AMD Radeon RX 6800S vs NVIDIA GeForce RTX 3070 Mobile Comparison

Head-to-Head Benchmarks

The benchmark data presents a clear split, with the NVIDIA GeForce RTX 3070 Mobile and AMD Radeon RX 6800S each claiming five wins across the ten recorded tests. However, the magnitude of those victories is far from equal, and the overall average benchmark scores tell a different story than the raw win count.

The NVIDIA GeForce RTX 3070 Mobile takes the most decisive victories in the modern and compute-oriented workloads. In the 3DMark Steel Nomad DX12 test, the RTX 3070 Mobile scores 2380 against the RX 6800S's 1689, a commanding 29% lead. This is the largest delta in the entire comparison and signals a substantial advantage in recent DirectX 12 rendering workloads. The Geekbench OpenCL result reinforces this pattern, with the RTX 3070 Mobile posting 92939 versus 73202, a 21.2% advantage. Compute performance also favors NVIDIA in the Passmark GPU Compute test, where the RTX 3070 Mobile scores 6827 against 6144, a 10% lead. The Geekbench Vulkan result is closer but still favors NVIDIA, 86768 to 81272, a 6.3% advantage. The Passmark DirectX 10 test completes NVIDIA's wins, 113 to 91, a 19.5% margin.

The AMD Radeon RX 6800S counters with wins in several legacy and 2D-oriented tests, though the margins are generally smaller. The standout AMD victory is in Passmark DirectX 9, where the RX 6800S scores 200 against 160, a 25% lead. This is the second-largest delta in the comparison and suggests the RDNA 2.0 architecture retains strong performance in older DirectX titles. The Passmark G2D test also goes to AMD, 732 to 641, a 14.2% advantage. In the more modern Passmark DirectX 11 test, the RX 6800S edges out a narrow win, 139 to 138, a 0.7% margin. The Passmark DirectX 12 result is similarly close, 65 to 64, a 1.6% lead for AMD. Finally, the Passmark G3D test, which is a broad gaming-oriented metric, favors the RX 6800S by 3.9%, with scores of 15908 against 15309.

The average benchmark scores, however, favor AMD overall. The RX 6800S records an average benchmark score of 24063, while the RTX 3070 Mobile sits at 20534. This places the RX 6800S in the 69th percentile of all GPUs, compared to the 65th percentile for the RTX 3070 Mobile. The nearest rivals for the RX 6800S include the NVIDIA GeForce RTX 2080 SUPER, which is only 0.4% behind, and the AMD Radeon RX 9070, which is 0.8% ahead. The RTX 3070 Mobile, by contrast, sits near the Intel Arc B570 and Intel Arc A750, which are 0.1% and 0.2% behind respectively. The data indicates that while the RTX 3070 Mobile dominates specific modern workloads, the RX 6800S delivers a higher average score across the full benchmark suite.

Architecture Differences

The two mobile GPUs are built on fundamentally different architectures, processes, and chip designs. The AMD Radeon RX 6800S uses the Navi 23 chip with RDNA 2.0 architecture, manufactured on a 7 nm process at TSMC. The NVIDIA GeForce RTX 3070 Mobile uses the GA104 chip with Ampere architecture, manufactured on an 8 nm process at Samsung. The process node difference is significant: 7 nm versus 8 nm, which contributes to the RX 6800S having a smaller die size of 237 mm² compared to 392 mm² for the RTX 3070 Mobile. Transistor counts also differ substantially, with the RTX 3070 Mobile housing 17,400 million transistors versus 11,060 million for the RX 6800S. The transistor density is slightly higher on the AMD chip, at 46.7M per mm² versus 44.4M per mm².

Core configurations diverge sharply. The RTX 3070 Mobile packs 5120 shading units, 160 texture mapping units, and 80 raster operation pipelines. The RX 6800S has 2048 shading units, 128 TMUs, and 64 ROPs. Despite having fewer than half the shading units, the RX 6800S achieves a higher pixel rate of 134.4 GPixel/s versus 124.8 GPixel/s for the RTX 3070 Mobile, and a higher texture rate of 268.8 GTexel/s versus 249.6 GTexel/s. The FP32 compute figures tell the opposite story: the RTX 3070 Mobile delivers 15.97 TFLOPS against 8.602 TFLOPS for the RX 6800S. The FP16 results are notable, with the RX 6800S hitting 17.20 TFLOPS at a 2:1 ratio, while the RTX 3070 Mobile produces 15.97 TFLOPS at a 1:1 ratio.

Ray tracing and tensor hardware differ as well. The RX 6800S includes 32 ray tracing cores but does not report tensor cores. The RTX 3070 Mobile has 40 ray tracing cores and 160 tensor cores, giving it a distinct advantage in workloads that leverage these dedicated units. Memory configurations are identical in capacity at 8 GB of GDDR6, but the bus width differs: the RX 6800S uses a 128-bit bus with 256.0 GB/s of bandwidth, while the RTX 3070 Mobile uses a 256-bit bus with 448.0 GB/s of bandwidth. The memory clocks also differ, with the RX 6800S running at 16 Gbps effective and the RTX 3070 Mobile at 14 Gbps effective, though the wider bus on the NVIDIA part yields much higher total bandwidth.

Power targets are distinct, with the RX 6800S rated at 100 W and the RTX 3070 Mobile at 115 W. The bus interface also differs: PCIe 4.0 x8 for AMD versus PCIe 4.0 x16 for NVIDIA. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 6800S is listed as an IGP form factor with no power connectors, while the RTX 3070 Mobile also has no power connectors listed. Both GPUs are end-of-life products, with the RX 6800S releasing on January 3, 2022, and the RTX 3070 Mobile releasing on January 11, 2021. The RX 6800S lists the Polaris Mobile as its predecessor, while the RTX 3070 Mobile lists the GeForce 20 Mobile.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6800S has a higher average benchmark score of 24063, compared to 20534 for the NVIDIA GeForce RTX 3070 Mobile. This places the RX 6800S in the 69th percentile of all GPUs, while the RTX 3070 Mobile sits in the 65th percentile.

Q: How large is the RTX 3070 Mobile's lead in the 3DMark Steel Nomad test?

A: The RTX 3070 Mobile scores 2380 in the 3DMark Steel Nomad DX12 test, which is 29% higher than the RX 6800S's score of 1689. This is the largest performance gap recorded in the head-to-head comparison.

Q: Where does the RX 6800S show its biggest advantage?

A: The RX 6800S's largest win is in the Passmark DirectX 9 test, where it scores 200 against 160 for the RTX 3070 Mobile, a 25% advantage. It also leads in Passmark G2D by 14.2% and in Passmark G3D by 3.9%.

Q: Does the RTX 3070 Mobile have more memory bandwidth?

A: Yes. The RTX 3070 Mobile has a 256-bit memory bus delivering 448.0 GB/s of bandwidth, while the RX 6800S has a 128-bit bus delivering 256.0 GB/s. Both have 8 GB of GDDR6 memory.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 3070 Mobile has 5120 shading units, while the AMD Radeon RX 6800S has 2048. The RTX 3070 Mobile also has 160 TMUs and 80 ROPs, compared to 128 TMUs and 64 ROPs for the RX 6800S.

Q: How do the FP32 compute figures compare?

A: The RTX 3070 Mobile delivers 15.97 TFLOPS of FP32 compute, while the RX 6800S delivers 8.602 TFLOPS. In FP16, the RX 6800S reaches 17.20 TFLOPS at a 2:1 ratio, while the RTX 3070 Mobile achieves 15.97 TFLOPS at a 1:1 ratio.

The Verdict

The data supports a nuanced conclusion. The NVIDIA GeForce RTX 3070 Mobile is the stronger choice for modern, demanding workloads. Its 29% lead in 3DMark Steel Nomad DX12, 21.2% lead in Geekbench OpenCL, and 10% lead in Passmark GPU Compute demonstrate a clear edge in contemporary DirectX 12 rendering and general-purpose compute. The additional bandwidth from the 256-bit bus, the higher FP32 throughput at 15.97 TFLOPS, and the presence of 160 tensor cores further reinforce this position for applications that use these features.

The AMD Radeon RX 6800S, however, posts the higher average benchmark score at 24063 and holds a 3.9% advantage in Passmark G3D, a broad gaming metric. Its wins in DirectX 9 and DirectX 11, along with its 2D performance lead, suggest strong compatibility with older software titles. The lower 100 W power target compared to 115 W for the RTX 3070 Mobile is also a relevant factor for thin-and-light laptop designs, though the database does not provide direct thermal or battery performance measurements.

For users prioritizing maximum performance in the latest DirectX 12 games and compute-heavy applications, the RTX 3070 Mobile is the clear pick based on the recorded deltas. For those who value a higher overall average score, strong legacy API performance, and lower power consumption, the RX 6800S presents a compelling case. The percentile rankings, 69th for the RX 6800S versus 65th for the RTX 3070 Mobile, align with the average score difference but do not erase the RTX 3070 Mobile's decisive wins in the most demanding tests.

Specification Differences

The two GPUs differ across nearly every major specification category. The RX 6800S uses the Navi 23 chip on RDNA 2.0 architecture with a 7 nm TSMC process, while the RTX 3070 Mobile uses the GA104 chip on Ampere architecture with an 8 nm Samsung process. The die size is 237 mm² for AMD and 392 mm² for NVIDIA, with transistor counts of 11,060 million and 17,400 million respectively. Transistor density is 46.7M per mm² for the RX 6800S and 44.4M per mm² for the RTX 3070 Mobile.

Clock speeds differ substantially. The RX 6800S has a base clock of 1800 MHz, a boost clock of 2100 MHz, and a game clock of 1975 MHz. The RTX 3070 Mobile has a base clock of 1110 MHz and a boost clock of 1560 MHz, with no game clock listed. Memory clocks are 2000 MHz with 16 Gbps effective for AMD, and 1750 MHz with 14 Gbps effective for NVIDIA.

Core counts and compute resources are heavily skewed toward NVIDIA. The RTX 3070 Mobile has 5120 shading units, 160 TMUs, 80 ROPs, 40 RT cores, and 160 tensor cores. The RX 6800S has 2048 shading units, 128 TMUs, 64 ROPs, and 32 RT cores, with no tensor cores. Despite this, the RX 6800S has higher pixel and texture rates at 134.4 GPixel/s and 268.8 GTexel/s, versus 124.8 GPixel/s and 249.6 GTexel/s for the RTX 3070 Mobile. FP32 compute is 8.602 TFLOPS for AMD and 15.97 TFLOPS for NVIDIA, while FP16 is 17.20 TFLOPS (2:1) for AMD and 15.97 TFLOPS (1:1) for NVIDIA.

Memory is 8 GB of GDDR6 on both, but the bus width and bandwidth differ: 128-bit with 256.0 GB/s for the RX 6800S, and 256-bit with 448.0 GB/s for the RTX 3070 Mobile. The TDP is 100 W for AMD and 115 W for NVIDIA. The bus interface is PCIe 4.0 x8 for AMD and PCIe 4.0 x16 for NVIDIA. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Release dates are January 3, 2022, for the RX 6800S and January 11, 2021, for the RTX 3070 Mobile.

Where Each One Wins

The RTX 3070 Mobile wins in modern rendering and compute. The 29% lead in 3DMark Steel Nomad DX12 makes it the preferred option for current-generation DirectX 12 games. The 21.2% advantage in Geekbench OpenCL and the 10% lead in Passmark GPU Compute position it as the stronger choice for GPU-accelerated computation, content creation, and workloads that leverage OpenCL. The 19.5% win in Passmark DirectX 10 and the 6.3% lead in Geekbench Vulkan further extend its reach across a broad range of APIs. The presence of 160 tensor cores and 40 RT cores, combined with 15.97 TFLOPS of FP32 compute and 448.0 GB/s of memory bandwidth, gives it the raw resources to handle demanding tasks.

The RX 6800S wins in legacy API performance and overall average score. Its 25% lead in Passmark DirectX 9 and 0.7% win in Passmark DirectX 11 make it the better choice for older game libraries and software that relies on these APIs. The 14.2% advantage in Passmark G2D indicates superior 2D performance. The 3.9% win in Passmark G3D, despite the RTX 3070 Mobile's dominance in the Steel Nomad test, suggests the RX 6800S holds its own in the broader Passmark gaming metric. The higher average benchmark score of 24063 and the 69th percentile ranking are also points in its favor. The lower 100 W TDP compared to 115 W for the RTX 3070 Mobile, combined with the smaller 237 mm² die, makes it a more power-efficient design on paper, which can be a deciding factor in portable systems.