which is higher than the RX 6700S's 67, but that percentile reflects the Arc's position relative to a different pool of recorded scores, not its performance against this specific AMD part.

The RX 6700S's Passmark results add context for workload distribution. Its Passmark G3D score of 15,066 and GPU compute score of 5,990 indicate strength in general 3D rendering and compute tasks, while its DirectX 12 score of 58 and DirectX 11 score of 134 show that API-specific performance varies widely. The Arc A350M has no Passmark entries, so any comparison in those subcategories is impossible from the recorded data.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. Intel's Arc A350M uses the DG2-128 chip built on TSMC's 6 nm process, with 7,200 million transistors on a 157 mm² die. The architecture is Xe-HPG, and it belongs to the Alchemist generation of Arc 3 Mobile parts. AMD's RX 6700S uses the Navi 23 chip on TSMC's 7 nm process, with 11,060 million transistors on a 237 mm² die. The architecture is RDNA 2.0, part of the Navi Mobile RX 6000M generation. The transistor density is nearly identical: 45.9 million per mm² for Intel versus 46.7 million per mm² for AMD, but the AMD die is larger and carries roughly 54 percent more transistors.

The compute configuration differs sharply. The Arc A350M has 768 shading units, 48 texture mapping units, and 24 raster operations pipelines. The RX 6700S has 1,792 shading units, 112 TMUs, and 64 ROPs. That is more than double the shading units, TMUs, and ROPs on the AMD side. Ray tracing cores also diverge: Intel packs 6, AMD packs 28. Neither part lists tensor cores in the database, so AI acceleration comparisons are not possible from the recorded facts.

Clock behavior is another differentiator. The Arc A350M runs a base clock of 1150 MHz and boosts to 2200 MHz. The RX 6700S has a higher base clock at 1700 MHz but a lower boost at 2000 MHz, with a game clock of 1890 MHz recorded separately. The memory clocks are identical at 1750 MHz, translating to 14 Gbps effective on both. However, the memory subsystem is not the same. The Arc A350M uses 4 GB of GDDR6 on a 64-bit bus, yielding 112.0 GB/s of bandwidth. The RX 6700S uses 8 GB of GDDR6 on a 128-bit bus, doubling bandwidth to 224.0 GB/s.

Power and packaging also differ. The Arc A350M is rated at 25 W TDP, while the RX 6700S is rated at 80 W TDP. Both are listed as IGP slot width and use PCIe 4.0 x8 interfaces. The RX 6700S lists no power connectors, while the Arc A350M lists none either. Display outputs for both are portable device dependent. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 6700S has a recorded predecessor, Polaris Mobile, while the Arc A350M has no predecessor listed. Both are end-of-life products.

Head-to-Head Benchmarks

The only two benchmarks where both GPUs have recorded scores are Geekbench OpenCL and Geekbench Vulkan. In OpenCL, the RX 6700S scores 70,965 against the Arc A350M's 24,546. The delta is 65.4 percent in AMD's favor. In Vulkan, the RX 6700S scores 76,150 against the Arc A350M's 24,747, a delta of 67.5 percent. The AMD part is not just ahead; it is ahead by a margin that is consistent across both APIs. The Vulkan gap is slightly larger than the OpenCL gap, suggesting AMD's advantage holds or grows depending on the API layer.

To put the Arc A350M's score in context, its nearest rivals in the database include the AMD Radeon RX 590 at 24,744 (0.4 percent higher), the NVIDIA RTX A5000 Mobile at 24,763 (0.5 percent higher), the AMD Radeon RX 6600 XT at 24,442 (0.8 percent lower), and the NVIDIA GeForce GTX 1630 at 24,277 (1.5 percent lower). The Arc A350M's average benchmark score is 24,647. This places it in a cluster of mid-range desktop and mobile parts from previous generations, not in the performance class of the RX 6700S.

The RX 6700S's nearest rivals tell a different story. Its average benchmark score is 22,154, and its nearest rivals include the AMD Radeon RX 5700 at 22,170 (0.1 percent higher), the NVIDIA GeForce RTX 5060 Mobile at 22,435 (1.3 percent higher), the NVIDIA GeForce GTX 1060 6 GB at 21,856 (1.4 percent lower), and the AMD Radeon RX 7700 XT at 22,549 (1.7 percent higher). The RX 6700S sits in a higher absolute performance band than the Arc A350M, even though its percentile ranking among all GPUs (67) is slightly lower than the Arc's (70). That discrepancy is a reminder that percentile rankings are relative to a broad GPU pool, not a direct head-to-head comparison.

The RX 6700S also has results that the Arc A350M lacks entirely. Its 3DMark Steel Nomad DX12 score of 1,451, Geekbench Metal score of 72,864, and Passmark G3D score of 15,066 all describe performance in workloads where no Arc A350M data exists. The Passmark DirectX 9 score of 195 is the highest of its Passmark DirectX results, while DirectX 12 sits at 58 and DirectX 10 at 87. These figures suggest the RX 6700S's performance varies by API generation, but no comparable Intel numbers exist to draw a direct comparison.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc A350M has an average benchmark score of 24,647, while the AMD Radeon RX 6700S has an average of 22,154. However, these averages are computed from different sets of recorded tests, so they should not be read as a direct performance ranking.

Q: How large is the AMD Radeon RX 6700S's lead in Vulkan?

A: In Geekbench Vulkan, the RX 6700S scores 76,150 versus the Arc A350M's 24,747, a delta of 67.5 percent in AMD's favor.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the memory bandwidth difference?

A: The Arc A350M has 112.0 GB/s of bandwidth from 4 GB of GDDR6 on a 64-bit bus. The RX 6700S has 224.0 GB/s from 8 GB of GDDR6 on a 128-bit bus, exactly double.

Q: Which GPU has more ray tracing cores?

A: The AMD Radeon RX 6700S has 28 ray tracing cores. The Intel Arc A350M has 6.

Q: What is the TDP difference?

A: The Intel Arc A350M is rated at 25 W. The AMD Radeon RX 6700S is rated at 80 W.

Specification Differences

| Specification | Intel Arc A350M | AMD Radeon RX 6700S |

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

| Chip | DG2-128 | Navi 23 |

| Architecture | Xe-HPG | RDNA 2.0 |

| Generation | Alchemist (Arc 3 Mobile) | Navi Mobile (RX 6000M) |

| Process node | 6 nm | 7 nm |

| Transistors | 7,200 million | 11,060 million |

| Die size | 157 mm² | 237 mm² |

| Transistor density | 45.9M / mm² | 46.7M / mm² |

| Base clock | 1150 MHz | 1700 MHz |

| Boost clock | 2200 MHz | 2000 MHz |

| Game clock | Not listed | 1890 MHz |

| Memory size | 4 GB | 8 GB |

| Memory bus width | 64 bit | 128 bit |

| Memory bandwidth | 112.0 GB/s | 224.0 GB/s |

| Shading units | 768 | 1792 |

| TMUs | 48 | 112 |

| ROPs | 24 | 64 |

| Ray tracing cores | 6 | 28 |

| Pixel rate | 52.80 GPixel/s | 128.0 GPixel/s |

| Texture rate | 105.6 GTexel/s | 224.0 GTexel/s |

| FP32 | 3.379 TFLOPS | 7.168 TFLOPS |

| FP16 | 6.758 TFLOPS (2:1) | 14.34 TFLOPS (2:1) |

| TDP | 25 W | 80 W |

| Power connectors | Not listed | None |

| Predecessor | Not listed | Polaris Mobile |

| Release date | 2022-03-29 | 2022-01-03 |

The Verdict

The data supports a clear choice for most workloads. The AMD Radeon RX 6700S wins both recorded head-to-head benchmarks by margins of roughly two-thirds, and it does so with a larger memory pool, double the bandwidth, more than double the shading units, and a substantially higher compute throughput. Its FP32 rating of 7.168 TFLOPS is more than double the Arc A350M's 3.379 TFLOPS. Its pixel rate of 128.0 GPixel/s and texture rate of 224.0 GTexel/s also dwarf the Intel part's 52.80 GPixel/s and 105.6 GTexel/s. For any application that can use OpenCL or Vulkan, the RX 6700S is the stronger option.

The Intel Arc A350M does have one statistical advantage: a higher percentile ranking among all GPUs (70 versus 67) and a higher average benchmark score (24,647 versus 22,154). But those figures come from different test sets and do not reflect a direct comparison. When the two are measured against each other in the same tests, the Arc A350M trails by a wide margin.

The RX 6700S also benefits from a broader benchmark record, including 3DMark Steel Nomad DX12, Geekbench Metal, and multiple Passmark tests. This gives it a more complete performance profile in the database. The Arc A350M, with only two recorded tests, offers less evidence of its capabilities across different API and workload types.

The choice depends on what the recorded data can support. For a user prioritizing compute performance in OpenCL or Vulkan, or needing a larger frame buffer and higher memory bandwidth, the RX 6700S is the data-backed pick. For a user who values the lower 25 W TDP and the smaller die size, the Arc A350M has an efficiency argument, but the recorded benchmarks show no performance scenario where it beats the RX 6700S. The verdict from the database is unambiguous: the AMD Radeon RX 6700S is the faster GPU in every recorded head-to-head comparison, and the Intel Arc A350M does not hold a single recorded win.