AMD Radeon RX 7700 vs NVIDIA GeForce RTX 5090 SE Comparison

FAQ

Q: What is the fundamental positioning of the AMD Radeon RX 7700 versus the NVIDIA GeForce RTX 5090 SE?

A: The RX 7700 is an RDNA 3.0 part from the Radeon RX 7000 series, built on the Navi 32 chip with a 5 nm process. The RTX 5090 SE is a Blackwell 2.0 part from the GeForce 50-series, built on the GB202 chip, also on a 5 nm process. The database records the RX 7700 as having an active production status with a release date of 2025-09-17, while the RTX 5090 SE is also active with a release date of 2025-12-31.

Q: How do the memory subsystems compare between these two GPUs?

A: The RX 7700 uses 16 GB of GDDR6 on a 256-bit bus, delivering 624.1 GB/s of bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus, delivering 1.34 TB/s of bandwidth. The RTX 5090 SE also has a higher effective memory clock at 28 Gbps versus 19.5 Gbps for the RX 7700.

Q: What are the core counts for each GPU?

A: The RX 7700 has 2560 shading units, 160 texture mapping units, 96 ROPs, and 40 ray tracing cores. The RTX 5090 SE has 14080 shading units, 440 TMUs, 160 ROPs, and 110 RT cores. The RTX 5090 SE also includes 440 tensor cores, while the RX 7700 has no tensor cores listed.

Q: Which GPU has a higher power requirement according to the database?

A: The RX 7700 has a TDP of 200 W with a suggested PSU of 550 W, using two 8-pin power connectors. The RTX 5090 SE has a TDP of 500 W with a suggested PSU of 900 W, using a single 16-pin connector.

Q: What does the benchmark data show for the RX 7700?

A: The RX 7700 has an average benchmark score of 15852, placing it in the 58th percentile of all GPUs. Its best recorded score is 106028 in Geekbench OpenCL, and its lowest is 92 in Passmark DirectX 10. The RTX 5090 SE has no benchmark scores recorded in the database, with an average score of 0 and a 50th percentile ranking.

Where Each One Wins

The recorded data splits the two GPUs into separate domains. The RX 7700 has a full set of benchmark results, while the RTX 5090 SE has none. This means the RX 7700 wins every measured test by definition, but that is a function of data availability rather than architectural comparison.

For the RX 7700, the strongest recorded result is in Geekbench OpenCL at 106028, which is more than five times its Passmark G3D score of 20974. The Passmark GPU Compute score of 10963 is roughly half of the Geekbench OpenCL result, indicating compute-oriented workloads show a different scaling pattern than graphics workloads. The Passmark DirectX 9 score of 261 is the highest among the Passmark DirectX tests, followed by DirectX 11 at 186, DirectX 12 at 96, and DirectX 10 at 92.

The RTX 5090 SE has no recorded wins because the database contains no benchmark entries for it. Its percentile rank of 50 suggests it sits at the median of all GPUs in the database, but without scores, no workload-specific advantage can be quantified.

Architecture Differences

The RX 7700 uses the Navi 32 chip with RDNA 3.0 architecture, codenamed Wheat Nas, from the Navi III generation. It has 28,100 million transistors on a 346 mm² die, resulting in a transistor density of 81.2M per mm². The RTX 5090 SE uses the GB202 chip with Blackwell 2.0 architecture from the GeForce 50 generation. It has 92,200 million transistors on a 750 mm² die, giving a density of 122.9M per mm².

Both chips are fabricated by TSMC on a 5 nm process, but the RTX 5090 SE packs more than three times the transistors into roughly double the die area. The RTX 5090 SE also has a significantly higher transistor density, indicating a denser layout. The RX 7700 has a 1:1 ratio for FP16 to FP32 at 25.18 TFLOPS each, while the RTX 5090 SE also shows 1:1 FP16 to FP32 at 66.94 TFLOPS each.

The RX 7700 has 40 RT cores and no tensor cores. The RTX 5090 SE has 110 RT cores and 440 tensor cores. This tensor core count is a distinguishing feature, as the RX 7700 has no equivalent hardware listed. The RTX 5090 SE also has significantly more shading units, TMUs, and ROPs: 14080 versus 2560 shading units, 440 versus 160 TMUs, and 160 versus 96 ROPs.

The bus interface differs as well, with the RX 7700 using PCIe 4.0 x16 and the RTX 5090 SE using PCIe 5.0 x16. This could affect data transfer rates in CPU-bound scenarios, though the database does not provide specific measurements for that difference.

Specification Differences

Clock speeds differ in both base and boost. The RX 7700 has a base clock of 1900 MHz, a boost clock of 2459 MHz, and a game clock of 2041 MHz. The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz, with no game clock listed. The RX 7700 has a higher base clock by 160 MHz and a higher boost clock by 82 MHz.

Memory clocks also differ. The RX 7700 runs at 2438 MHz with 19.5 Gbps effective, while the RTX 5090 SE runs at 1750 MHz with 28 Gbps effective. The effective data rate is much higher on the RTX 5090 SE, but the base memory clock is lower.

Pixel and texture rates reflect the core count differences. The RX 7700 achieves 236.1 GPixel/s and 393.4 GTexel/s. The RTX 5090 SE achieves 380.3 GPixel/s and 1,045.9 GTexel/s. The RTX 5090 SE has a 61% higher pixel rate and a 166% higher texture rate.

Physical dimensions are similar in length but differ in height and width. Both cards measure 267 mm in length. The RX 7700 is 135 mm tall and 50 mm wide, while the RTX 5090 SE is 111 mm tall and 40 mm wide. Both are dual-slot cards.

Display outputs differ: the RX 7700 has 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C. The RTX 5090 SE has 1x HDMI 2.1b and 3x DisplayPort 2.1b. The RX 7700 includes a USB Type-C output that the RTX 5090 SE lacks.

The API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The RTX 5090 SE has a launch MSRP of 1,499 USD. The RX 7700 has no launch MSRP recorded.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two GPUs. The RX 7700 has nine individual benchmark scores, while the RTX 5090 SE has zero. This creates an asymmetric comparison where only one side has measurable results.

For the RX 7700 alone, the scores show a wide spread across different test methodologies. The Geekbench OpenCL score of 106028 is the highest single result. The Passmark G3D score of 20974 is the next highest, followed by Passmark GPU Compute at 10963. The Passmark G2D score of 1206 is lower than the compute scores but higher than the DirectX-specific tests.

The DirectX tests show a clear hierarchy: DirectX 9 scores 261, DirectX 11 scores 186, DirectX 12 scores 96, and DirectX 10 scores 92. The DirectX 9 result is nearly three times the DirectX 12 result, suggesting that legacy DirectX workloads run relatively better on this architecture than modern ones, at least in these specific Passmark tests.

The average benchmark score of 15852 places the RX 7700 in the 58th percentile of all GPUs. Its nearest rivals include the AMD Radeon R9 370X with an average score of 15862 and a delta of -0.1%, the AMD Radeon RX 9060 with 16014 and a delta of -1%, the AMD Radeon Pro W5500 with 15679 and a delta of 1.1%, and the NVIDIA GeForce RTX 3060 Ti with 16129 and a delta of -1.7%. The RX 7700 sits within 2% of all four rivals, with the Pro W5500 being the only one that scores lower.

The RTX 5090 SE has no rivals listed and no scores to compare. Its 50th percentile rank is below the RX 7700's 58th percentile, but this ranking is based on incomplete data and should not be interpreted as a performance comparison.

The Verdict

The data presents an unusual situation. The RX 7700 has a complete benchmark profile, while the RTX 5090 SE has none. This means any verdict must be based on recorded results for one GPU and architectural specifications for the other.

For the RX 7700, the recorded data shows a mid-range GPU that sits in the 58th percentile of all GPUs, with an average score of 15852. Its nearest rivals are all within 2% of its average score, indicating tight competition in its segment. The Passmark DirectX 9 score of 261 is its strongest legacy test, while the Geekbench OpenCL score of 106028 shows substantial compute capability.

For the RTX 5090 SE, the absence of benchmark scores means the database cannot confirm any performance level. The specifications suggest a high-end part: 14080 shading units, 24 GB of GDDR7, 1.34 TB/s bandwidth, and 66.94 TFLOPS of FP32 throughput. Its transistor count of 92,200 million and die size of 750 mm² are more than three times and double the RX 7700's respective figures.

The choice between these two GPUs depends on what the data can support. The RX 7700 has measurable results and a known percentile ranking. The RTX 5090 SE has no measured results, so any performance claim would be speculative. The RTX 5090 SE does have a launch MSRP of 1,499 USD, while the RX 7700 has no recorded MSRP.

The RTX 5090 SE also has a higher TDP of 500 W versus 200 W for the RX 7700, and a suggested PSU of 900 W versus 550 W. The power connector differs as well, with the RTX 5090 SE using a single 16-pin connector and the RX 7700 using two 8-pin connectors.

For users who require measured performance data, the RX 7700 is the only option with recorded scores. For users who prioritize raw specifications, the RTX 5090 SE has higher core counts, more memory, faster bandwidth, and tensor cores. The data does not support a definitive performance winner because only one side has benchmark results.