AMD Radeon Pro 580X vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains two directly comparable benchmark results between the NVIDIA GeForce RTX 5090 Mobile and the AMD Radeon Pro 580X. In both tests, the NVIDIA part delivers a commanding victory.

In Geekbench OpenCL, the RTX 5090 Mobile scores 201,834 points against 36,426 points for the Radeon Pro 580X. That is a delta of 454.1% in favor of the NVIDIA GPU. The margin is not incremental; it represents a multiple of the AMD part's raw compute output in this cross-platform API test.

Geekbench Vulkan tells a similar story. The RTX 5090 Mobile records 198,405 points, while the Radeon Pro 580X manages 40,115 points. The resulting delta is 394.6% in favor of NVIDIA. Although the absolute scores differ slightly between OpenCL and Vulkan for both cards, the proportional gap remains consistently enormous.

The NVIDIA GPU also holds a substantial advantage in the aggregate benchmark average. Its average benchmark score across all recorded tests is 45,152, compared to 38,706 for the AMD Radeon Pro 580X. That is a relatively modest overall gap of roughly 16.7%, but it is important to note that the two cards share only two common benchmarks in the database. The average figures draw on different test sets, so the aggregate comparison should be weighed alongside the head-to-head results.

The RTX 5090 Mobile's wider benchmark portfolio includes additional tests that are not present for the Radeon Pro 580X. In 3DMark Steel Nomad (DX12), it scores 5,871. In Passmark G3D, it reaches 30,034, with a GPU compute score of 13,401. The Radeon Pro 580X has no corresponding entries for these tests, so direct comparison is not possible there.

The Radeon Pro 580X does have one exclusive benchmark result: Geekbench Metal, where it scores 39,577. This test cannot be run on the NVIDIA card, as Metal support is outside its API set. Still, the number offers context for AMD's compute performance in Apple-centric workloads.

When placed against its nearest rivals in the database, the RTX 5090 Mobile sits 0.5% below the AMD Radeon Pro 5500 XT, 0.8% above the NVIDIA GeForce RTX 4070 Ti, 1% below the Intel Arc A730M, and 1.8% below the NVIDIA RTX 5880 Ada Generation. These are tight margins, indicating that the RTX 5090 Mobile's average score places it in a competitive cluster despite its dominant head-to-head showing against the Radeon Pro 580X.

The Radeon Pro 580X, meanwhile, matches the NVIDIA GeForce MX570 A exactly (0% delta), sits 0.9% below the NVIDIA GeForce RTX 5080 Mobile, 1.1% below the NVIDIA GeForce MX570, and 1% above the AMD Radeon Pro 575X. Its 82nd percentile ranking across all GPUs is close to the RTX 5090 Mobile's 84th percentile, but the head-to-head results reveal a far larger performance separation than the percentile positions suggest.

FAQ

Q: How much faster is the NVIDIA GeForce RTX 5090 Mobile than the AMD Radeon Pro 580X in OpenCL?

A: The RTX 5090 Mobile scores 201,834 in Geekbench OpenCL versus 36,426 for the Radeon Pro 580X, a 454.1% advantage for NVIDIA.

Q: Does the Radeon Pro 580X win any benchmark against the RTX 5090 Mobile?

A: No. In the two shared tests (Geekbench OpenCL and Geekbench Vulkan), the RTX 5090 Mobile wins both. The Radeon Pro 580X has no recorded victory in any head-to-head benchmark.

Q: What is the only benchmark unique to the AMD card?

A: Geekbench Metal, where the Radeon Pro 580X scores 39,577. The RTX 5090 Mobile has no Metal result because it does not support that API.

Q: How do the two cards compare in aggregate average score?

A: The RTX 5090 Mobile has an average benchmark score of 45,152 across all its recorded tests, while the Radeon Pro 580X averages 38,706. The NVIDIA card is ahead by roughly 16.7% in this metric.

Q: Where does the RTX 5090 Mobile rank relative to its nearest rivals?

A: Its average score is 0.5% below the AMD Radeon Pro 5500 XT, 0.8% above the NVIDIA GeForce RTX 4070 Ti, 1% below the Intel Arc A730M, and 1.8% below the NVIDIA RTX 5880 Ada Generation.

Q: What is the Radeon Pro 580X's closest competitor in the database?

A: The NVIDIA GeForce MX570 A, with a 0% delta in average score. The Radeon Pro 580X also sits 0.9% below the RTX 5080 Mobile and 1.1% below the GeForce MX570.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip built on the Blackwell 2.0 architecture, manufactured by TSMC on a 5 nm process. The AMD Radeon Pro 580X uses the Ellesmere chip with GCN 4.0 architecture, produced by GlobalFoundries on a 14 nm process. The node difference alone explains much of the efficiency gap between them.

Transistor counts reflect the generational chasm. The RTX 5090 Mobile integrates 45,600 million transistors on a die size of 378 mm², yielding a density of 120.6 million transistors per square millimeter. The Radeon Pro 580X has 5,700 million transistors on a 232 mm² die, which works out to 24.6 million per square millimeter. NVIDIA's part carries roughly eight times as many transistors in a die that is only about 63% larger.

Compute resources are drastically skewed toward NVIDIA. The RTX 5090 Mobile has 10,496 shading units, 328 texture mapping units, 82 RT cores, and 328 tensor cores. The Radeon Pro 580X has 2,304 shading units and 144 TMUs, with no RT cores and no tensor cores. The NVIDIA GPU is built for ray tracing and AI acceleration; the AMD card predates both as a standard component of its feature set.

Memory technology also separates the two. The RTX 5090 Mobile uses 24 GB of GDDR7 on a 256 bit bus, delivering 896.0 GB/s of bandwidth. The Radeon Pro 580X carries 8 GB of GDDR5 on a 256 bit bus, for 218.9 GB/s. Both use the same bus width, but the newer memory type and higher capacity give NVIDIA a fourfold bandwidth advantage.

API support differs as well. The RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Radeon Pro 580X supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The NVIDIA card's DirectX 12 Ultimate designation includes features not available in the older AMD part's 12_0 profile.

The Radeon Pro 580X is designed for Apple MPX bus interface with 2x HDMI 2.0b display outputs, and its generation is listed as Radeon Pro Mac (500X Series). Production status is end-of-life. The RTX 5090 Mobile uses PCIe 5.0 x16, has display outputs marked as portable device dependent, and is still in active production.

Specification Differences

The NVIDIA GeForce RTX 5090 Mobile and AMD Radeon Pro 580X differ in nearly every recorded specification field. Process node: 5 nm versus 14 nm. Foundry: TSMC versus GlobalFoundries. Architecture: Blackwell 2.0 versus GCN 4.0.

Clock speeds are not directly comparable in a simple sense. The RTX 5090 Mobile has a base clock of 990 MHz and a boost of 1515 MHz. The Radeon Pro 580X has a base clock of 1100 MHz and a boost of 1200 MHz. AMD actually starts at a higher base frequency, but NVIDIA's boost ceiling is much higher, and the NVIDIA card's performance lead in benchmarks shows that raw clock rate is not the deciding factor.

Memory specifications diverge sharply. The RTX 5090 Mobile has 24 GB of GDDR7 at 1750 MHz (28 Gbps effective), with 896.0 GB/s bandwidth. The Radeon Pro 580X has 8 GB of GDDR5 at 1710 MHz (6.8 Gbps effective), with 218.9 GB/s bandwidth. The bus width is identical at 256 bit, but capacity, memory type, effective speed, and bandwidth all favor NVIDIA.

Compute throughput numbers illustrate the scale of difference. The RTX 5090 Mobile delivers 31.80 TFLOPS FP32 and 31.80 TFLOPS FP16 (1:1). The Radeon Pro 580X delivers 5.530 TFLOPS FP32 and 5.530 TFLOPS FP16 (1:1). That is roughly 5.75 times higher FP32 throughput for NVIDIA. Pixel rate is 169.7 GPixel/s versus 38.40 GPixel/s, and texture rate is 496.9 GTexel/s versus 172.8 GTexel/s.

Power draw runs in the opposite direction. The RTX 5090 Mobile has a TDP of 95 W and no power connectors, while the Radeon Pro 580X has a TDP of 185 W. Despite drawing nearly twice as much power, the AMD card delivers far lower performance in the shared benchmarks. The Radeon Pro 580X's higher power consumption with lower output makes the efficiency gap stark.

Release timing also differs. The RTX 5090 Mobile launched on 2025-03-26, while the Radeon Pro 580X launched on 2019-03-17. Six years of architectural progress separate the two, which explains much of the performance differential.

Where Each One Wins

The NVIDIA GeForce RTX 5090 Mobile wins in every measurable category where both cards have data. It is faster in OpenCL, faster in Vulkan, has a higher average benchmark score, more memory, higher bandwidth, newer architecture, and lower power draw. Its wins are not marginal; the head-to-head deltas of 454.1% and 394.6% place it in a completely different performance tier.

The Radeon Pro 580X's only exclusive benchmark result is Geekbench Metal, where it scores 39,577. This gives it a niche: Apple ecosystem compute workloads that require the Metal API. The RTX 5090 Mobile cannot run Metal benchmarks at all, so for users constrained to that API, the AMD card is the only option between the two.

The RTX 5090 Mobile's tensor cores and RT cores make it suitable for AI acceleration and hardware ray tracing, capabilities the Radeon Pro 580X lacks entirely. Its 24 GB of GDDR7 memory with 896.0 GB/s bandwidth supports large datasets and high-resolution textures. The 82 RT cores and 328 tensor cores are not present in the AMD part at all.

The Radeon Pro 580X's advantages are limited to its exclusive Metal support and its different bus interface (Apple MPX). It also has a different display output configuration with 2x HDMI 2.0b, which may suit specific workstation setups. Its 8 GB of GDDR5 is far smaller, but for legacy software targeting its API set, it remains functional.

The Verdict

The data supports a clear conclusion: the NVIDIA GeForce RTX 5090 Mobile is the superior GPU in nearly every recorded metric. It wins both shared benchmarks by margins exceeding 394%, offers roughly 5.75 times the FP32 throughput, provides three times the memory capacity, and consumes 90 W less power. Its 84th percentile ranking versus the Radeon Pro 580X's 82nd percentile understates the gap because the two cards share few benchmarks, and the shared ones overwhelmingly favor NVIDIA.

The Radeon Pro 580X should only be selected by users who specifically require Metal API support or Apple MPX bus compatibility. Its Geekbench Metal score of 39,577 is its only recorded benchmark result that the RTX 5090 Mobile cannot contest. For any workload that uses OpenCL or Vulkan, the RTX 5090 Mobile is dramatically faster.

For general mobile graphics, compute, ray tracing, or AI tasks, the RTX 5090 Mobile is the clear choice. Its active production status, newer architecture, lower power draw, and massive performance lead make it the only rational pick from the recorded data. The Radeon Pro 580X is end-of-life and belongs to a 2019-era architecture that cannot compete with the 2025 Blackwell design.

The one scenario where the Radeon Pro 580X wins is a narrow one: a Mac-based system requiring Metal performance and Apple MPX integration, where the RTX 5090 Mobile is not a viable alternative. Outside that context, the verdict is unambiguous.