AMD Radeon RX 9070 vs NVIDIA GeForce GTX 980 Ti Comparison

The Verdict

The data is unambiguous: the AMD Radeon RX 9070 is the faster card by a massive margin in every recorded benchmark. The GTX 980 Ti holds no wins in the head-to-head tests, so for anyone building a new system or upgrading from an older Maxwell card, the RX 9070 is the clear choice. It offers roughly 4.8 times the score in 3DMark Steel Nomad DX12, over 3 times the OpenCL score, and a solid 23% lead in Vulkan. The GTX 980 Ti remains a functional card for older DirectX 12 titles, but its 6 GB memory and 28 nm process place it firmly in legacy territory. The RX 9070, with its 16 GB VRAM and modern RDNA 4.0 architecture, is the only sensible pick for current and upcoming games, especially at higher resolutions or with ray tracing enabled. The GTX 980 Ti is for retro builds or budget systems where only legacy drivers and older APIs are needed, but the recorded data shows it is outclassed in every measurable way.

Architecture Differences

The two cards are separated by a decade of silicon evolution. The GTX 980 Ti uses the GM200 chip on NVIDIA's Maxwell 2.0 architecture, built on a 28 nm TSMC process. It packs 8,000 million transistors on a 601 mm² die, resulting in a transistor density of 13.3 million per square millimeter. The RX 9070, in contrast, uses the Navi 48 chip on AMD's RDNA 4.0 architecture, fabricated on a 4 nm TSMC process. It holds 53,900 million transistors on a much smaller 357 mm² die, giving it a density of 151.0 million per square millimeter, over 11 times higher.

The core configurations differ significantly. The GTX 980 Ti has 2816 shading units, 176 texture units, and 96 ROPs. The RX 9070 has 3584 shading units, 224 texture units, and 128 ROPs. The RX 9070 also includes 56 dedicated ray tracing cores, a feature entirely absent from the Maxwell 2.0 architecture. The GTX 980 Ti supports DirectX 12 (12_1) and Vulkan 1.4, while the RX 9070 reaches DirectX 12 Ultimate (12_2) and Vulkan 1.4. Both cards support OpenGL 4.6.

The RX 9070 is built for modern parallel workloads. Its FP32 throughput is 36.13 TFLOPS, and it matches this with FP16 at 36.13 TFLOPS (1:1 ratio). The GTX 980 Ti manages 6.060 TFLOPS FP32 and has no recorded FP16 capability. The pixel and texture rates tell the same story: the RX 9070 delivers 322.6 GPixel/s and 564.5 GTexel/s, versus 103.3 GPixel/s and 189.4 GTexel/s for the GTX 980 Ti. The RX 9070's process node advantage also brings lower power draw (220 W TDP vs 250 W) despite far higher performance, and it requires a 550 W suggested PSU versus the GTX 980 Ti's 600 W suggestion.

Head-to-Head Benchmarks

The head-to-head data shows a complete sweep for the RX 9070 across all three recorded tests. The most dramatic gap appears in 3DMark Steel Nomad DX12, where the RX 9070 scores 6290 against the GTX 980 Ti's 1321. That is a delta of -79% from the RX 9070's perspective, meaning the GTX 980 Ti delivers only about 21% of the RX 9070's performance in this modern DirectX 12 workload. This test is particularly demanding on memory bandwidth and raw compute, both areas where the RX 9070's 644.6 GB/s GDDR6 bandwidth and 36.13 TFLOPS FP32 utterly overwhelm the GTX 980 Ti's 336.6 GB/s GDDR5 and 6.060 TFLOPS.

In Geekbench OpenCL, the RX 9070 scores 131539 versus 43513 for the GTX 980 Ti, a delta of -66.9%. This reflects the RX 9070's massive compute advantage in general-purpose tasks. The Vulkan test is closer but still decisive: the RX 9070 scores 58705 against 47724, a delta of -18.7%. Vulkan tends to scale well with driver optimization and architectural efficiency, and while the GTX 980 Ti is not embarrassed here, it still trails by nearly a fifth. The recorded data shows zero wins for the GTX 980 Ti in any test, confirming that the RX 9070 is superior in every measured scenario.

Specification Differences

The following fields differ between the two cards as recorded in the database:

• Process node: 28 nm (GTX 980 Ti) vs 4 nm (RX 9070)
• Transistors: 8,000 million vs 53,900 million
• Die size: 601 mm² vs 357 mm²
• Transistor density: 13.3M / mm² vs 151.0M / mm²
• Base clock: 1000 MHz vs 1330 MHz
• Boost clock: 1076 MHz vs 2520 MHz
• Memory clock: 1753 MHz (7 Gbps effective) vs 2518 MHz (20.1 Gbps effective)
• Memory size: 6 GB vs 16 GB
• Memory type: GDDR5 vs GDDR6
• Memory bus width: 384 bit vs 256 bit
• Memory bandwidth: 336.6 GB/s vs 644.6 GB/s
• Shading units: 2816 vs 3584
• TMUs: 176 vs 224
• ROPs: 96 vs 128
• Ray tracing cores: none vs 56
• Pixel rate: 103.3 GPixel/s vs 322.6 GPixel/s
• Texture rate: 189.4 GTexel/s vs 564.5 GTexel/s
• FP32: 6.060 TFLOPS vs 36.13 TFLOPS
• FP16: none recorded vs 36.13 TFLOPS (1:1)
• TDP: 250 W vs 220 W
• Power connectors: 1x 6-pin + 1x 8-pin vs 2x 8-pin
• Suggested PSU: 600 W vs 550 W
• Bus interface: PCIe 3.0 x16 vs PCIe 5.0 x16
• Display outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 vs 1x HDMI 2.1b, 3x DisplayPort 2.1a
• DirectX support: 12 (12_1) vs 12 Ultimate (12_2)
• Production status: End-of-life vs Active
• Release date: 2015-06-01 vs 2025-03-05
• Predecessor: GeForce 700 vs Navi III
• Successor: GeForce 10 vs none recorded
• Launch MSRP: 649 USD vs 549 USD

FAQ

Q: Which card is faster in 3DMark Steel Nomad DX12?

A: The RX 9070 scores 6290 versus the GTX 980 Ti's 1321, a 79% advantage for the RX 9070. This is the largest recorded gap between the two cards.

Q: Does the GTX 980 Ti have any ray tracing hardware?

A: No. The GTX 980 Ti's Maxwell 2.0 architecture has no ray tracing cores recorded. The RX 9070 includes 56 ray tracing cores as part of its RDNA 4.0 design.

Q: How much memory bandwidth does each card provide?

A: The GTX 980 Ti offers 336.6 GB/s over a 384-bit GDDR5 bus, while the RX 9070 provides 644.6 GB/s over a 256-bit GDDR6 bus. Despite the narrower bus, the RX 9070's faster memory clocks deliver nearly double the bandwidth.

Q: Which card is more power efficient per the recorded data?

A: The RX 9070 has a lower TDP at 220 W versus the GTX 980 Ti's 250 W, while delivering far higher performance. It also suggests a lower PSU requirement (550 W vs 600 W).

Q: What is the Vulkan performance difference?

A: In Geekbench Vulkan, the RX 9070 scores 58705 against the GTX 980 Ti's 47724, a lead of 18.7% for the RX 9070. This is the closest benchmark result between the two.

Q: Can the GTX 980 Ti handle modern DirectX 12 Ultimate titles?

A: No. The GTX 980 Ti only supports DirectX 12 (12_1), while the RX 9070 supports DirectX 12 Ultimate (12_2). The RX 9070 is required for full feature set compliance in current-generation games.

Where Each One Wins

The RX 9070 wins every recorded benchmark, so the use-case split is clear. For any modern workload, including 3DMark Steel Nomad DX12, OpenCL compute, and Vulkan gaming, the RX 9070 is the only rational choice. Its 16 GB VRAM and 644.6 GB/s bandwidth make it suitable for high-resolution textures and future game releases. The 56 ray tracing cores add hardware support for ray-traced effects, which the GTX 980 Ti simply cannot offer. The RX 9070's FP16 support at 1:1 ratio also makes it useful for AI-adjacent or mixed-precision workloads, something the GTX 980 Ti cannot do at all.

The GTX 980 Ti's only remaining niche is legacy software. Its 28 nm process and Maxwell 2.0 architecture align with older DirectX 12 (12_1) titles and early Vulkan games. For a retro system running Windows-era games from the mid-2010s, the GTX 980 Ti remains serviceable, and its 6 GB VRAM is adequate for 1080p at that era's settings. However, the database shows its percentile rank among all GPUs is 73, versus the RX 9070's 69, meaning the GTX 980 Ti actually sits higher in the overall distribution despite being far slower in absolute terms. This is due to the RX 9070's lower average benchmark score of 23877 against the GTX 980 Ti's 28020, which includes multiple PassMark tests where the RX 9070 scores very low (e.g., 141 in DirectX 10, 74 in DirectX 12). Those outlier numbers pull its average down, but the head-to-head data is what matters: the RX 9070 wins all three tests decisively.

For practical advice: if you own a GTX 980 Ti and are considering an upgrade, the RX 9070 is a massive step forward in every measurable way. If you are building a new PC, there is no scenario in the recorded data where the GTX 980 Ti is preferable. The RX 9070 also launches at a lower MSRP (549 USD vs 649 USD) and consumes less power (220 W vs 250 W), making it the better choice on all fronts. The GTX 980 Ti belongs in a museum or a pure legacy setup, not in a modern gaming rig.