AMD Radeon RX 6800S vs NVIDIA GeForce GTX 980 Ti Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 980 Ti holds a higher average benchmark score of 28,020 compared to the AMD Radeon RX 6800S at 24,063. The GTX 980 Ti also sits at the 73rd percentile of all GPUs, while the RX 6800S is at the 69th percentile.

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

A: The AMD Radeon RX 6800S wins this test with a score of 1,689, while the NVIDIA GeForce GTX 980 Ti scores 1,321. That gives the RX 6800S a 21.8% lead in this modern DX12 workload.

Q: Which GPU has the larger memory bus width?

A: The NVIDIA GeForce GTX 980 Ti uses a 384-bit memory bus, while the AMD Radeon RX 6800S uses a 128-bit bus. Despite the narrower bus, the RX 6800S achieves lower memory bandwidth at 256.0 GB/s compared to 336.6 GB/s for the GTX 980 Ti.

Q: What are the transistor counts for each GPU?

A: The NVIDIA GeForce GTX 980 Ti packs 8,000 million transistors on a 601 mm² die, whereas the AMD Radeon RX 6800S has 11,060 million transistors on a much smaller 237 mm² die. This gives the RX 6800S a transistor density of 46.7M per mm² versus 13.3M per mm² for the GTX 980 Ti.

Q: Which GPU supports DirectX 12 Ultimate?

A: Only the AMD Radeon RX 6800S supports DirectX 12 Ultimate (12_2). The NVIDIA GeForce GTX 980 Ti is limited to DirectX 12 (12_1), which means it lacks some of the newer feature-level capabilities.

Q: How large is the performance gap in the Geekbench Vulkan test?

A: The AMD Radeon RX 6800S scores 81,272 in Geekbench Vulkan, which is 41.3% ahead of the NVIDIA GeForce GTX 980 Ti's score of 47,724. This is one of the largest single-test deltas between the two.

Architecture Differences

The NVIDIA GeForce GTX 980 Ti is built on the Maxwell 2.0 architecture using the GM200 chip, manufactured on a 28 nm process at TSMC. It belongs to the GeForce 900 generation and was released in 2015. In contrast, the AMD Radeon RX 6800S uses the RDNA 2.0 architecture with the Navi 23 chip, built on a 7 nm process also at TSMC. It is part of the Radeon RX 6000 series and the Navi Mobile (RX 6000M) generation, released in 2022.

The process node difference is substantial: 28 nm versus 7 nm. This allows the RX 6800S to pack 11,060 million transistors into a 237 mm² die, resulting in a transistor density of 46.7M per mm². The GTX 980 Ti, with 8,000 million transistors on a 601 mm² die, has a density of only 13.3M per mm². The newer manufacturing process gives the RX 6800S a significant efficiency and density advantage.

The RX 6800S includes 32 ray tracing cores, a feature entirely absent from the GTX 980 Ti. It also supports DirectX 12 Ultimate (12_2), whereas the GTX 980 Ti is limited to DirectX 12 (12_1). Both GPUs support OpenGL 4.6 and Vulkan 1.4, but the RX 6800S has broader API coverage for modern workloads.

The memory subsystems differ fundamentally. The GTX 980 Ti uses 6 GB of GDDR5 on a 384-bit bus, yielding 336.6 GB/s of bandwidth. The RX 6800S uses 8 GB of GDDR6 on a 128-bit bus, yielding 256.0 GB/s. Despite the smaller bus, GDDR6 memory at 16 Gbps effective helps close the bandwidth gap.

Power characteristics are also markedly different. The GTX 980 Ti has a 250 W TDP, requires a dual-slot cooler, and needs both a 6-pin and an 8-pin power connector, with a suggested 600 W power supply. The RX 6800S has a 100 W TDP, is integrated into the motherboard (IGP form factor), and requires no power connectors. The bus interface differs as well: PCIe 3.0 x16 for the GTX 980 Ti versus PCIe 4.0 x8 for the RX 6800S.

Head-to-Head Benchmarks

The recorded head-to-head data covers four benchmark tests, and the AMD Radeon RX 6800S wins all four. The NVIDIA GeForce GTX 980 Ti does not win any of the head-to-head comparisons.

In the 3DMark Steel Nomad DX12 test, the RX 6800S scores 1,689 against 1,321 for the GTX 980 Ti. This is a 21.8% advantage for the AMD part. This test represents a modern DX12 workload, where the newer architecture's feature set and higher clock speeds provide a clear edge.

The Geekbench Metal test shows the largest disparity. The RX 6800S scores 85,256, while the GTX 980 Ti manages only 19,520. The delta is 77.1% in favor of the RX 6800S. This is an enormous gap, reflecting both the architectural age of the GTX 980 Ti and the RX 6800S's much higher clock speeds and newer compute capabilities.

In Geekbench OpenCL, the RX 6800S scores 73,202 against 43,513 for the GTX 980 Ti, a 40.6% lead. The Geekbench Vulkan test shows a similar pattern: 81,272 for the RX 6800S versus 47,724 for the GTX 980 Ti, a 41.3% difference.

These results indicate that the RX 6800S maintains a consistent and often large lead across all tested APIs. The smallest margin is in 3DMark Steel Nomad DX12 at 21.8%, while the largest is in Geekbench Metal at 77.1%. The average benchmark scores from the wider database tell a slightly different story: the GTX 980 Ti has a higher average score (28,020) than the RX 6800S (24,063), but this includes many additional tests where the GTX 980 Ti's older driver support and different workload characteristics may play a role.

Specification Differences

The following specifications differ between the two GPUs:

• Process Node: 28 nm (GTX 980 Ti) versus 7 nm (RX 6800S)
• Transistors: 8,000 million versus 11,060 million
• Die Size: 601 mm² versus 237 mm²
• Transistor Density: 13.3M / mm² versus 46.7M / mm²
• Base Clock: 1000 MHz versus 1800 MHz
• Boost Clock: 1076 MHz versus 2100 MHz
• Game Clock: Not applicable versus 1975 MHz
• Memory Clock: 1753 MHz (7 Gbps effective) versus 2000 MHz (16 Gbps effective)
• Memory Size: 6 GB versus 8 GB
• Memory Type: GDDR5 versus GDDR6
• Memory Bus Width: 384 bit versus 128 bit
• Memory Bandwidth: 336.6 GB/s versus 256.0 GB/s
• Shading Units: 2816 versus 2048
• TMUs: 176 versus 128
• ROPs: 96 versus 64
• Ray Tracing Cores: None versus 32
• Pixel Rate: 103.3 GPixel/s versus 134.4 GPixel/s
• Texture Rate: 189.4 GTexel/s versus 268.8 GTexel/s
• FP32 Performance: 6.060 TFLOPS versus 8.602 TFLOPS
• FP16 Performance: Not applicable versus 17.20 TFLOPS (2:1)
• TDP: 250 W versus 100 W
• Slot Width: Dual-slot versus IGP
• Power Connectors: 1x 6-pin + 1x 8-pin versus None
• Suggested PSU: 600 W versus Not applicable
• Bus Interface: PCIe 3.0 x16 versus PCIe 4.0 x8
• Display Outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 versus Portable Device Dependent
• DirectX Support: 12 (12_1) versus 12 Ultimate (12_2)
• Release Date: 2015-06-01 versus 2022-01-03
• Predecessor: GeForce 700 versus Polaris Mobile
• Successor: GeForce 10 versus Not applicable
• Launch MSRP: 649 USD (GTX 980 Ti only)

Where Each One Wins

The AMD Radeon RX 6800S wins decisively in all four head-to-head benchmark tests. Its largest advantages come in compute-oriented workloads: Geekbench Metal shows a 77.1% lead, while Geekbench OpenCL and Vulkan show 40.6% and 41.3% leads respectively. The RX 6800S also wins the 3DMark Steel Nomad DX12 test by 21.8%. This makes the RX 6800S the clear choice for modern compute-heavy applications, ray tracing workloads (thanks to its 32 ray tracing cores), and any scenario leveraging DirectX 12 Ultimate features.

The RX 6800S also wins on efficiency. Its 100 W TDP is 150 W lower than the GTX 980 Ti's 250 W TDP, and it requires no external power connectors or dedicated power supply recommendation. This makes it suitable for portable devices and integrated layouts, whereas the GTX 980 Ti needs a dual-slot cooler and a 600 W power supply.

The NVIDIA GeForce GTX 980 Ti retains advantages in specific areas. It has a higher average benchmark score (28,020 versus 24,063) across the full database, placing it at the 73rd percentile versus the 69th percentile for the RX 6800S. It also offers much higher memory bandwidth at 336.6 GB/s versus 256.0 GB/s, thanks to its 384-bit bus. The GTX 980 Ti has more shading units (2816 versus 2048), more TMUs (176 versus 128), and more ROPs (96 versus 64). For workloads that are bandwidth-bound or benefit from higher raw memory throughput, the GTX 980 Ti may still hold an edge despite its older architecture.

The GTX 980 Ti's nearest rivals in the database include the AMD Radeon Pro W5500X (0.2% ahead) and the AMD FirePro S7150 (0.3% behind), indicating it sits in a competitive mid-range position. The RX 6800S's nearest rivals include the NVIDIA GeForce RTX 2080 SUPER (0.4% ahead) and the NVIDIA GeForce GTX 780 Ti (0.7% ahead), showing it performs at a similar level to those older high-end parts.

For users prioritizing modern API support, ray tracing, efficiency, and compute performance, the RX 6800S is the stronger choice. For those who value memory bandwidth, higher average benchmark scores, and a more traditional discrete desktop form factor, the GTX 980 Ti still has relevant strengths. The data shows a clear generational split: the newer RX 6800S dominates the specific tests where its architecture and features matter most, while the older GTX 980 Ti maintains a broader average score advantage due to its memory subsystem and raw shading unit count.