AMD Radeon RX 7700 vs NVIDIA GeForce GTX 1080 Ti Comparison

Head-to-Head Benchmarks

The benchmark data tells a clear story: the AMD Radeon RX 7700 wins 8 of the 9 head-to-head comparisons, and it wins most of them by substantial margins. The single exception is DirectX 10, where the NVIDIA GeForce GTX 1080 Ti leads by 22% (118 vs. 92). That is a legacy API test, and it is the only category where the older card shows an edge.

The biggest gap comes in Geekbench OpenCL. The RX 7700 scores 106,028 against the GTX 1080 Ti’s 67,929, a 56.1% advantage. That is a massive compute lead, and it reflects the fundamental difference in how these two architectures handle parallel workloads. In 3DMark Steel Nomad DX12, the RX 7700 posts 2,865 versus 2,231, a 28.4% win. That is a modern, demanding test, and the margin there is decisive.

In the Passmark suite, the RX 7700 wins DirectX 12 by 45.5% (96 vs. 66), DirectX 11 by 23.2% (186 vs. 151), and DirectX 9 by 13% (261 vs. 231). The G3D score—which aggregates overall 3D performance—shows the RX 7700 at 20,974 versus 18,600, a 12.8% lead. The GPU compute score is similarly one-sided: 10,963 vs. 9,632, a 13.8% edge. Even the 2D test (Passmark G2D) goes to the RX 7700, 1,206 vs. 939, a 28.4% margin.

What is notable is that the RX 7700’s wins are not narrow. In every modern API test, the lead is at least 13% and often much larger. The GTX 1080 Ti’s sole victory is in a DirectX 10 workload that is over a decade old. For any contemporary use case, the data points firmly to the AMD card.

Architecture Differences

The two cards come from completely different eras of GPU design. The RX 7700 uses the Navi 32 chip built on TSMC’s 5 nm process, with 28,100 million transistors packed into a 346 mm² die. The GTX 1080 Ti uses the GP102 chip on TSMC’s 16 nm process, with 11,800 million transistors on a larger 471 mm² die. The transistor density difference is stark: 81.2M per mm² for the RX 7700 versus 25.1M per mm² for the GTX 1080 Ti. That is a 3x density advantage for AMD, which explains how the newer card fits more than double the transistors into a smaller package.

The architectures themselves are generations apart. The RX 7700 is RDNA 3.0, part of the Navi III (RX 7000) generation. The GTX 1080 Ti is Pascal, from the GeForce 10 series. The RX 7700 has 40 dedicated ray tracing cores; the GTX 1080 Ti has none. That alone makes the AMD card the only option for hardware-accelerated ray tracing. The RX 7700 also supports DirectX 12 Ultimate (12_2), while the GTX 1080 Ti is limited to DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4, so those APIs are not differentiators.

Memory architecture is another major division. The RX 7700 uses 16 GB of GDDR6 on a 256-bit bus, yielding 624.1 GB/s of bandwidth. The GTX 1080 Ti uses 11 GB of GDDR5X on a 352-bit bus, yielding 484.4 GB/s. Despite the narrower bus, the newer GDDR6 memory runs at a higher effective speed (19.5 Gbps vs. 11 Gbps), giving AMD the bandwidth advantage. The RX 7700’s FP32 throughput is 25.18 TFLOPS versus 11.34 TFLOPS for NVIDIA—more than double. FP16 is even more lopsided: 25.18 TFLOPS on AMD versus 177.2 GFLOPS on NVIDIA, a 1:1 ratio versus a 1:64 ratio. The RX 7700 also has a higher pixel rate (236.1 GPixel/s vs. 139.2) and texture rate (393.4 GTexel/s vs. 354.4), despite having fewer shading units (2,560 vs. 3,584) and TMUs (160 vs. 224).

FAQ

Q: Which card has more VRAM, and does it matter?

A: The RX 7700 has 16 GB of GDDR6, while the GTX 1080 Ti has 11 GB of GDDR5X. The AMD card also offers higher bandwidth (624.1 GB/s vs. 484.4 GB/s). For modern games and textures, the extra 5 GB gives the RX 7700 more headroom.

Q: Can the GTX 1080 Ti do ray tracing?

A: No. The RX 7700 has 40 ray tracing cores, while the GTX 1080 Ti has none. If ray tracing is a requirement, the GTX 1080 Ti is not an option.

Q: Which card wins in DirectX 12?

A: The RX 7700 wins decisively. In Passmark DirectX 12, it scores 96 versus 66, a 45.5% advantage. In 3DMark Steel Nomad DX12, it leads 2,865 to 2,231 (28.4%).

Q: Is there any test where the GTX 1080 Ti wins?

A: Yes, one: Passmark DirectX 10, where it scores 118 versus 92, a 22% lead. That is a legacy API test with no relevance to modern workloads.

Q: How do these cards compare in compute performance?

A: The RX 7700 is far ahead. In Geekbench OpenCL, it scores 106,028 versus 67,929 (56.1% higher). In Passmark GPU compute, it leads 10,963 to 9,632 (13.8%). The FP32 throughput difference is 25.18 TFLOPS versus 11.34 TFLOPS.

Q: Which card is more power-efficient based on specs?

A: The RX 7700 has a 200 W TDP versus 250 W for the GTX 1080 Ti, and it delivers higher performance in nearly every test. The RX 7700 also has a lower suggested PSU (550 W vs. 600 W). The data indicates AMD gets more performance per watt.

Specification Differences

The two cards differ in nearly every measurable specification. The RX 7700 is built on a 5 nm process; the GTX 1080 Ti is on 16 nm. The RX 7700 has 28,100 million transistors on a 346 mm² die; the GTX 1080 Ti has 11,800 million on 471 mm². Transistor density is 81.2M/mm² versus 25.1M/mm².

Clock speeds are different: the RX 7700 runs at 1900 MHz base and 2459 MHz boost, with a game clock of 2041 MHz. The GTX 1080 Ti runs at 1481 MHz base and 1582 MHz boost, with no game clock listed. Memory clocks are 2438 MHz (19.5 Gbps effective) for AMD versus 1376 MHz (11 Gbps effective) for NVIDIA.

Memory capacity is 16 GB GDDR6 versus 11 GB GDDR5X. Bus width is 256-bit versus 352-bit, but bandwidth favors AMD (624.1 GB/s vs. 484.4 GB/s). The RX 7700 has 2,560 shading units, 160 TMUs, and 96 ROPs; the GTX 1080 Ti has 3,584 shading units, 224 TMUs, and 88 ROPs. The RX 7700 has 40 RT cores; the GTX 1080 Ti has none.

Pixel rate is 236.1 GPixel/s versus 139.2 GPixel/s. Texture rate is 393.4 GTexel/s versus 354.4 GTexel/s. FP32 is 25.18 TFLOPS versus 11.34 TFLOPS. FP16 is 25.18 TFLOPS versus 177.2 GFLOPS.

Power draw differs: 200 W TDP for AMD versus 250 W for NVIDIA. Power connectors are 2x 8-pin versus 1x 6-pin + 1x 8-pin. Suggested PSU is 550 W versus 600 W. The RX 7700 uses PCIe 4.0 x16; the GTX 1080 Ti uses PCIe 3.0 x16. Display outputs are 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C for AMD; 1x HDMI 2.0 and 3x DisplayPort 1.4a for NVIDIA.

Dimensions are similar in length (267 mm for both), but the RX 7700 is taller (135 mm vs. 112 mm) and thicker (50 mm vs. 40 mm). The RX 7700 is still in active production; the GTX 1080 Ti is end-of-life. The GTX 1080 Ti launched with an MSRP of 699 USD, which is stated here once per the data.

The Verdict

The data is unambiguous: the AMD Radeon RX 7700 is the faster card in almost every scenario. It wins 8 of 9 benchmarks, with margins ranging from 12.8% to 56.1%. It has more VRAM, higher bandwidth, more than double the FP32 throughput, and hardware ray tracing. It also draws 50 W less power and requires a smaller PSU. The GTX 1080 Ti wins only in DirectX 10, a test that modern games do not use.

The RX 7700’s average benchmark score is 15,852, while the GTX 1080 Ti’s is 15,548. Both sit at the 58th percentile of all GPUs. In the nearest rival comparison, the RX 7700 is 1.7% behind the RTX 3060 Ti and 1% behind the RX 9060; the GTX 1080 Ti is 1.7% ahead of the RTX 2060. These are different neighborhoods of performance, but the head-to-head numbers show the RX 7700 pulling ahead by double digits in most tests.

The GTX 1080 Ti is an end-of-life product from 2017. The RX 7700 is an active product from 2025. If you are choosing between these two today, the RX 7700 is the rational pick for any modern workload. The only reason to choose the GTX 1080 Ti would be if you specifically needed its DirectX 10 performance—an extremely narrow use case.

Where Each One Wins

AMD Radeon RX 7700 wins in:

• DirectX 12 gaming: 45.5% lead in Passmark DX12, 28.4% lead in 3DMark Steel Nomad
• DirectX 11 gaming: 23.2% lead
• DirectX 9 legacy titles: 13% lead
• Compute workloads: 56.1% lead in OpenCL, 13.8% lead in GPU compute
• Overall 3D performance: 12.8% lead in Passmark G3D
• 2D desktop work: 28.4% lead in Passmark G2D
• Ray tracing: has 40 RT cores; the GTX 1080 Ti has none
• Future-proofing: 16 GB VRAM, PCIe 4.0, DirectX 12 Ultimate, active production status

NVIDIA GeForce GTX 1080 Ti wins in:

• DirectX 10 workloads: 22% lead (118 vs. 92)
• Raw shader count: 3,584 shading units versus 2,560
• Texture units: 224 versus 160
• Physical size: shorter height (112 mm vs. 135 mm) and thinner (40 mm vs. 50 mm)

The GTX 1080 Ti’s wins are mostly on paper. Having more shading units and TMUs does not translate to higher benchmark scores because the RX 7700’s newer architecture and higher clocks compensate. The DirectX 10 result is the only real benchmark victory, and it is irrelevant for modern gaming. The RX 7700 is the better card for everything current, and its production status means it will remain available and supported. The GTX 1080 Ti is a collector’s item at this point—one that still works fine, but one that is outclassed by a card that draws less power and costs the same in performance terms.