AMD Radeon RX 560 vs NVIDIA GeForce GTX 980M Comparison

Head-to-Head Benchmarks

The benchmark data delivers a decisive verdict: the NVIDIA GeForce GTX 980M wins all eight recorded head-to-head comparisons against the AMD Radeon RX 560. The most lopsided result comes in PassMark G3D, where the GTX 980M scores 7,338 versus 3,671 for the RX 560, a 99.9% advantage. This is nearly double the frame throughput in the generalized 3D graphics workload, which sets the tone for the rest of the comparison.

In DirectX 11, the gap is even more pronounced on a percentage basis. The GTX 980M posts 57 points against 25 for the RX 560, a 128% lead. DirectX 9 tells a similar story: 125 versus 57, a 119.3% margin. The older API results suggest the Maxwell architecture retains a strong legacy driver and shader pipeline advantage over GCN 4.0 in these specific tests. Even in DirectX 12, where AMD's architecture is often considered more competitive, the GTX 980M leads 31 to 21, a 47.6% difference. The RX 560 cannot close the gap in any API generation, which indicates a consistent raw performance deficit rather than a workload-specific weakness.

Compute workloads follow the same pattern. In Geekbench OpenCL, the GTX 980M scores 23,832 versus 16,472, a 44.7% lead. PassMark GPU Compute shows 2,816 versus 1,437, a 96% advantage. The GTX 980M's higher shading unit count and wider memory bus translate directly into compute throughput. The RX 560, despite its newer 14 nm process and higher clock speeds, cannot overcome the architectural scaling disadvantage.

The closest contest is PassMark G2D, where the GTX 980M scores 490 and the RX 560 scores 485, a mere 1% difference. This 2D graphics test is nearly a tie, which makes sense given that both cards share similar memory types and the workload is not compute-bound. However, even this narrow win belongs to NVIDIA, so the sweep is complete: 8 wins for the GTX 980M, 0 for the RX 560.

Where Each One Wins

The GTX 980M wins everywhere in the recorded benchmarks, but the magnitude of the win varies by workload type. The largest advantages appear in legacy DirectX 9 and DirectX 11 tests, where the GTX 980M leads by over 119% and 128% respectively. This suggests the Maxwell 2.0 architecture is particularly well optimized for older API paths, likely due to mature driver tuning and higher raw texture and pixel throughput. The GTX 980M also dominates compute-heavy workloads, with a 96% lead in PassMark GPU Compute and a 44.7% lead in Geekbench OpenCL. For users running general-purpose GPU tasks, OpenCL acceleration, or older DirectX titles, the GTX 980M is the clear choice.

The RX 560 has no benchmark wins, but it is not without relative strengths. Its closest result is the G2D test, where it trails by only 1%. In DirectX 12, the RX 560 narrows the gap to 47.6%, which is still a loss but better than its DirectX 11 performance. This indicates that GCN 4.0 is comparatively less disadvantaged in newer API workloads, though it never reaches parity. The RX 560 also offers a lower power footprint, with a 75 W TDP and a suggested 250 W PSU, versus the GTX 980M's MXM module form factor and no specified TDP. For systems constrained by power delivery or physical space, the RX 560's Dual-slot PCIe card with no power connectors may be easier to integrate, even if it loses every performance benchmark.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 980M is the faster GPU in every recorded benchmark. Its average benchmark score is 5,308, placing it in the 31st percentile of all GPUs, while the RX 560 averages 4,569 and sits in the 26th percentile. The GTX 980M also outperforms its nearest rivals, including the NVIDIA GeForce 930A (5,317, -0.2% delta) and the NVIDIA GeForce 840M (5,322, -0.3% delta), while the RX 560's closest competitor is the AMD Radeon R5 M230 (4,577, -0.2% delta) and the Intel HD Graphics P530 (4,560, 0.2% delta). In direct comparison, the GTX 980M leads the RX 560 by 16.2% in average score, which is consistent with the head-to-head margins.

Who should pick the GTX 980M? Anyone prioritizing raw graphics performance, especially in DirectX 9, DirectX 11, or compute workloads. The 8 GB GDDR5 memory on a 256-bit bus provides 160.4 GB/s of bandwidth, more than double the RX 560's 112.0 GB/s on a 128-bit bus. The 1,536 shading units, 96 TMUs, and 64 ROPs deliver 3.462 TFLOPS of FP32 throughput, far above the RX 560's 2.611 TFLOPS. For legacy games or OpenCL acceleration, the GTX 980M is the superior choice.

Who should pick the RX 560? Only those who require a modern PCIe 3.0 x8 card with DisplayPort 1.4a and HDMI 2.0b outputs, or who need a 75 W TDP card with no external power connectors. The RX 560 also supports FP16 at a 1:1 ratio, which the GTX 980M lacks, and it has a smaller die (123 mm² versus 398 mm²) with a higher transistor density (24.4M per mm² versus 13.1M per mm²). But in pure performance, the RX 560 loses every test. The verdict is straightforward: the GTX 980M dominates, and the RX 560 is only relevant for specific form-factor or power constraints.

FAQ

Q: Which GPU wins in DirectX 12 performance?

A: The NVIDIA GeForce GTX 980M wins, scoring 31 in PassMark DirectX 12 versus 21 for the AMD Radeon RX 560, a 47.6% lead.

Q: How much faster is the GTX 980M in OpenCL compute?

A: The GTX 980M scores 23,832 in Geekbench OpenCL, while the RX 560 scores 16,472, giving the NVIDIA card a 44.7% advantage.

Q: What is the memory bandwidth difference between the two?

A: The GTX 980M has 160.4 GB/s of bandwidth from 8 GB GDDR5 on a 256-bit bus. The RX 560 has 112.0 GB/s from 4 GB GDDR5 on a 128-bit bus.

Q: Does the RX 560 win any benchmark?

A: No. In the head-to-head comparison, the GTX 980M wins all 8 recorded tests, with the closest margin being 1% in PassMark G2D.

Q: What is the average benchmark score for each card?

A: The GTX 980M averages 5,308, while the RX 560 averages 4,569. The GTX 980M also ranks in the 31st percentile of all GPUs, versus the 26th percentile for the RX 560.

Q: Which GPU has a higher pixel rate?

A: The GTX 980M delivers 72.13 GPixel/s, while the RX 560 delivers 20.40 GPixel/s, a difference of over 3.5 times in favor of NVIDIA.

Architecture Differences

The GTX 980M uses the GM204 chip on a 28 nm TSMC process, built on the Maxwell 2.0 architecture. It contains 5,200 million transistors on a 398 mm² die, yielding a transistor density of 13.1M per mm². The RX 560 uses the Polaris 21 chip on a 14 nm GlobalFoundries process, built on GCN 4.0. It contains 3,000 million transistors on a 123 mm² die, with a much higher density of 24.4M per mm². The newer process allows the RX 560 to pack more transistors per area, but the GTX 980M's larger die provides more absolute resources.

The GTX 980M has 1,536 shading units, 96 TMUs, and 64 ROPs, while the RX 560 has 1,024 shading units, 64 TMUs, and 16 ROPs. This 50% advantage in shading units and 3x advantage in ROPs explains the GTX 980M's higher pixel rate (72.13 GPixel/s versus 20.40 GPixel/s) and texture rate (108.2 GTexel/s versus 81.60 GTexel/s). The GTX 980M also achieves higher FP32 throughput (3.462 TFLOPS versus 2.611 TFLOPS), while the RX 560 uniquely supports FP16 at a 1:1 ratio, a feature the GTX 980M lacks.

Clock speeds favor the RX 560, with a base of 1,175 MHz and boost of 1,275 MHz, versus the GTX 980M's 1,038 MHz base and 1,127 MHz boost. Memory clocks also favor AMD: 7 Gbps effective versus 5 Gbps effective. However, the GTX 980M's wider 256-bit bus compensates with higher total bandwidth. API support differs slightly: the GTX 980M supports DirectX 12 (12_1) and Vulkan 1.4, while the RX 560 supports DirectX 12 (12_0) and Vulkan 1.3. Both support OpenGL 4.6.

Specification Differences

The two cards differ in nearly every physical and performance specification. The GTX 980M is an MXM Module with an MXM-B (3.0) bus interface, while the RX 560 is a Dual-slot PCIe 3.0 x8 card. The GTX 980M has no power connectors and its display outputs are listed as portable device dependent, while the RX 560 has no power connectors either but offers 1x DVI, 1x HDMI 2.0b, and 1x DisplayPort 1.4a. The RX 560 has a specified TDP of 75 W and a suggested PSU of 250 W, while the GTX 980M has no TDP or PSU data in the database.

Memory configurations differ significantly: the GTX 980M has 8 GB GDDR5 on a 256-bit bus, while the RX 560 has 4 GB GDDR5 on a 128-bit bus. This yields bandwidth of 160.4 GB/s versus 112.0 GB/s. The GTX 980M has 1,536 shading units, 96 TMUs, and 64 ROPs, while the RX 560 has 1,024 shading units, 64 TMUs, and 16 ROPs. Pixel rate is 72.13 GPixel/s for NVIDIA versus 20.40 GPixel/s for AMD. Texture rate is 108.2 GTexel/s versus 81.60 GTexel/s. FP32 is 3.462 TFLOPS versus 2.611 TFLOPS. The RX 560 adds FP16 at 2.611 TFLOPS, which the GTX 980M does not support. The GTX 980M measures a die size of 398 mm², while the RX 560 measures 123 mm². Release dates also differ: the GTX 980M launched on October 6, 2014, while the RX 560 launched on April 17, 2017. The RX 560 has a launch MSRP of 99 USD.