AMD Radeon R9 M290X vs AMD Radeon RX 5600 XT Comparison

# The Verdict

The AMD Radeon RX 5600 XT is the decisive winner in every recorded head-to-head benchmark. In Geekbench Metal, it scores 80,376 against 24,524 for the Radeon R9 M290X, a 69.5% gap. In Geekbench OpenCL, the RX 5600 XT posts 68,537 versus 22,028, a 67.9% margin. The data leaves no ambiguity: the RX 5600 XT is the faster GPU by a wide margin, and any workload that leverages Metal or OpenCL will see a massive advantage.

That said, the R9 M290X holds a different kind of value. It sits at the 68th percentile of all GPUs in the database, slightly above the RX 5600 XT's 66th percentile, despite scoring far lower on the two shared benchmarks. This is because the R9 M290X's average benchmark score of 23,276 is actually higher than the RX 5600 XT's average of 20,713. The R9 M290X's nearest rivals in that average are the AMD Radeon RX 6600M (23,273, 0% delta) and the AMD Radeon AI PRO R9700 (23,315, -0.2% delta), placing it in a performance tier that is competitive with those parts. The RX 5600 XT's nearest rivals include the AMD Radeon R9 M390X (20,662, 0.2% delta) and the Intel Arc A750 (20,582, 0.6% delta).

So who should pick which? If the task is raw graphics compute in current-generation APIs or high-resolution gaming, the RX 5600 XT is the clear choice. If the requirement is a low-power, mobile-oriented MXM module with a lighter footprint and the workload is older or compute-light, the R9 M290X remains a viable option, especially given its higher percentile ranking in the broader database. The RX 5600 XT is a desktop-class part with a dual-slot cooler, a 150 W TDP, and a PCIe 4.0 interface; the R9 M290X is a 100 W MXM module with no external power connectors, designed for portable systems.

# Architecture Differences

The two GPUs come from entirely different architectural eras. The Radeon R9 M290X uses the Neptune chip built on GCN 1.0, fabricated on a 28 nm process at TSMC with 2,800 million transistors on a 212 mm² die, yielding a transistor density of 13.2 million transistors per mm². The Radeon RX 5600 XT uses the Navi 10 chip on RDNA 1.0, built on a 7 nm process at TSMC with 10,300 million transistors on a 251 mm² die, for a density of 41.0 million transistors per mm². That is roughly three times the transistor density, which explains much of the performance gap.

The R9 M290X belongs to the Gem System generation (R9 M200 series), released in January 2014, with its predecessor noted as Solar System and successor as Polaris Mobile. The RX 5600 XT belongs to the Navi (RX 5000) generation, released in January 2020, with its predecessor as Vega and successor as Navi II. The RX 5600 XT supports DirectX 12 (12_1), Vulkan 1.4, and OpenGL 4.6; the R9 M290X supports DirectX 12 (11_1), Vulkan 1.2.170, and OpenGL 4.6. The newer part also exposes FP16 at 14.38 TFLOPS (2:1 ratio) while the older part has no recorded FP16 figure.

Memory architecture differs substantially. The R9 M290X has 4 GB of GDDR5 on a 256-bit bus with 153.6 GB/s bandwidth, while the RX 5600 XT has 6 GB of GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth. The newer memory type and higher effective data rate (12 Gbps versus 4.8 Gbps) give the RX 5600 XT nearly double the bandwidth despite a narrower bus. The R9 M290X's memory clock is 1200 MHz (4.8 Gbps effective) versus 1500 MHz (12 Gbps effective) for the RX 5600 XT.

The RX 5600 XT also has more execution resources: 2,304 shading units, 144 texture mapping units, and 64 ROPs, compared to 1,280 shading units, 80 TMUs, and 32 ROPs on the R9 M290X. Pixel rate on the RX 5600 XT is 99.84 GPixel/s versus 28.80 GPixel/s, and texture rate is 224.6 GTexel/s versus 72.00 GTexel/s. The FP32 throughput is 7.188 TFLOPS versus 2.304 TFLOPS.

# Head-to-Head Benchmarks

The two recorded head-to-head tests are Geekbench Metal and Geekbench OpenCL, and the RX 5600 XT wins both by a wide margin.

In Geekbench Metal, the RX 5600 XT scores 80,376, while the R9 M290X scores 24,524. The delta is 69.5% in favor of the RX 5600 XT. This is not a marginal win; it is a complete outclassing in a modern graphics API. The R9 M290X's Metal score is less than a third of the RX 5600 XT's, indicating that the older GCN 1.0 architecture is severely limited in this workload.

In Geekbench OpenCL, the RX 5600 XT scores 68,537, against 22,028 for the R9 M290X, a 67.9% delta. Again, the RX 5600 XT is nearly three times faster. OpenCL is a common compute workload, and the gap here confirms that the RX 5600 XT's architectural advantages (more shading units, higher clocks, more bandwidth, newer process) translate directly into compute performance.

The RX 5600 XT also has a larger benchmark suite in the database, including 3DMark Steel Nomad DX12 (1,669), Geekbench Vulkan (56,218), and Passmark tests across DirectX 9 through 12, plus G2D (870), G3D (13,457), and GPU compute (6,296). The R9 M290X has no recorded scores for these tests, so the comparison is limited to the two shared benchmarks. However, the RX 5600 XT's average benchmark score of 20,713 across its suite is lower than the R9 M290X's average of 23,276 across its two tests, which suggests the R9 M290X performs relatively better in its own test set, likely due to the lighter workload requirements.

# FAQ

Q: Which GPU has the higher average benchmark score?

A: The R9 M290X has an average benchmark score of 23,276, while the RX 5600 XT has an average of 20,713. Despite this, the RX 5600 XT wins both head-to-head tests by margins of roughly 68% to 70%.

Q: Does the RX 5600 XT support newer DirectX features than the R9 M290X?

A: Yes. The RX 5600 XT supports DirectX 12 (12_1), while the R9 M290X supports DirectX 12 (11_1). Both support OpenGL 4.6, but the RX 5600 XT has Vulkan 1.4 versus Vulkan 1.2.170 for the older part.

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

A: The RX 5600 XT has 288.0 GB/s bandwidth from 6 GB of GDDR6 on a 192-bit bus, while the R9 M290X has 153.6 GB/s from 4 GB of GDDR5 on a 256-bit bus. The RX 5600 XT offers nearly double the bandwidth.

Q: Which GPU has higher transistor density?

A: The RX 5600 XT has a transistor density of 41.0 million transistors per mm² on a 7 nm process, compared to 13.2 million per mm² for the R9 M290X on a 28 nm process.

Q: Are there any benchmark tests where the R9 M290X wins?

A: In the recorded head-to-head data, the R9 M290X wins zero tests. The RX 5600 XT wins both the Geekbench Metal and Geekbench OpenCL tests. However, the R9 M290X has a higher percentile ranking, 68th versus 66th, and a higher average benchmark score.

Q: What are the nearest rivals for each GPU based on average score?

A: For the R9 M290X, the nearest rivals are the AMD Radeon RX 6600M (23,273, 0% delta) and the AMD Radeon AI PRO R9700 (23,315, -0.2% delta). For the RX 5600 XT, the nearest rivals are the AMD Radeon R9 M390X (20,662, 0.2% delta) and the Intel Arc A750 (20,582, 0.6% delta).

# Where Each One Wins

The RX 5600 XT wins in every scenario where raw graphics compute and modern API performance matter. Its Geekbench Metal score of 80,376 is more than three times the R9 M290X's 24,524, making it the obvious choice for Metal-based applications on macOS or iOS-like environments. Its OpenCL score of 68,537 versus 22,028 confirms dominance in compute-heavy tasks such as rendering, physics simulation, or data-parallel workloads. The RX 5600 XT also offers 6 GB of GDDR6 memory with 288.0 GB/s bandwidth, which is better suited for modern game assets and higher resolutions. Its PCIe 4.0 x16 interface, dual-slot cooler, and 1x 8-pin power connector indicate a desktop-oriented design that can sustain higher performance under load.

The R9 M290X wins in the narrow case of power-constrained or space-constrained systems. Its 100 W TDP is 50 W lower than the RX 5600 XT's 150 W, and it uses an MXM module form factor with no external power connectors, making it drop-in compatible with many laptops and small-form-factor systems. Its 28 nm process and 4 GB of GDDR5 memory are older, but the GPU's 68th percentile ranking versus the RX 5600 XT's 66th suggests that in the broader database context, the R9 M290X is not far behind in relative standing. For workloads that are not Metal or OpenCL heavy, such as older DirectX 11 titles or light 2D tasks, the R9 M290X's lower power draw and modular design could be preferable.

The RX 5600 XT also has a much richer benchmark profile in the database, with scores for 3DMark Steel Nomad DX12 (1,669), Geekbench Vulkan (56,218), and Passmark DirectX 9 through 12 tests, plus G2D (870), G3D (13,457), and GPU compute (6,296). This indicates it is tested across a broader range of workloads, whereas the R9 M290X only has Geekbench Metal and OpenCL results.

# Specification Differences

The two GPUs differ on nearly every key specification. The R9 M290X uses the Neptune chip on GCN 1.0 architecture, while the RX 5600 XT uses Navi 10 on RDNA 1.0. The process node is 28 nm for the older part versus 7 nm for the newer, with transistor counts of 2,800 million versus 10,300 million, and die sizes of 212 mm² versus 251 mm². Transistor density is 13.2 million per mm² versus 41.0 million per mm².

Clock speeds: the R9 M290X has a base clock of 850 MHz and boost of 900 MHz, while the RX 5600 XT has a base of 1130 MHz, game clock of 1375 MHz, and boost of 1560 MHz. Memory clocks are 1200 MHz (4.8 Gbps effective) for the R9 M290X versus 1500 MHz (12 Gbps effective) for the RX 5600 XT.

Memory: 4 GB GDDR5 on a 256-bit bus with 153.6 GB/s bandwidth versus 6 GB GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth. Shading units: 1,280 versus 2,304. TMUs: 80 versus 144. ROPs: 32 versus 64. Pixel rate: 28.80 GPixel/s versus 99.84 GPixel/s. Texture rate: 72.00 GTexel/s versus 224.6 GTexel/s. FP32: 2.304 TFLOPS versus 7.188 TFLOPS. The RX 5600 XT also records FP16 at 14.38 TFLOPS (2:1) while the R9 M290X has no FP16 figure.

TDP: 100 W versus 150 W. Slot width: MXM Module versus Dual-slot. Power connectors: None versus 1x 8-pin. The RX 5600 XT lists a suggested PSU of 450 W, while the R9 M290X has none. Bus interface: PCIe 3.0 x16 versus PCIe 4.0 x16. Display outputs: the R9 M290X is "Portable Device Dependent" while the RX 5600 XT has 1x HDMI 2.0b and 3x DisplayPort 1.4a. Dimensions: the RX 5600 XT is 267 mm (10.5 inches) long; the R9 M290X has no recorded length.

Release dates: January 8, 2014 for the R9 M290X versus January 20, 2020 for the RX 5600 XT. The RX 5600 XT has a launch MSRP of 279 USD. Both are end-of-life, but the RX 5600 XT's successor is Navi II, while the R9 M290X's successor is Polaris Mobile. The RX 5600 XT supports Vulkan 1.4 versus Vulkan 1.2.170, and DirectX 12 (12_1) versus DirectX 12 (11_1).