AMD Radeon RX 6700 XT vs NVIDIA GeForce GTX 980 Ti Comparison

The NVIDIA GeForce GTX 980 Ti and AMD Radeon RX 6700 XT represent two distinct eras of GPU design, with the former launching in mid-2015 on the Maxwell architecture and the latter arriving in early 2021 on RDNA 2.0. While the GTX 980 Ti holds a slightly higher percentile ranking at 73 versus the RX 6700 XT's 72, the benchmark data tells a much more decisive story in favor of the newer AMD card. Across every head-to-head test, the RX 6700 XT delivers a commanding victory, making this comparison less about raw specs and more about architectural generational leaps.

Head-to-Head Benchmarks

The most dramatic disparity appears in the Geekbench Metal test, where the RX 6700 XT scores 130,896 against the GTX 980 Ti's 19,520. That is an 85.1% delta in favor of AMD, a staggering margin that reflects not just clock speed improvements but a fundamentally more efficient compute design. For any workload leveraging Apple's Metal API, the RX 6700 XT is in a different league entirely.

In the 3DMark Steel Nomad DX12 test, the RX 6700 XT posts 2,435 points while the GTX 980 Ti manages 1,321, representing a 45.7% advantage for AMD. This is a modern DirectX 12 benchmark, and the gap underscores how the older Maxwell architecture struggles with contemporary rendering workloads. The RX 6700 XT's support for DirectX 12 Ultimate (12_2) compared to the GTX 980 Ti's DirectX 12 (12_1) likely contributes to this substantial lead.

The Geekbench Vulkan test shows a similar pattern: the RX 6700 XT scores 93,500 versus the GTX 980 Ti's 47,724, a 49% difference. Vulkan is a low-level API that rewards modern hardware design, and the RDNA 2.0 architecture clearly extracts far more performance per clock.

The closest contest is in Geekbench OpenCL, where the RX 6700 XT edges out the GTX 980 Ti by only 1.4%, scoring 44,152 against 43,513. This near-parity is notable because OpenCL is a more generic compute workload that doesn't always leverage the latest hardware features. It suggests that in raw, non-API-specific compute tasks, the older card can still hold its own, though it remains behind.

In total, the RX 6700 XT wins all four benchmark comparisons. The average benchmark score reflects this: the GTX 980 Ti averages 28,020, while the RX 6700 XT averages 27,425. Interestingly, the GTX 980 Ti's average is slightly higher despite losing every head-to-head test, which indicates that its benchmark suite includes different tests where it performs relatively better, such as the Passmark tests where the RX 6700 XT scores 19,786 in G3D and 9,336 in GPU compute, while the GTX 980 Ti has no corresponding Passmark entries.

FAQ

Q: Which card is faster in DirectX 12 gaming?

A: The RX 6700 XT wins decisively, scoring 2,435 in 3DMark Steel Nomad DX12 versus the GTX 980 Ti's 1,321, a 45.7% advantage. The RX 6700 XT also supports DirectX 12 Ultimate (12_2), while the GTX 980 Ti is limited to DirectX 12 (12_1).

Q: How do the two cards compare in Vulkan performance?

A: The RX 6700 XT scores 93,500 in Geekbench Vulkan, which is 49% higher than the GTX 980 Ti's 47,724. Both cards support Vulkan 1.4, but the newer architecture extracts significantly more performance.

Q: Is there any workload where the GTX 980 Ti is competitive?

A: In Geekbench OpenCL, the GTX 980 Ti scores 43,513 against the RX 6700 XT's 44,152, a mere 1.4% difference. This is the closest margin in any head-to-head test, suggesting that generic compute tasks don't fully expose the generational gap.

Q: What is the memory configuration difference?

A: The GTX 980 Ti uses 6 GB of GDDR5 on a 384-bit bus with 336.6 GB/s bandwidth. The RX 6700 XT uses 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. Despite the narrower bus, the RX 6700 XT delivers higher total bandwidth.

Q: Which card has a higher transistor count?

A: The RX 6700 XT has 17,200 million transistors on a 335 mm² die, while the GTX 980 Ti has 8,000 million transistors on a 601 mm² die. The RX 6700 XT achieves this with a much smaller physical footprint.

Q: Do both cards consume similar power?

A: The GTX 980 Ti has a 250 W TDP with a 600 W suggested PSU, while the RX 6700 XT has a 230 W TDP with a 550 W suggested PSU. The RX 6700 XT delivers far more performance while drawing less power.

Architecture Differences

The GTX 980 Ti is built on the GM200 chip using Maxwell 2.0 architecture on a 28 nm process from TSMC. It packs 8,000 million transistors into a massive 601 mm² die, yielding a transistor density of 13.3 million per square millimeter. This is a large, hot chip by modern standards, reflecting the limitations of the older manufacturing node.

The RX 6700 XT uses the Navi 22 chip with RDNA 2.0 architecture on a 7 nm process, also from TSMC. It contains 17,200 million transistors in a much smaller 335 mm² die, achieving a density of 51.3 million per square millimeter. This is nearly four times the transistor density, which explains how AMD fits more than double the transistors into roughly half the silicon area.

The shading unit counts are similar — the GTX 980 Ti has 2,816 shading units, while the RX 6700 XT has 2,560 — but the execution efficiency differs dramatically. The RX 6700 XT includes 40 ray tracing cores, a feature entirely absent from the Maxwell-based GTX 980 Ti. Additionally, the RX 6700 XT supports FP16 at 26.43 TFLOPS with a 2:1 ratio, while the GTX 980 Ti has no FP16 capability listed.

The pixel and texture rates tell the story of architectural efficiency. The GTX 980 Ti achieves 103.3 GPixel/s and 189.4 GTexel/s, while the RX 6700 XT reaches 165.2 GPixel/s and 413.0 GTexel/s. Despite having fewer shading units, TMUs (160 vs. 176), and ROPs (64 vs. 96), the RX 6700 XT produces higher throughput thanks to its much higher clock speeds and newer design.

Specification Differences

Clock speeds show a massive gap. The GTX 980 Ti runs at a 1000 MHz base and 1076 MHz boost, while the RX 6700 XT operates at 2321 MHz base, 2424 MHz game clock, and 2581 MHz boost. This more than doubles the effective frequency, which is the primary driver of the performance difference.

Memory differs in size, type, and bandwidth. The GTX 980 Ti has 6 GB of GDDR5 at 1753 MHz (7 Gbps effective) on a 384-bit bus, yielding 336.6 GB/s. The RX 6700 XT has 12 GB of GDDR6 at 2000 MHz (16 Gbps effective) on a 192-bit bus, yielding 384.0 GB/s. The RX 6700 XT offers double the capacity and higher bandwidth despite the narrower bus.

Interface and connectivity also differ. The GTX 980 Ti uses PCIe 3.0 x16, while the RX 6700 XT uses PCIe 4.0 x16. Display outputs vary: the GTX 980 Ti offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, while the RX 6700 XT provides 1x HDMI 2.1 and 3x DisplayPort 1.4a. The RX 6700 XT supports DirectX 12 Ultimate (12_2) versus the GTX 980 Ti's DirectX 12 (12_1), though both support OpenGL 4.6 and Vulkan 1.4.

Physical dimensions are nearly identical — both are 267 mm long, 40 mm wide, dual-slot cards, with the GTX 980 Ti at 111 mm tall and the RX 6700 XT at 110 mm. Power requirements favor the RX 6700 XT, which has a 230 W TDP and 550 W suggested PSU versus the GTX 980 Ti's 250 W TDP and 600 W suggested PSU. Both use the same 1x 6-pin + 1x 8-pin power connector configuration.

Where Each One Wins

The RX 6700 XT wins in every measured benchmark category. It dominates modern API workloads like DirectX 12 and Vulkan, where its architectural advantages and ray tracing support come into play. It also excels in Metal performance, making it the clear choice for any macOS or iOS development environment. Its 12 GB VRAM and higher bandwidth make it better suited for modern textures and higher resolutions.

The GTX 980 Ti's only competitive showing is in OpenCL, where it trails by just 1.4%. This suggests that in legacy compute workloads that don't leverage modern API features, the older card can still perform respectably. Its higher ROP count (96 vs. 64) and wider 384-bit memory bus might theoretically benefit certain fill-rate-bound scenarios, though the benchmark data does not show any test where this translates into a win.

For ray tracing workloads, the RX 6700 XT is the only option with dedicated RT cores. The GTX 980 Ti has no ray tracing hardware whatsoever, making it unsuitable for any modern game or application that requires this feature.

The Verdict

The data is unambiguous: the RX 6700 XT is the superior card in every head-to-head comparison. It wins by margins ranging from 1.4% in OpenCL to 85.1% in Metal, with substantial 45.7% and 49% leads in DirectX 12 and Vulkan respectively. Its newer 7 nm process, higher clock speeds, double the VRAM, and ray tracing support make it the practical choice for any modern workload.

The GTX 980 Ti should only be considered if you have a specific need for its legacy characteristics, such as its 384-bit memory bus or its higher ROP count, and you are working exclusively in older APIs where its OpenCL performance remains within striking distance. However, with an end-of-life production status and a launch MSRP of 649 USD versus the RX 6700 XT's 479 USD, the older card was more expensive at launch and offers dramatically less performance today.

Benchmark results indicate that the RX 6700 XT sits within 0.5% of the NVIDIA GeForce RTX 3090 in average score, while the GTX 980 Ti is roughly comparable to the AMD Radeon Pro W5500X and AMD FirePro S7150. This places the two cards in entirely different performance tiers despite their similar percentile rankings. For anyone building a system today, the RX 6700 XT is the only rational choice based on this data.