AMD Radeon RX 7900 XT vs NVIDIA GeForce RTX 5080 Mobile Comparison

The AMD Radeon RX 7900 XT and NVIDIA GeForce RTX 5080 Mobile occupy nearly identical positions in the aggregate benchmark hierarchy, with average scores of 38358 and 38349 respectively, a difference of 0%. This places both in the 81st and 82nd percentiles of all GPUs, respectively. Despite the statistical tie in overall averages, the individual benchmark suite reveals a clear split in workload characteristics, with the desktop AMD part dominating compute-heavy and legacy DirectX tests, while the mobile NVIDIA part shows its strength in specific modern API and geometry-bound scenarios.

Head-to-Head Benchmarks

The most decisive victory for the AMD Radeon RX 7900 XT comes in the Passmark GPU Compute test, where it scores 16828 against the RTX 5080 Mobile's 12134. This 38.7% advantage is the single largest delta in the entire comparison, underscoring a substantial lead in raw parallel processing throughput. The AMD card also secures a commanding 34.4% lead in Passmark DirectX 11, scoring 340 versus 253, indicating better optimization for that legacy API's rendering paths.

In the 3DMark Steel Nomad DX12 test, the AMD Radeon RX 7900 XT posts 5623 points, beating the RTX 5080 Mobile's 4952 by 13.6%. This is a significant win in a modern, demanding benchmark that stresses overall GPU throughput. The AMD card also wins the Passmark G2D test with a score of 1232, a 12.5% improvement over the NVIDIA part's 1095, and the Passmark G3D test with 29009 versus 27711, a 4.7% margin.

The AMD card's wins extend to Geekbench OpenCL, where it scores 169834 versus 166986, a narrow 1.7% lead, and Passmark DirectX 9, where it scores 322 versus 314, a 2.5% margin. In total, the AMD Radeon RX 7900 XT claims 7 out of 10 head-to-head benchmark victories.

The NVIDIA GeForce RTX 5080 Mobile, despite losing the aggregate average by only 9 points, wins three tests. Its largest win is in Passmark DirectX 10, scoring 171 against AMD's 158, a 7.6% advantage. In Geekbench Vulkan, the NVIDIA part scores 169754 compared to AMD's 160119, a 5.7% lead, suggesting a more efficient Vulkan driver or hardware scheduler. The NVIDIA card also edges out AMD in Passmark DirectX 12, scoring 116 versus 110, a 5.2% margin. These three wins highlight that the NVIDIA architecture holds its own in newer, lower-level APIs that are less reliant on raw shader throughput.

Architecture Differences

The two GPUs are built on fundamentally different architectures and design philosophies. The AMD Radeon RX 7900 XT uses the Navi 31 chip based on RDNA 3.0 architecture, with the codename Plum Bonito. It is manufactured on a 5 nm process at TSMC, containing 57,700 million transistors on a 529 mm² die, yielding a transistor density of 109.1M / mm². In contrast, the NVIDIA GeForce RTX 5080 Mobile uses the GB203 chip based on Blackwell 2.0 architecture. It is also built on a 5 nm process at TSMC but packs 45,600 million transistors on a smaller 378 mm² die, resulting in a higher transistor density of 120.6M / mm².

The compute configurations diverge sharply. The AMD card features 5376 shading units, 336 TMUs, and 192 ROPs, while the NVIDIA card has 7680 shading units, 240 TMUs, and only 96 ROPs. This explains the AMD card's massive lead in pixel rate (459.6 GPixel/s versus 144.0 GPixel/s) and texture rate (804.4 GTexel/s versus 360.0 GTexel/s). However, the NVIDIA part compensates with a higher shading unit count. The AMD GPU's FP32 throughput is listed at 51.48 TFLOPS, more than double the RTX 5080 Mobile's 23.04 TFLOPS. The FP16 performance also differs: AMD achieves 103.0 TFLOPS with a 2:1 ratio, while NVIDIA matches its FP32 at 23.04 TFLOPS with a 1:1 ratio.

Memory subsystems are also distinct. The AMD Radeon RX 7900 XT carries 20 GB of GDDR6 on a 320-bit bus, delivering 800.0 GB/s of bandwidth. The NVIDIA GeForce RTX 5080 Mobile has 16 GB of GDDR7 on a 256-bit bus, which achieves a higher bandwidth of 896.0 GB/s. The NVIDIA part's memory clock is listed at 1750 MHz with 28 Gbps effective, while AMD runs at 2500 MHz with 20 Gbps effective. The RTX 5080 Mobile also integrates 240 tensor cores and 60 RT cores, whereas the AMD card has 84 RT cores and no tensor core count listed. The power envelopes are drastically different: the AMD card has a TDP of 300 W, requires 2x 8-pin power connectors, and a 700 W suggested PSU, while the NVIDIA mobile part has an 80 W TDP and is an IGP with no power connectors.

Where Each One Wins

The AMD Radeon RX 7900 XT is the clear winner for compute-heavy workloads and higher-resolution gaming that stresses pixel fill and texture throughput. Its 38.7% lead in Passmark GPU Compute and 34.4% lead in DirectX 11 make it the superior choice for applications that rely on general-purpose GPU computing or legacy API performance. The 13.6% victory in 3DMark Steel Nomad DX12 also suggests it handles modern AAA titles with more headroom, likely due to its 51.48 TFLOPS FP32 throughput and 800.0 GB/s of memory bandwidth, which allows it to push more data through the pipeline.

The NVIDIA GeForce RTX 5080 Mobile wins in scenarios where the workload is bound by driver efficiency in newer APIs rather than raw shader count. Its 5.7% lead in Geekbench Vulkan and 5.2% lead in Passmark DirectX 12 indicate that it extracts more performance per FLOP in these environments. The 7.6% win in DirectX 10 is also notable, as it outperforms the AMD card despite having fewer ROPs. For users on laptops or space-constrained systems, the NVIDIA part's 80 W TDP versus AMD's 300 W TDP is a decisive factor, though this comparison focuses solely on performance metrics.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 7900 XT has an average score of 38358, while the NVIDIA GeForce RTX 5080 Mobile scores 38349, resulting in a 0% delta.

Q: Where does the AMD card have its largest performance advantage?

A: The AMD Radeon RX 7900 XT leads by 38.7% in Passmark GPU Compute and by 34.4% in Passmark DirectX 11.

Q: In which benchmark does the NVIDIA RTX 5080 Mobile perform best relative to the AMD card?

A: The NVIDIA GeForce RTX 5080 Mobile achieves its largest win in Passmark DirectX 10, scoring 171 versus 158, a 7.6% advantage.

Q: How do the memory bandwidths compare between the two?

A: The AMD Radeon RX 7900 XT has a bandwidth of 800.0 GB/s, while the NVIDIA GeForce RTX 5080 Mobile has a higher bandwidth of 896.0 GB/s.

Q: What is the difference in FP32 performance?

A: The AMD Radeon RX 7900 XT delivers 51.48 TFLOPS, which is more than double the NVIDIA GeForce RTX 5080 Mobile's 23.04 TFLOPS.

Q: How many benchmark wins does each GPU have in the head-to-head comparison?

A: The AMD Radeon RX 7900 XT wins 7 benchmarks, while the NVIDIA GeForce RTX 5080 Mobile wins 3.

Specification Differences

| Specification | AMD Radeon RX 7900 XT | NVIDIA GeForce RTX 5080 Mobile |

| :--- | :--- | :--- |

| Chip | Navi 31 | GB203 |

| Architecture | RDNA 3.0 | Blackwell 2.0 |

| Codename | Plum Bonito | null |

| Generation | Navi III (RX 7000) | GeForce 50 Mobile |

| Transistors | 57,700 million | 45,600 million |

| Die Size | 529 mm² | 378 mm² |

| Transistor Density | 109.1M / mm² | 120.6M / mm² |

| Base Clock | 1387 MHz | 975 MHz |

| Boost Clock | 2394 MHz | 1500 MHz |

| Memory Size | 20 GB | 16 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus Width | 320 bit | 256 bit |

| Memory Bandwidth | 800.0 GB/s | 896.0 GB/s |

| Shading Units | 5376 | 7680 |

| TMUs | 336 | 240 |

| ROPs | 192 | 96 |

| RT Cores | 84 | 60 |

| Tensor Cores | null | 240 |

| Pixel Rate | 459.6 GPixel/s | 144.0 GPixel/s |

| Texture Rate | 804.4 GTexel/s | 360.0 GTexel/s |

| FP32 Performance | 51.48 TFLOPS | 23.04 TFLOPS |

| FP16 Performance | 103.0 TFLOPS (2:1) | 23.04 TFLOPS (1:1) |

| TDP | 300 W | 80 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 700 W | null |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Display Outputs | 1x HDMI 2.1a, 2x DisplayPort 2.1, 1x USB Type-C | Portable Device Dependent |

| Production Status | End-of-life | Active |

| Release Date | 2022-11-02 | 2025-04-01 |

| Predecessor | Navi II | GeForce 40 Mobile |

| Successor | Navi IV | null |