AMD Radeon RX 6700S vs AMD Radeon RX 6800S Comparison

Head-to-Head Benchmarks

The benchmark database paints a clear picture: the AMD Radeon RX 6800S wins 10 of 11 head-to-head comparisons against the AMD Radeon RX 6700S, with the largest margins appearing in modern DirectX 12 workloads and compute-heavy tests.

The most decisive victory comes in the 3DMark Steel Nomad DX12 test, where the RX 6800S scores 1689 against the RX 6700S's 1451, a 16.4% advantage. This is a substantial gap for two mobile GPUs sharing the same Navi 23 chip and 7 nm TSMC process. The DirectX 12 PassMark test reinforces the pattern: 65 versus 58, a 12.1% delta in favor of the 6800S.

Geekbench results show a similar hierarchy. In the Metal API test, the RX 6800S scores 85256, which is 17% higher than the RX 6700S's 72864. The Vulkan test shows a smaller but still meaningful 6.7% edge (81272 versus 76150), while OpenCL narrows further to just 3.2% (73202 versus 70965). The pattern suggests that the 6800S scales better with newer, lower-level APIs, while the gap compresses under more traditional compute interfaces.

Older DirectX versions tell a more modest story. The RX 6800S leads by 4.6% in DirectX 10 (91 versus 87), 3.7% in DirectX 11 (139 versus 134), and 2.6% in DirectX 9 (200 versus 195). These legacy tests show the 6800S is faster, but the margins shrink as the API overhead dominates the raw shader throughput.

The one exception is the PassMark G2D test, where the RX 6700S scores 739 against the 6800S's 732, a 0.9% edge. This is a minor win for the 6700S in 2D graphics workloads, likely reflecting clock behavior or memory timing differences under low-load conditions. It does not offset the overall trend.

In the aggregate gaming metric, PassMark G3D, the 6800S posts 15908 versus 15066, a 5.6% lead. The compute-specific PassMark GPU Compute test shows a 2.6% advantage (6144 versus 5990). The average benchmark score across the entire suite is 24063 for the 6800S and 22154 for the 6700S, a difference of roughly 8.6%.

The 6800S also sits higher in the global percentile ranking: 69th percentile versus 67th for the 6700S. Its nearest rivals include the NVIDIA GeForce RTX 2080 SUPER (delta -0.4%) and the GTX 780 Ti (delta -0.7%), placing it in a performance tier that the 6700S does not reach. The 6700S, by contrast, trades blows with the AMD Radeon RX 5700 (delta -0.1%) and the NVIDIA GeForce RTX 5060 Mobile (delta -1.3%).

FAQ

Q: Which GPU wins in DirectX 12 Ultimate workloads?

A: The AMD Radeon RX 6800S. In the 3DMark Steel Nomad DX12 test, it scores 1689 versus 1451 for the RX 6700S, a 16.4% lead. The PassMark DirectX 12 test shows a 12.1% advantage (65 versus 58).

Q: How large is the memory bandwidth difference?

A: The RX 6800S offers 256.0 GB/s of bandwidth, while the RX 6700S provides 224.0 GB/s. Both use 8 GB of GDDR6 memory on a 128-bit bus, but the 6800S runs its memory at 2000 MHz (16 Gbps effective) versus 1750 MHz (14 Gbps effective) for the 6700S.

Q: Does the RX 6700S win any benchmark at all?

A: Yes, in the PassMark G2D test, the RX 6700S scores 739 against 732 for the RX 6800S, a 0.9% edge. This is the only head-to-head win for the 6700S out of 11 tests.

Q: What is the compute performance gap in raw FP32 throughput?

A: The RX 6800S delivers 8.602 TFLOPS of FP32 compute, while the RX 6700S delivers 7.168 TFLOPS. This translates to a theoretical 20% difference, though real-world compute benchmarks show a smaller 2.6% gap in PassMark GPU Compute (6144 versus 5990).

Q: How do these GPUs compare to desktop rivals?

A: The RX 6800S sits 0.4% below the NVIDIA GeForce RTX 2080 SUPER in average benchmark score, while the RX 6700S sits 0.1% below the AMD Radeon RX 5700. The 6800S also ranks 0.8% above the AMD Radeon RX 9070, showing it competes with a wide range of desktop parts.

Q: Are both GPUs based on the same silicon?

A: Yes, both use the Navi 23 chip with RDNA 2.0 architecture, built on TSMC's 7 nm process with 11,060 million transistors and a 237 mm² die size. The differences come from binning, clock speeds, and enabled compute units.

Where Each One Wins

The AMD Radeon RX 6800S is the clear choice for modern gaming workloads. Its 16.4% lead in 3DMark Steel Nomad DX12 and 12.1% edge in PassMark DirectX 12 indicate strong performance under current-generation APIs. The 17% advantage in Geekbench Metal also makes it the better option for macOS or Metal-based applications. For compute-heavy tasks like OpenCL, the 6800S still leads, though the margin narrows to 3.2%, suggesting that the extra shader cores matter less when memory-bound.

The AMD Radeon RX 6700S finds its niche in 2D desktop workloads, where it edges out the 6800S by 0.9% in PassMark G2D. This is a minor win, but it hints at slightly more efficient low-load behavior, possibly due to its lower 80 W TDP versus the 100 W TDP of the 6800S. For users prioritizing battery life or thermal headroom in a thin-and-light laptop, the 6700S may be the more practical pick despite lower peak performance.

For legacy DirectX 9 and DirectX 10 titles, the 6800S maintains a consistent but smaller lead (2.6% and 4.6% respectively), meaning older games will run fine on either GPU. The 6700S remains a capable option for users who mostly play esports titles or less demanding games, where the 5.6% G3D gap becomes less noticeable.

Specification Differences

The two GPUs share the same foundation but differ in several key specifications. The RX 6800S has 2048 shading units, 128 texture mapping units, and 32 ray tracing cores. The RX 6700S scales down to 1792 shading units, 112 TMUs, and 28 RT cores. Both retain 64 ROPs.

Clock speeds differ across the board. The 6800S runs at 1800 MHz base, 1975 MHz game, and 2100 MHz boost. The 6700S runs at 1700 MHz base, 1890 MHz game, and 2000 MHz boost. Memory clocks also differ: 2000 MHz (16 Gbps effective) for the 6800S versus 1750 MHz (14 Gbps effective) for the 6700S.

These clock and core differences produce measurable rate differences. The 6800S achieves 134.4 GPixel/s pixel rate and 268.8 GTexel/s texture rate. The 6700S delivers 128.0 GPixel/s and 224.0 GTexel/s. FP32 throughput is 8.602 TFLOPS versus 7.168 TFLOPS, and FP16 is 17.20 TFLOPS versus 14.34 TFLOPS (both at 2:1 ratio).

Power draw is another differentiator: the 6800S is rated at 100 W TDP, while the 6700S is rated at 80 W TDP. Both are IGP-class slot widths with no power connectors and portable-device-dependent display outputs. Neither has a suggested PSU rating. The 6800S's higher power budget likely explains its ability to sustain higher clocks and deliver better performance.

Architecture Differences

Both GPUs are built on the same Navi 23 chip using RDNA 2.0 architecture, fabricated on TSMC's 7 nm process. They share the same transistor count (11,060 million), die size (237 mm²), and transistor density (46.7M per mm²). The architecture is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and both use PCIe 4.0 x8 interfaces.

The differences are purely in configuration. The 6800S enables more of the Navi 23 silicon: 2048 shading units versus 1792, 128 TMUs versus 112, and 32 RT cores versus 28. This represents a roughly 14% increase in shader throughput, which aligns with the observed performance deltas in most tests.

Memory architecture is also configured differently. Both use 8 GB of GDDR6 on a 128-bit bus, but the 6800S runs at a higher effective speed (16 Gbps versus 14 Gbps), yielding 256.0 GB/s versus 224.0 GB/s. This 14.3% bandwidth advantage helps explain why the 6800S performs better in bandwidth-sensitive tests like 3DMark Steel Nomad.

The RDNA 2.0 architecture itself brings hardware ray tracing, variable rate shading, and mesh shaders. Both GPUs support these features, but the 6800S has more RT cores (32 versus 28), giving it a modest edge in ray-traced workloads. The 6800S also benefits from higher boost clocks (2100 MHz versus 2000 MHz), which, combined with more cores, compounds the performance advantage.

Both GPUs are end-of-life products from the Radeon RX 6000 series, released on the same date and part of the Navi Mobile (RX 6000M) generation. Neither has a successor listed in the database, and both trace their lineage to Polaris Mobile. The measured data shows that while the 6700S is a capable mobile GPU, the 6800S consistently outperforms it across nearly every benchmark, making it the stronger choice for demanding workloads.