AMD Radeon RX 6800S vs NVIDIA GeForce RTX 5060 Mobile Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6800S has a higher average benchmark score of 24063, while the NVIDIA GeForce RTX 5060 Mobile averages 22435. This places the RX 6800S in the 69th percentile of all GPUs, versus the 67th percentile for the RTX 5060 Mobile.

Q: How do the two compare in the 3DMark Steel Nomad DX12 test?

A: The RTX 5060 Mobile scores 3013.5, which is 44% higher than the RX 6800S’s 1689. This is the largest performance gap in the head-to-head benchmark set.

Q: What is the memory bandwidth difference?

A: The RTX 5060 Mobile offers 384.0 GB/s bandwidth with GDDR7 memory, while the RX 6800S provides 256.0 GB/s with GDDR6. Both have 8 GB capacity on a 128-bit bus.

Q: Which GPU has more shading units?

A: The RTX 5060 Mobile has 3328 shading units, compared to 2048 on the RX 6800S. However, the RX 6800S has higher clock speeds (1800 MHz base, 2100 MHz boost) versus the RTX 5060 Mobile’s 952 MHz base and 1455 MHz boost.

Q: What are the process node differences?

A: The RX 6800S uses a 7 nm process with 11,060 million transistors on a 237 mm² die. The RTX 5060 Mobile uses a 5 nm process with 21,900 million transistors on a smaller 181 mm² die.

Q: Which GPU wins more benchmark tests?

A: The RTX 5060 Mobile wins all 10 head-to-head benchmark comparisons. The RX 6800S does not win a single test in the comparative data.

Architecture Differences

The AMD Radeon RX 6800S and NVIDIA GeForce RTX 5060 Mobile represent two distinct architectural generations. The RX 6800S is built on RDNA 2.0, part of the Navi Mobile RX 6000M generation, using the Navi 23 chip. In contrast, the RTX 5060 Mobile employs Blackwell 2.0 architecture with the GB206 chip, belonging to the GeForce 50 Mobile generation.

The manufacturing processes differ significantly. The RX 6800S uses TSMC’s 7 nm node, packing 11,060 million transistors into a 237 mm² die, yielding a transistor density of 46.7 million per mm². The RTX 5060 Mobile uses a more advanced 5 nm process from TSMC, fitting 21,900 million transistors into a smaller 181 mm² die, with a density of 121.0 million per mm². This nearly doubles the transistor density.

Core configurations reveal a fundamental design split. The RX 6800S has 2048 shading units, 128 texture mapping units, 64 ROPs, and 32 ray tracing cores. The RTX 5060 Mobile has 3328 shading units (62.5% more), 104 TMUs, 48 ROPs, 26 ray tracing cores, and 104 tensor cores. The RX 6800S has no tensor cores listed, while the RTX 5060 Mobile includes them as a distinct feature.

Clock behavior also differs markedly. The RX 6800S runs at a base clock of 1800 MHz and boosts to 2100 MHz, with a game clock of 1975 MHz. The RTX 5060 Mobile has a much lower base clock of 952 MHz and a boost of 1455 MHz. Despite lower clocks, the RTX 5060 Mobile achieves higher FP32 performance at 9.684 TFLOPS versus 8.602 TFLOPS for the RX 6800S. The FP16 performance shows a sharp contrast: the RX 6800S delivers 17.20 TFLOPS (2:1 ratio), while the RTX 5060 Mobile provides 9.684 TFLOPS (1:1 ratio).

Memory architecture differs in type and bandwidth. The RX 6800S uses GDDR6 at 2000 MHz (16 Gbps effective), while the RTX 5060 Mobile uses GDDR7 at 1500 MHz (24 Gbps effective). Both have 8 GB capacity and a 128-bit bus, but the newer GDDR7 gives the RTX 5060 Mobile 384.0 GB/s versus 256.0 GB/s.

Power characteristics are notably different. The RX 6800S has a TDP of 100 W, while the RTX 5060 Mobile draws 45 W. The bus interface also differs: PCIe 4.0 x8 for the RX 6800S versus PCIe 5.0 x16 for the RTX 5060 Mobile. Both are IGP slot width with no power connectors and portable-device-dependent display outputs. The RX 6800S is end-of-life with a 2022 release date, while the RTX 5060 Mobile is active with a 2025 release date.

The Verdict

The data paints a clear picture for most workloads. The RTX 5060 Mobile wins every benchmark in the comparative set, making it the stronger choice for raw performance across DX10, DX11, DX12, and DX9 tests, as well as compute and API-agnostic workloads. The largest margin is a 44% lead in 3DMark Steel Nomad DX12, indicating a substantial advantage in modern DirectX 12 rendering.

However, the RX 6800S holds a higher average benchmark score (24063 versus 22435) and a higher percentile ranking (69th versus 67th). This suggests that in a broader benchmark database, the RX 6800S performs closer to other high-end GPUs. Its nearest rivals include the RTX 2080 SUPER (0.4% behind) and GTX 780 Ti (0.7% behind), while the RTX 5060 Mobile’s nearest rivals are the RX 7700 XT (0.5% behind) and RTX 4060 Mobile (1.3% behind).

For users prioritizing modern DX12 performance and compute workloads, the RTX 5060 Mobile is the data-supported choice. Its 45 W TDP also makes it markedly more power-efficient, which matters for mobile systems. The RX 6800S, despite losing every head-to-head test, remains competitive in legacy DirectX 9 (only 1.5% behind) and offers higher FP16 throughput, which could benefit specific workloads that leverage 2:1 FP16 processing.

Specification Differences

The two GPUs differ across nearly every specification category. The RX 6800S uses RDNA 2.0 architecture with the Navi 23 chip, while the RTX 5060 Mobile uses Blackwell 2.0 with GB206. Process nodes differ: 7 nm versus 5 nm. Transistor counts are 11,060 million versus 21,900 million, with die sizes of 237 mm² versus 181 mm². Transistor density is 46.7M/mm² versus 121.0M/mm².

Clock speeds: the RX 6800S has a base clock of 1800 MHz (versus 952 MHz) and a boost of 2100 MHz (versus 1455 MHz). The RX 6800S also has a game clock of 1975 MHz, which the RTX 5060 Mobile lacks. Memory clocks are 2000 MHz (16 Gbps effective) versus 1500 MHz (24 Gbps effective). Memory type is GDDR6 versus GDDR7.

Core counts: shading units are 2048 versus 3328, TMUs are 128 versus 104, ROPs are 64 versus 48, ray tracing cores are 32 versus 26, and tensor cores are absent versus 104. Pixel rate is 134.4 GPixel/s versus 69.84 GPixel/s. Texture rate is 268.8 GTexel/s versus 151.3 GTexel/s. FP32 is 8.602 TFLOPS versus 9.684 TFLOPS. FP16 is 17.20 TFLOPS (2:1) versus 9.684 TFLOPS (1:1).

TDP is 100 W versus 45 W. Bus interface is PCIe 4.0 x8 versus PCIe 5.0 x16. Release dates are January 2022 versus May 2025. Production status is end-of-life versus active. Predecessors are Polaris Mobile versus GeForce 40 Mobile.

Head-to-Head Benchmarks

The RTX 5060 Mobile dominates every direct comparison. The most decisive win is in 3DMark Steel Nomad DX12, where it scores 3013.5 against 1689, a 44% advantage. This test likely stresses modern DirectX 12 features where the newer Blackwell architecture excels.

Compute benchmarks show consistent but smaller gaps. In PassMark GPU Compute, the RTX 5060 Mobile scores 7607 versus 6144, a 19.2% lead. Geekbench OpenCL shows 96969 versus 73202, a 24.5% margin. Geekbench Vulkan shows 96451 versus 81272, a 15.7% advantage. These results indicate the RTX 5060 Mobile handles general-purpose GPU workloads better across multiple API frameworks.

DirectX legacy tests reveal a pattern. PassMark DirectX 10 has the RTX 5060 Mobile ahead by 23.5% (119 versus 91). DirectX 11 shows a 17.3% lead (168 versus 139). DirectX 12 has a 25.3% margin (87 versus 65). The smallest gap is in DirectX 9, where the RTX 5060 Mobile leads by only 1.5% (203 versus 200). This near-parity in DX9 suggests the RX 6800S retains strong legacy DirectX performance.

The PassMark G3D score, often used as an overall gaming indicator, shows the RTX 5060 Mobile at 18852 versus 15908, a 15.6% advantage. The 2D test (G2D) shows 876 versus 732, a 16.4% lead for the RTX 5060 Mobile.

Where Each One Wins

The RTX 5060 Mobile wins in every measured category, so the choice depends on which margins matter most. For modern DirectX 12 gaming and workloads, the RTX 5060 Mobile’s 44% lead in Steel Nomad DX12 is decisive. For compute-intensive tasks using OpenCL, its 24.5% advantage is substantial. Vulkan workloads show a 15.7% benefit. Across all DirectX versions, the RTX 5060 Mobile is ahead, though the DX9 margin (1.5%) is minimal.

The RX 6800S does not win any benchmark, but it has structural advantages. Its FP16 throughput of 17.20 TFLOPS is nearly double the RTX 5060 Mobile’s 9.684 TFLOPS, which could benefit applications that use FP16 for AI or compute acceleration. Its higher pixel rate (134.4 GPixel/s versus 69.84 GPixel/s) and texture rate (268.8 GTexel/s versus 151.3 GTexel/s) suggest stronger fill-rate performance, even if benchmark scores do not reflect wins. The RX 6800S also has a higher average benchmark score overall (24063 versus 22435), indicating that in a broader test suite, it may sit closer to other high-end GPUs.

Users prioritizing legacy DirectX 9 compatibility will find the RX 6800S nearly equivalent, with only a 1.5% deficit. Those needing lower power draw will prefer the RTX 5060 Mobile at 45 W versus 100 W. The RTX 5060 Mobile also offers tensor cores, which the RX 6800S lacks entirely, making it the only option for workloads that rely on tensor core acceleration.

For a mobile system where power efficiency, modern API performance, and compute versatility matter, the RTX 5060 Mobile is the data-backed winner. For scenarios where FP16 throughput or higher fill rates are critical, the RX 6800S retains specific advantages, though no benchmark in the comparative set confirms a practical win.