SYSTEM ANALYZER

Rate My PC: AMD Ryzen 7 5700X3D + NVIDIA GeForce RTX 5090 D

Get a comprehensive performance analysis of your gaming rig with detailed benchmarks, bottleneck detection, and upgrade recommendations

92 / 100
ULTIMATE READY

Apex Performer

Top 8% of systems. Capable of 4K Ultra gaming and advanced rendering.

4K 60+ FPSVR ReadyRay Tracing

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
86%
VS
GPU
98%
PROCESSOR

AMD Ryzen 7 5700X3D

24,709 Benchmark Score
Top 14% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5090 D

77,712 Benchmark Score
Top 2% Market Ranking
View Full Specs →

Market Position

How your build compares to others
Budget
0-30
Mid-Range
30-60
High-End
60-85
Enthusiast
85-100
Your Build

Game Performance Benchmarks

Real-world 4K FPS in popular titles
View All Games →

Performance Insights

Tips to maximize your system

Optimal Performance

Your system is in the top tier. You can run any modern game at maximum settings.

4K Gaming Ready

Consider a 4K 144Hz monitor to fully utilize your hardware capabilities.

Compatible Games See what you can play Compare CPUs Find upgrades Compare GPUs Find upgrades

Performance Tiers Explained

90-100

Ultimate

4K Ultra gaming, VR ready, ray tracing enabled, professional workloads

4K 60+ FPS VR Ready
70-89

High-End

1440p Ultra or 4K High settings, excellent for modern AAA titles

1440p Ultra 4K High
50-69

Mid-Range

1080p Ultra or 1440p Medium, great value for most gamers

1080p Ultra 1440p Med
30-49

Entry Level

1080p Medium settings, suitable for eSports and older titles

1080p Med eSports
0-29

Legacy

Basic gaming, older titles, consider upgrading for modern games

720p-1080p Low Older Games

The AMD Ryzen 7 5700X3D and NVIDIA GeForce RTX 5090 D pairing is an unusual desktop combination, placing the highest-tier Blackwell GPU from the GeForce 50-series alongside a Zen 3 processor designed for the previous platform generation. The data in this analysis covers CPU and GPU synthetic benchmarks, platform specifications, and measured frame rates across dozens of titles at three resolutions, providing a complete picture of what this build achieves and where its limits lie.

Upgrade Path and Platform

The CPU is built for the AMD Socket AM4 platform, which represents a mature ecosystem that has been in use since the Ryzen 1000 series. This particular chip, the Ryzen 7 5700X3D, belongs to the 5000 series and uses the Zen 3 architecture on the Vermeer codename. It is produced on a 7 nm process at TSMC, with a die size of 74 mm² containing 8,850 million transistors. The processor supports dual-channel DDR4 memory with a bandwidth of 51.2 GB/s and includes ECC memory support, which is a feature typically valued in workstation environments. PCIe connectivity is Gen 4 with 20 lanes available from the CPU, which is sufficient for the GPU and a single high-speed NVMe drive, though it falls short of the PCIe 5.0 bandwidth that the GPU itself is designed to use.

The RTX 5090 D, by contrast, uses a PCIe 5.0 x16 bus interface, meaning the platform’s Gen 4 support will not bottleneck the GPU severely in most workloads, but the theoretical bandwidth is halved. Memory support on the CPU side is limited to DDR4, which is a generation behind current standards, but the 51.2 GB/s bandwidth is adequate for the 8-core processor’s needs. The CPU’s TDP is 105 W, while the GPU has a TDP of 575 W, and the suggested PSU for the GPU alone is 950 W. This means the platform requires a high-capacity power supply, and the 105 W CPU draw adds to the total system requirement, so users must account for both figures when selecting a PSU.

The upgrade path from this platform is straightforward but limited. The AM4 socket has reached the end of its supported generation with the 5000 series, so the only CPU upgrades available would be within the same socket family, such as moving to a higher-core-count 5000 series part. The GPU, being the top of the GeForce 50-series, has no higher tier to move to, so the next sensible upgrade would be to a new platform entirely, requiring a new motherboard and DDR5 memory. For users coming from an older AM4 system, this build offers a way to reuse DDR4 memory and an existing motherboard, provided the BIOS supports the 5700X3D, which launched on 2024-01-07. The GPU’s dual-slot design and 304 mm length will fit in most mid-tower cases, but the 1x 16-pin power connector and 950 W PSU recommendation are critical constraints for any system build.

Benchmark Performance

The combined performance of this CPU and GPU places the pair at the 85th percentile of all builds, with an average FPS across games of 201.1 at the settings tested. The pair ranks 254th out of 3,732 pairs, which puts it in the top 7% of all recorded CPU-GPU combinations. This is a high-performance pairing, but the CPU’s percentile ranking relative to all CPUs is 77, while the GPU sits at 92, indicating a clear disparity in capability.

The CPU’s average benchmark score is 24,709, which is nearly identical to its nearest rival, the AMD Ryzen 5 7600X3D, which scores 24,728, a difference of only -0.1%. The Ryzen 9 5900HX scores 24,822, putting the 5700X3D 0.5% behind, while the Intel Core i5-12450HX scores 24,576, placing the AMD chip 0.5% ahead. The Intel Core i5-11600 scores 24,563, making the 5700X3D 0.6% faster. These are extremely tight margins, showing that the 5700X3D is competitive with a mix of newer and older mid-range to high-end processors, but it does not dominate any of them.

The GPU, on the other hand, has an average benchmark score of 77,712, which is 1.1% ahead of the AMD Radeon RX 6650M XT (76,904) and 1.6% behind the AMD Radeon RX 6850M XT (78,940). It is also 2.1% behind the NVIDIA Tesla P100 PCIe 12 GB (79,396) and 2.4% behind the Tesla P100 PCIe 16 GB (79,605). These rivals are a mix of mobile GPUs and professional compute cards, which is an unusual field for a desktop flagship, but the data shows the RTX 5090 D is not the absolute top performer in this benchmark set.

CPU Analysis

The Ryzen 7 5700X3D has 8 cores and 16 threads, with a base clock of 3.00 GHz and a boost clock of 4.10 GHz. It uses the Zen 3 architecture, which is known for its strong single-threaded performance relative to its successor generation. The cache configuration is the standout feature: 64 KB of L1 per core, 512 KB of L2 per core, and a massive 96 MB of shared L3 cache. This large L3 is the X3D differentiator, designed to reduce memory latency in gaming workloads.

In 3DMark tests, the CPU scores 6764 in the 16-thread test and 6755 in the max-thread test, showing that scaling from 16 threads to the maximum thread count yields almost no gain, which is expected for an 8-core part. The 8-thread score is 5357, the 4-thread score is 3097, and the 2-thread score is 1575, while the single-thread score is 804. This scaling is linear, with each doubling of threads producing roughly a doubling of score, indicating efficient use of the cores.

Cinebench results reinforce this picture. The R23 multicore score is 22,366, with a single-core score of 3,157. The R20 multicore score is 9,393 and single-core is 1,325, while R15 shows 2,254 multicore and 318 single-core. Geekbench scores are 11,086 multicore and 1,849 single-core. Passmark tests show a multithread score of 26,318 and single-thread score of 2,970, with floating-point math at 46,492 and integer math at 81,257. Data compression scores are 307,237, encryption is 18,788, and extended instructions are 21,202. Physics scores are 2,686, and random string sorting is 31,492.

The 96 MB L3 cache is the key architectural advantage, and it shows in gaming benchmarks where the CPU can hold more game data on-chip. However, the single-thread score of 804 in 3DMark and 3,157 in Cinebench R23 indicate that this is not a top-tier single-thread performer, as it is beaten by newer architectures with higher IPC. The CPU’s percentile of 77 versus all CPUs means it outperforms the majority of processors but sits below the top quarter, and its nearest rivals are all within a 1% margin, showing that it trades blows with much newer parts.

FAQ

Q: What socket does the AMD Ryzen 7 5700X3D use?

A: The CPU uses the AMD Socket AM4, which is a mature platform that supports DDR4 memory and PCIe Gen 4 with 20 lanes from the CPU.

Q: How much L3 cache does the CPU have, and why is it significant?

A: The CPU has 96 MB of shared L3 cache. This large cache is designed to reduce memory latency and is a key feature of the X3D series, which helps in gaming workloads where data reuse is high.

Q: What is the GPU’s memory configuration?

A: The RTX 5090 D has 32 GB of GDDR7 memory on a 512-bit bus, providing 1.79 TB/s of bandwidth. The memory clock is 1750 MHz, which translates to 28 Gbps effective.

Q: What is the suggested power supply for this GPU?

A: The suggested PSU for the RTX 5090 D is 950 W. The GPU’s TDP is 575 W, and the CPU’s TDP is 105 W, so the total system draw will be high.

Q: How does the CPU compare to the AMD Ryzen 5 7600X3D?

A: The Ryzen 7 5700X3D scores 24,709 on average, while the Ryzen 5 7600X3D scores 24,728, making the 5700X3D 0.1% slower. The difference is negligible in real-world terms.

Q: Is the GPU faster than the AMD Radeon RX 6850M XT?

A: No, the RTX 5090 D scores 77,712, which is 1.6% behind the RX 6850M XT’s score of 78,940. It is faster than the RX 6650M XT by 1.1%.

Q: What is the CPU’s base and boost clock?

A: The base clock is 3.00 GHz, and the boost clock is 4.10 GHz. The CPU has 8 cores and 16 threads.

Balance and Bottleneck

The pairing of a 77th-percentile CPU with a 92nd-percentile GPU creates an inherent imbalance. The CPU’s average benchmark score of 24,709 is nearly identical to its rivals, but the GPU’s score of 77,712 places it far above the median. In gaming, this means the CPU is more likely to be the limiting factor at lower resolutions where frame rates are high, while the GPU becomes the limit at higher resolutions where pixel throughput dominates.

The measured FPS data supports this. At 1920x1080, the pair achieves high frame rates in most games, such as 392 FPS in Counter-Strike 2 and 439 FPS in Tom Clancy’s Rainbow Six Siege, but these numbers are far beyond what a 60 Hz or even 144 Hz display needs. The CPU’s single-thread score of 804 in 3DMark suggests that in esports titles with high frame rates, the CPU’s per-core performance will cap the maximum FPS. At 3840x2160, the GPU’s workload increases dramatically, and the frame rates drop to 145 FPS in Counter-Strike 2 and 168 FPS in Rainbow Six Siege, showing that the GPU is still not fully stretched at 4K in these lighter titles.

In more demanding games, the bottleneck shifts. Cyberpunk 2077 runs at 76 FPS at 1080p, 69 FPS at 1440p, and 57 FPS at 4K, with the frame rate scaling downward as resolution increases. This suggests the GPU is the limiting factor at 4K, but at 1080p, the CPU may be holding back the GPU, as the 76 FPS figure is lower than what a top-tier CPU might achieve with the same GPU. Ark: Survival Ascended is even more extreme, with 57 FPS at 1080p, 36 FPS at 1440p, and 19 FPS at 4K, indicating a game that is heavily GPU-bound across all resolutions.

The pair’s average FPS of 201.1 across all games is high, but the distribution shows that the CPU is the bottleneck in esports and light games, while the GPU governs heavy titles. The 3DMark 16-thread score of 6,764 and the max-thread score of 6,755 show that the CPU has no headroom for additional threads, meaning that any game that scales beyond 8 cores will see a performance plateau. For a GPU of this caliber, a faster CPU with higher single-thread performance would balance the system better, but the measured data shows that the pair still delivers excellent frame rates in the majority of titles.

Who Should Build It

This build targets users who prioritize raw GPU performance and are willing to keep an older CPU platform. The 85th combined percentile places it in the high-performance tier, suitable for gamers at 2560x1440 and 3840x2160 resolutions who play demanding AAA titles. The CPU’s 8 cores and 16 threads are sufficient for modern games, and the 96 MB L3 cache helps in titles that benefit from large caches, but the CPU’s 77th percentile means it is not the fastest available.

Content creators who work with GPU-accelerated rendering will benefit from the RTX 5090 D’s 32 GB of VRAM and its compute scores, such as the Geekbench OpenCL score of 310,674 and Vulkan score of 376,915. The CPU’s Cinebench R23 multicore score of 22,366 is adequate for video encoding and 3D rendering, but it is not a top-tier workstation processor, so users who rely heavily on CPU rendering might be better served by a newer platform. Software developers will find the CPU’s Passmark integer math score of 81,257 and data compression score of 307,237 useful for compilation and data processing tasks, but the single-thread performance is modest for code compilation that is often single-threaded.

Students and small business users building a workstation will find this pairing overkill for office tasks, but the GPU’s compute capabilities can accelerate machine learning and data analysis workloads, provided the software uses CUDA. The CPU’s ECC memory support is a plus for data integrity in scientific computing, but the platform’s DDR4 limitation may be a drawback for memory-intensive tasks. This is not a budget build by any measure, but for users who already own an AM4 motherboard and DDR4 memory, it offers a way to get top-tier GPU performance without upgrading the entire platform.

Usage Scenarios

High-refresh gaming at 1080p is where this build excels in frame rate, with esports titles like Counter-Strike 2 hitting 392 FPS and Tom Clancy’s Rainbow Six Siege reaching 439 FPS. The CPU’s single-thread performance is sufficient for these games, and the GPU is barely taxed, so the system can drive a 360 Hz monitor in many titles. However, the CPU may become the bottleneck in games that are not well-optimized for high frame rates, as seen in Cyberpunk 2077 at 76 FPS, which is lower than expected for a flagship GPU.

Streaming while gaming is viable, as the CPU’s 16 threads can handle encoding overhead, but the 105 W TDP and 8 cores mean that concurrent streaming and heavy gaming may cause frame drops in CPU-bound titles. The GPU’s NVENC encoder would offload this work, but the data does not specify its capabilities. Video editing is GPU-accelerated, and the RTX 5090 D’s 1.79 TB/s bandwidth and 32 GB VRAM will handle 4K and 8K footage smoothly, with the CPU’s 22,366 Cinebench R23 multicore score providing adequate preview rendering.

3D rendering in applications that use the GPU will see massive performance, with the GPU’s FP32 throughput of 104.8 TFLOPS and 170 RT cores accelerating ray tracing. The CPU’s role in scene preparation and physics simulation is secondary, and its 2,686 Passmark physics score is modest. Software development benefits from the CPU’s 8 cores and large L3 cache for build times, while the GPU can accelerate parallel workloads. Student and office work is easily handled, but this configuration is far beyond what is needed for word processing or spreadsheets, making it a poor fit for budget-conscious academic use.

Build Overview

This is a desktop build, classified as such in the data, combining the AMD Ryzen 7 5700X3D with the NVIDIA GeForce RTX 5090 D. The overall tier is high, with the combined percentile at 85 and the pair rank at 254 out of 3,732 pairs, placing it in the top 7% of recorded builds. The CPU is a 2024 release, while the GPU is a 2025 release, creating a generational gap that is reflected in the benchmark percentiles (77 for CPU, 92 for GPU).

The build’s strengths lie in GPU-heavy workloads and high-resolution gaming, while its weaknesses are in CPU-bound scenarios. The launch MSRP for the CPU is $249, and the GPU has a launch MSRP of 2,299 USD, but those figures are provided for reference only. The pair’s average FPS of 201.1 across games is impressive, but the CPU’s 77th percentile suggests that a faster processor would unlock more of the GPU’s potential in certain titles. This is a build for users who want maximum GPU performance on a legacy platform, accepting that the CPU will be the limiting factor in some games.

GPU Analysis

The NVIDIA GeForce RTX 5090 D is built on the Blackwell 2.0 architecture with the GB202 chip, produced on a 5 nm process at TSMC, with 92,200 million transistors on a 750 mm² die. It has 21,760 shading units, 680 texture mapping units, and 176 raster output units, along with 170 RT cores and 680 tensor cores. The base clock is 2017 MHz, and the boost clock is 2407 MHz, with a memory clock of 1750 MHz running at 28 Gbps effective on GDDR7 memory.

The memory configuration is massive: 32 GB on a 512-bit bus, yielding 1.79 TB/s of bandwidth. This is a class-leading amount of VRAM, suitable for 8K textures and large dataset processing. The pixel rate is 423.6 GPixel/s, and the texture rate is 1,636.8 GTexel/s, with FP32 and FP16 performance both at 104.8 TFLOPS, indicating that the GPU does not sacrifice half-precision throughput for double-precision. The TDP is 575 W, requiring a 950 W PSU, and it uses a single 16-pin power connector.

In benchmarks, the GPU scores 14,326 in 3DMark Steel Nomad DX12, which is a measure of modern DX12 gaming performance. Geekbench scores are 310,674 for OpenCL and 376,915 for Vulkan, showing strong compute capability. Passmark scores are more varied, with G3D at 44,065 and GPU compute at 28,396, while older DirectX versions score lower (DirectX 10 at 231, DirectX 11 at 371, DirectX 12 at 219, and DirectX 9 at 434). The GPU’s percentile of 92 places it in the top 8% of all GPUs, but its nearest rivals are mobile GPUs and professional Tesla cards, suggesting that its performance is not as dominant as the name might imply in this specific benchmark suite.

Gaming Performance

The measured FPS data covers 51 games at three resolutions, all at ultra settings, and the data is measured, not estimated. At 1920x1080, the average frame rate across all games is very high, with esports titles exceeding 300 FPS: Counter-Strike: Global Offensive hits 866 FPS, Roblox reaches 507 FPS, and Tom Clancy’s Rainbow Six Siege achieves 439 FPS. Heavier games are lower but still playable, with Cyberpunk 2077 at 76 FPS, Red Dead Redemption 2 at 105 FPS, and Ark: Survival Ascended at 57 FPS.

At 2560x1440, frame rates drop by roughly 20-40% depending on the game. Counter-Strike: Global Offensive still hits 596 FPS, but Cyberpunk 2077 falls to 69 FPS, and Ark: Survival Ascended drops to 36 FPS. Microsoft Flight Simulator runs at 114 FPS, and Control is at 124 FPS. At 3840x2160, the GPU’s workload increases significantly, and frame rates are lower: Counter-Strike 2 drops to 145 FPS, Cyberpunk 2077 to 57 FPS, and Ark: Survival Ascended to 19 FPS. Valorant is an outlier, running at 328 FPS at 4K, showing that lighter games can still exceed 300 FPS at the highest resolution.

The average FPS across all games is 201.1, but this figure is skewed by the high frame rates in esports titles. For AAA gaming, the pair delivers 60+ FPS at 4K in most titles, with exceptions like Ark at 19 FPS and Red Dead Redemption 2 at 52 FPS. The CPU’s bottleneck is evident in games like Allods Online, which runs at 132 FPS at 1080p but only 56 FPS at 4K, suggesting that the GPU is not the limiting factor at the lower resolution. This data indicates that the build is best suited for 1440p and 4K gaming, where the GPU’s power is fully utilized, while 1080p users will see diminishing returns due to CPU limitations.