AMD Radeon RX 570 vs AMD Radeon RX 6800S Comparison

Head-to-Head Benchmarks

The benchmark data is unambiguous: the AMD Radeon RX 6800S wins every recorded head-to-head test against the AMD Radeon RX 570. The largest margin comes in Geekbench OpenCL, where the RX 6800S scores 73,202 against 32,084 for the RX 570, a 56.2% advantage. That is the widest gap in the comparison, and it reflects a fundamental shift in raw compute capability between the two architectures.

In Geekbench Metal, the RX 6800S posts 85,256 versus 39,349 for the RX 570, a 53.8% lead. The RX 6800S also dominates in Geekbench Vulkan with 81,272 against 42,752, a 47.4% advantage. The 3DMark Steel Nomad DX12 test shows a similar pattern: the RX 6800S scores 1,689 while the RX 570 manages only 880, a 47.9% deficit for the older card. Across all four tests, the RX 6800S wins by roughly half, indicating that the performance gap is consistent rather than workload-specific.

The average benchmark scores tell a slightly different story. The RX 570 has an average score of 28,766, while the RX 6800S averages 24,063. This discrepancy arises because the RX 6800S dataset includes additional Passmark tests with low scores (DirectX 9 at 200, DirectX 10 at 91, DirectX 11 at 139, DirectX 12 at 65, G2D at 732, G3D at 15,908, and GPU compute at 6,144), which drag its average downward. The RX 570 has no recorded Passmark results, so its average reflects only the four high-scoring Geekbench and 3DMark tests. When isolating the shared tests, the RX 6800S is consistently ahead by 47% to 56%.

The percentile rankings also diverge. The RX 570 sits at the 74th percentile among all GPUs, while the RX 6800S is at the 69th percentile. This is counterintuitive given the head-to-head results, but it reflects the broader benchmark pool: the RX 6800S is a mobile part with a wider range of test scores, including low DirectX legacy results, which pull its percentile down relative to the desktop-oriented RX 570.

Architecture Differences

The architectural gap between these two GPUs is generational. The RX 570 uses the Polaris 20 chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. The RX 6800S uses the Navi 23 chip with RDNA 2.0 architecture, built on a 7 nm process at TSMC. The node shrink is substantial: 14 nm to 7 nm, which allows the RX 6800S to pack 11,060 million transistors into a 237 mm² die, versus 5,700 million transistors in a 232 mm² die for the RX 570. Transistor density nearly doubles, from 24.6M per mm² to 46.7M per mm².

Both GPUs have 2,048 shading units and 128 texture mapping units, but the ROP count differs: the RX 570 has 32 ROPs, while the RX 6800S has 64. The RX 6800S also introduces 32 ray tracing cores, a feature entirely absent from the RX 570. The FP32 compute output is 8.602 TFLOPS for the RX 6800S versus 5.095 TFLOPS for the RX 570. The FP16 performance gap is even larger: the RX 6800S delivers 17.20 TFLOPS at a 2:1 ratio, while the RX 570 offers only 5.095 TFLOPS at a 1:1 ratio.

Memory architecture also diverges. The RX 570 uses 4 GB of GDDR5 on a 256 bit bus, delivering 224.0 GB/s of bandwidth. The RX 6800S uses 8 GB of GDDR6 on a 128 bit bus, achieving 256.0 GB/s. Despite the narrower bus, the faster GDDR6 memory (16 Gbps effective versus 7 Gbps effective) gives the RX 6800S a bandwidth advantage. The RX 570 runs at a base clock of 1168 MHz and boost of 1244 MHz, while the RX 6800S runs at 1800 MHz base and 2100 MHz boost, with a game clock of 1975 MHz.

API support differs as well. The RX 570 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RX 6800S supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The newer DirectX 12 Ultimate tier and Vulkan 1.4 support reflect the RDNA 2 feature set, including ray tracing and mesh shaders.

Where Each One Wins

The RX 6800S wins in every recorded head-to-head test, but the magnitude of the win varies by workload. In compute-heavy Geekbench OpenCL, the RX 6800S is 56.2% ahead, which is its best showing. This suggests that the RDNA 2 architecture's higher FP32 throughput (8.602 TFLOPS versus 5.095 TFLOPS) translates directly to compute performance. The RX 6800S also excels in Metal and Vulkan, with leads of 53.8% and 47.4% respectively, indicating strong driver optimization for modern graphics APIs.

The 3DMark Steel Nomad DX12 test shows a 47.9% lead for the RX 6800S, which is its smallest margin in the shared tests. This is still a decisive win, but it hints that the RX 570's GCN architecture holds up relatively better in traditional rasterization workloads than in compute-heavy tasks. The RX 6800S also benefits from twice the ROPs (64 versus 32), which boosts pixel throughput to 134.4 GPixel/s versus 39.81 GPixel/s for the RX 570.

The RX 570 does not win any recorded test. However, its 74th percentile ranking versus the RX 6800S's 69th percentile suggests that in the broader GPU landscape, the RX 570's consistent desktop-oriented scores place it higher relative to its peers. The RX 570 also has a lower power draw in terms of board design context: its 150 W TDP versus 100 W for the RX 6800S means the newer mobile part is more power-efficient per unit of performance, though the RX 570 is a dual-slot desktop card with a 6-pin connector, while the RX 6800S is an integrated mobile solution with no external power connectors.

Specification Differences

The following fields differ between the two GPUs:

| Specification | AMD Radeon RX 570 | AMD Radeon RX 6800S |

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

| Architecture | GCN 4.0 | RDNA 2.0 |

| Process node | 14 nm | 7 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 5,700 million | 11,060 million |

| Die size | 232 mm² | 237 mm² |

| Transistor density | 24.6M / mm² | 46.7M / mm² |

| Base clock | 1168 MHz | 1800 MHz |

| Boost clock | 1244 MHz | 2100 MHz |

| Game clock | None | 1975 MHz |

| Memory clock | 1750 MHz, 7 Gbps effective | 2000 MHz, 16 Gbps effective |

| Memory size | 4 GB | 8 GB |

| Memory type | GDDR5 | GDDR6 |

| Memory bus width | 256 bit | 128 bit |

| Memory bandwidth | 224.0 GB/s | 256.0 GB/s |

| ROPs | 32 | 64 |

| RT cores | None | 32 |

| Pixel rate | 39.81 GPixel/s | 134.4 GPixel/s |

| Texture rate | 159.2 GTexel/s | 268.8 GTexel/s |

| FP32 | 5.095 TFLOPS | 8.602 TFLOPS |

| FP16 | 5.095 TFLOPS (1:1) | 17.20 TFLOPS (2:1) |

| TDP | 150 W | 100 W |

| Slot width | Dual-slot | IGP |

| Power connectors | 1x 6-pin | None |

| Suggested PSU | 450 W | None |

| Bus interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display outputs | 1x DVI, 1x HDMI 2.0b, 3x DisplayPort 1.4a | Portable Device Dependent |

| DirectX | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan | 1.3 | 1.4 |

| Release date | 2017-04-17 | 2022-01-03 |

| Predecessor | Arctic Islands | Polaris Mobile |

| Successor | Vega | None |

| Launch MSRP | 169 USD | None |

FAQ

Q: Which GPU has more memory bandwidth?

A: The AMD Radeon RX 6800S has 256.0 GB/s, compared to 224.0 GB/s for the RX 570, despite using a narrower 128 bit bus versus 256 bit.

Q: Does the RX 6800S support ray tracing?

A: Yes, it has 32 ray tracing cores, while the RX 570 has none.

Q: What is the compute performance difference?

A: The RX 6800S delivers 8.602 TFLOPS FP32 versus 5.095 TFLOPS for the RX 570, and 17.20 TFLOPS FP16 versus 5.095 TFLOPS FP16.

Q: Which GPU is more power-efficient?

A: The RX 6800S has a 100 W TDP versus 150 W for the RX 570, making it the lower-power part despite higher performance.

Q: Are both GPUs end-of-life?

A: Yes, both are marked as end-of-life in the production status field.

Q: What is the difference in memory capacity?

A: The RX 6800S has 8 GB of GDDR6, while the RX 570 has 4 GB of GDDR5.

The Verdict

The data points to a clear choice for anyone comparing these two GPUs in isolation: the AMD Radeon RX 6800S outperforms the AMD Radeon RX 570 in every recorded benchmark, with margins ranging from 47.4% to 56.2%. The RX 6800S also offers double the memory capacity (8 GB versus 4 GB), higher bandwidth (256.0 GB/s versus 224.0 GB/s), more ROPs (64 versus 32), and ray tracing support, all while drawing 50 W less power (100 W versus 150 W). Its 7 nm process and RDNA 2 architecture are five years newer, and the benchmark results reflect that generational leap.

The RX 570's only statistical advantage is its higher percentile ranking (74th versus 69th) and its higher average benchmark score (28,766 versus 24,063), but those figures are skewed by the RX 6800S's inclusion of low-scoring Passmark tests. In the four tests where both GPUs have recorded scores, the RX 6800S wins each by a substantial margin. The RX 570 does have a higher launch MSRP of 169 USD, but that figure is historical and does not reflect current availability.

For users who prioritize raw compute, modern API support, and power efficiency, the RX 6800S is the superior option. For those constrained to a desktop slot with a 6-pin power connector and PCIe 3.0 x16 interface, the RX 570 remains a functional legacy part, but its performance ceiling is far lower. The RX 6800S, as a mobile integrated part, is designed for portable devices and offers no display outputs of its own, so it is not a direct drop-in replacement in a desktop build. The choice ultimately depends on the form factor: the RX 570 serves traditional desktop systems, while the RX 6800S serves high-performance laptops and compact devices where its 100 W TDP and lack of external power connectors are advantages.