SYSTEM ANALYZER

Rate My PC: AMD Ryzen 9 5900 + NVIDIA GeForce RTX 4070 SUPER

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

95 / 100
ULTIMATE READY

Apex Performer

Top 5% 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
94%
VS
GPU
96%
PROCESSOR

AMD Ryzen 9 5900

46,971 Benchmark Score
Top 6% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 4070 SUPER

43,223 Benchmark Score
Top 4% 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 9 5900 and NVIDIA GeForce RTX 4070 SUPER form a desktop pairing that targets a high-performance sweet spot for both productivity and gaming. The CPU brings 12 cores and 24 threads from the Zen 3 architecture, while the GPU delivers Ada Lovelace features and 12 GB of GDDR6X memory. This analysis relies strictly on the benchmark data provided, which shows a combined percentile of 86, placing this pairing above the vast majority of systems. It is important to note that no measured FPS rows exist for this exact combination; the FACT PACK contains no measuredFps data. Consequently, all FPS discussion in this analysis is framed as an estimate derived from the benchmark scores, not from direct gameplay testing.

GPU Analysis — VRAM, bandwidth, clocks, RT/tensor hardware, what the benchmark scores mean for rendering

The NVIDIA GeForce RTX 4070 SUPER is built on the Ada Lovelace architecture using a 5 nm process at TSMC, with a die size of 294 mm² containing 35,800 million transistors. The memory subsystem consists of 12 GB of GDDR6X on a 192-bit bus, which provides a bandwidth of 504.2 GB/s. This memory configuration is substantial for high-resolution textures and complex 3D scenes, as the bandwidth figure directly supports the data throughput required for rendering workloads.

Clock speeds are listed with a base of 1980 MHz and a boost of 2475 MHz, with memory running at 1313 MHz (21 Gbps effective). The GPU has 7168 shading units, 224 texture mapping units, and 80 raster output units, which translate into a pixel rate of 198.0 GPixel/s and a texture rate of 554.4 GTexel/s. For raw compute, the FP32 performance is 35.48 TFLOPS, and the FP16 performance is identical at 35.48 TFLOPS (1:1), indicating strong parallel processing capability for both single-precision and half-precision tasks.

Ray tracing and tensor hardware are present with 56 RT cores and 224 tensor cores. This hardware configuration supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it compatible with modern graphics APIs that rely on ray-traced effects and DLSS-style upscaling. In benchmark terms, the GPU scores 4627 in 3DMark Steel Nomad DX12, which is a measure of its DirectX 12 rendering performance. The Geekbench OpenCL score is 172795, and the Vulkan score is 205624, showing that compute and graphics workloads scale well across different API environments.

The PassMark scores provide additional context: G3D score is 29995, GPU Compute is 17108, and DirectX 11 score is 273. The DirectX 10 score is 167, DirectX 9 is 344, and DirectX 12 is 110. These scores suggest that the GPU is particularly strong in modern API workloads, as the DirectX 12 score, while lower numerically, represents a more complex rendering path. The G2D score is 1184, which is less relevant for 3D rendering but indicates solid 2D performance.

Relative to its nearest rivals, the RTX 4070 SUPER has an average benchmark score of 43223. It sits 0.1% behind the NVIDIA Quadro M6000 24 GB (score 43262), 0.1% behind the NVIDIA GeForce RTX 5050 Mobile (score 43268), 0.2% behind the NVIDIA Quadro M6000 (score 43301), and 1% behind the NVIDIA GeForce RTX 4090 Mobile (score 43667). This places it in a competitive tier where the differences are marginal for the first three rivals, but the RTX 4090 Mobile holds a slight edge of 1%. For rendering, the data indicates that this GPU is well-suited for 1440p and 4K workloads, though the 12 GB VRAM may be a limiting factor for extremely large scenes.

Balance and Bottleneck — which component limits which workload, using percentiles and FPS scaling as evidence

The balance between the CPU and GPU is critical for determining which component becomes the limiting factor in various workloads. The CPU has a percentile of 89 against all CPUs, while the GPU has a percentile of 83 against all GPUs. The combined percentile for the pairing is 86. This suggests that the CPU is slightly stronger relative to its peers than the GPU is to its peers, which implies that in most scenarios, the GPU will be the first to reach its limit.

For gaming, the GPU is typically the bottleneck at higher resolutions and with ultra settings, as the rendering load increases. The benchmark scores support this: the GPU’s PassMark G3D score of 29995 is substantial, but the CPU’s single-thread score of 3439 in PassMark and Cinebench R23 single-core score of 4070 indicate strong per-core performance that can feed the GPU adequately. In CPU-bound scenarios, such as low-resolution gaming with high frame rates or physics-heavy simulations, the CPU’s 12 cores and 24 threads with a boost clock of 4.70 GHz will be the limiting factor.

The FPS scaling is not measured for this exact combination, so estimates must be derived from the scores. In GPU-bound workloads, the RTX 4070 SUPER’s 35.48 TFLOPS FP32 performance and 504.2 GB/s memory bandwidth will drive frame rates, and the GPU’s percentile of 83 suggests it will handle most modern games at high settings. In CPU-bound workloads, the Ryzen 9 5900’s Cinebench R23 multi-core score of 28834 and PassMark multi-thread score of 33969 indicate that it can handle complex simulations and encoding tasks without being a bottleneck.

The data shows that for mixed workloads like streaming while gaming, the CPU’s 24 threads provide headroom for encoding, while the GPU handles rendering. The CPU’s PassMark data compression score of 411453 and encryption score of 26247 indicate strong processing capability for background tasks. The bottleneck will shift to the GPU in 4K gaming, where the 12 GB VRAM and 504.2 GB/s bandwidth become more critical, and the CPU’s advantage becomes less relevant.

CPU Analysis — cores, clocks, architecture, what the benchmark scores mean for real workloads

The AMD Ryzen 9 5900 is a 5000 series processor based on the Zen 3 architecture, codenamed Vermeer, manufactured on a 7 nm process at TSMC. It has 12 cores and 24 threads, with a base clock of 3.00 GHz and a boost clock of 4.70 GHz. The TDP is 65 watts, which is notably efficient for a 12-core part, and it uses the AMD Socket AM4 platform. The CPU supports DDR4 memory in a dual-channel configuration with a memory bandwidth of 51.2 GB/s, and it has ECC memory support. The PCIe interface is Gen 4 with 20 lanes from the CPU, which is sufficient for a high-end GPU and NVMe storage.

The cache hierarchy includes 64 KB of L1 per core, 512 KB of L2 per core, and 64 MB of L3 cache, which is shared across the cores. The die size is 2x 74 mm², and the transistor count is 8,300 million. The multiplier is unlocked, allowing for overclocking, and the production status is active with a release date of January 2021.

Benchmark scores show strong multi-threaded performance: Cinebench R15 multi-core is 2906, R20 multi-core is 12110, and R23 multi-core is 28834. Single-core scores are 410 (R15), 1709 (R20), and 4070 (R23). PassMark scores include multi-thread at 33969, single-thread at 3439, integer math at 128641, floating point math at 69124, and extended instructions at 26859. The data compression score is 411453, and encryption is 26247. These numbers indicate that the CPU excels in tasks that use all cores, such as video encoding, 3D rendering, and software compilation.

The average benchmark score is 46971, with a percentile of 89, meaning it outperforms 89% of all CPUs. Relative to rivals, it is 0.1% behind the AMD Ryzen AI 9 HX PRO 375 (score 47022), 0.2% ahead of the Intel Core i7-13700K (score 46881), 0.4% behind the Intel Core i9-12900F (score 47176), and 0.7% ahead of the AMD Ryzen 9 7845HX (score 46654). This places the Ryzen 9 5900 in a very competitive position, trading blows with modern high-end parts.

For real workloads, the 12 cores and 24 threads are ideal for multitasking, content creation, and heavy multi-threaded applications. The 64 MB L3 cache is beneficial for gaming and data-intensive tasks, as it reduces memory latency. The 65 W TDP means it can be cooled with a capable air cooler, and the unlocked multiplier allows users to extract extra performance if needed.

FAQ

Q: What is the combined performance percentile of this CPU and GPU pairing?

A: The combined percentile is 86, indicating that this pairing outperforms 86% of all systems in the benchmark database.

Q: How does the CPU compare to the Intel Core i7-13700K?

A: The Ryzen 9 5900 has an average benchmark score of 46971, which is 0.2% higher than the Intel Core i7-13700K’s score of 46881.

Q: What is the GPU’s memory bandwidth and capacity?

A: The RTX 4070 SUPER has 12 GB of GDDR6X memory on a 192-bit bus, providing a bandwidth of 504.2 GB/s.

Q: Does the CPU support ECC memory?

A: Yes, the AMD Ryzen 9 5900 has ECC memory support, which is useful for workstation builds where data integrity is critical.

Q: What is the GPU’s FP32 compute performance?

A: The GPU delivers 35.48 TFLOPS of FP32 performance, which is also the same for FP16 at a 1:1 ratio.

Q: How does the GPU compare to the NVIDIA GeForce RTX 4090 Mobile?

A: The RTX 4070 SUPER has an average score of 43223, which is 1% lower than the RTX 4090 Mobile’s score of 43667.

Q: What are the CPU’s core and thread counts?

A: The Ryzen 9 5900 has 12 cores and 24 threads, with a boost clock of 4.70 GHz.

Benchmark Performance

The exact CPU and GPU scores define the performance envelope of this system. The CPU’s average benchmark score is 46971, with a percentile of 89, meaning it is in the top 11% of all CPUs. The GPU’s average benchmark score is 43223, with a percentile of 83, placing it in the top 17% of all GPUs. The combined percentile is 86, which is a strong indicator that this pairing is well-balanced for high-end tasks.

For the CPU, the Cinebench R23 multi-core score of 28834 is a key metric for rendering workloads, while the single-core score of 4070 shows strong per-thread performance. The PassMark multi-thread score of 33969 and single-thread score of 3439 corroborate these findings. The GPU’s 3DMark Steel Nomad DX12 score of 4627 and PassMark G3D score of 29995 are strong for gaming, while the Geekbench OpenCL score of 172795 indicates solid compute capability.

Relative to rivals, the CPU is nearly identical in performance to the AMD Ryzen AI 9 HX PRO 375 (0.1% behind) and the Intel Core i9-12900F (0.4% behind), while slightly ahead of the Intel Core i7-13700K (0.2% ahead) and the AMD Ryzen 9 7845HX (0.7% ahead). The GPU is within 1% of the NVIDIA Quadro M6000 24 GB, RTX 5050 Mobile, and Quadro M6000, but trails the RTX 4090 Mobile by 1%. The combined picture is a system that is roughly 0.1-0.5% faster than its closest competitors in aggregate, making it a top-tier choice for both gaming and productivity.

Usage Scenarios

High-refresh gaming: The GPU’s 35.48 TFLOPS FP32 performance and 504.2 GB/s memory bandwidth, combined with the CPU’s strong single-core score of 4070 in Cinebench R23, suggest this system can push high frame rates at 1440p. The CPU’s 89th percentile and GPU’s 83rd percentile indicate that the pairing is capable of sustaining high refresh rates in most titles, though the GPU will likely be the limiting factor at ultra settings.

Streaming: The CPU’s 24 threads and PassMark multi-thread score of 33969 provide ample headroom for software encoding while gaming. The data compression score of 411453 and encryption score of 26247 indicate that background tasks will not significantly impact gaming performance, making this a viable option for single-PC streaming setups.

Video editing: The Cinebench R23 multi-core score of 28834 and PassMark floating point math score of 69124 show strong performance in rendering and effects. The GPU’s 224 tensor cores and 56 RT cores can accelerate AI-based effects and ray-traced previews, while the 12 GB VRAM is sufficient for 4K timelines.

3D rendering: The CPU’s 12 cores and 24 threads, with a Cinebench R20 multi-core score of 12110, are well-suited for CPU-based rendering. The GPU’s FP32 performance of 35.48 TFLOPS and Geekbench OpenCL score of 172795 make it capable for GPU-accelerated renders in Blender or similar software, though the 12 GB VRAM may limit very large scenes.

Software development: The CPU’s integer math score of 128641 and multi-thread score of 33969 indicate fast compilation times. The 64 MB L3 cache and 65 W TDP make it efficient for long build sessions, and the 20 PCIe Gen 4 lanes allow for fast NVMe storage.

Student and office work: The CPU’s single-thread score of 3439 in PassMark and the GPU’s G2D score of 1184 handle everyday tasks with ease. The 65 W TDP means lower power consumption, and the system is overkill for basic productivity, but it provides a smooth experience for multitasking with many applications open.

Gaming Performance

Since no measured FPS rows exist for this exact combination, all FPS figures are estimates based on the benchmark scores. The data shows that the system is not directly measured, so these numbers are qualitative expectations, not verified results. The GPU’s PassMark G3D score of 29995 and 3DMark Steel Nomad DX12 score of 4627 suggest strong performance in modern titles. The CPU’s single-core score of 4070 in Cinebench R23 ensures that the GPU is not starved for data in CPU-bound games.

For 1080p gaming, the CPU’s high single-thread performance will likely allow the GPU to reach very high frame rates, as the bottleneck will be the GPU’s rendering speed. The 12 GB VRAM and 504.2 GB/s bandwidth are more than sufficient for this resolution. At 1440p, the GPU becomes the primary limiter, but the scores indicate it can handle ultra settings in most games with frame rates well above 60 FPS. At 4K, the GPU’s 12 GB VRAM may be a constraint in some titles, but the 35.48 TFLOPS FP32 compute should still deliver playable frame rates in many games.

The absence of measured FPS data means that these expectations are derived from the GPU’s percentile of 83 and the CPU’s percentile of 89. The combined percentile of 86 suggests that this system will perform better than the vast majority of systems in gaming benchmarks, but exact frame rates cannot be stated with certainty.

Build Overview

This is a desktop-class build combining the AMD Ryzen 9 5900 with the NVIDIA GeForce RTX 4070 SUPER. The CPU is a 12-core, 24-thread part from the 5000 series, based on Zen 3 architecture, while the GPU is from the GeForce 40-series, based on Ada Lovelace. The pairing has a combined percentile of 86, which places it in the upper tier of systems in the database.

The CPU’s 89th percentile and GPU’s 83rd percentile indicate that the CPU is slightly stronger relative to its peers, but the overall system is well-matched for high-end workloads. The CPU’s 65 W TDP is efficient, while the GPU’s 220 W TDP requires a 550 W suggested PSU. The GPU is dual-slot with a 16-pin power connector, and it has 1x HDMI 2.1 and 3x DisplayPort 1.4a outputs. The system uses PCIe 4.0 x16 for the GPU and supports DDR4 memory, which is a mature and cost-effective platform.

This pairing is classified as a high-end desktop system, suitable for enthusiasts and professionals who need a balance of multi-threaded CPU performance and GPU-accelerated rendering. The production status of the GPU is end-of-life, meaning it is being phased out, but the CPU is still active, which may affect future upgrade paths.

Who Should Build It

This system is ideal for gamers targeting 1440p or 4K resolutions with high settings. The GPU’s 83rd percentile and 12 GB VRAM support high-resolution textures, while the CPU’s strong single-core performance ensures smooth frame pacing. The 24 threads provide headroom for streaming or recording gameplay without a dedicated capture card.

Content creators, particularly video editors and 3D artists, will benefit from the CPU’s Cinebench R23 multi-core score of 28834 and the GPU’s 35.48 TFLOPS FP32 compute. The 224 tensor cores can accelerate AI-based tools, and the 56 RT cores are useful for ray-traced rendering in real-time engines. Software developers will appreciate the fast compilation times from the integer math score of 128641 and the 64 MB L3 cache for large codebases.

Students and office workers will find this system overkill for basic tasks, but the 65 W TDP CPU and efficient design make it a quiet and cool workstation. Small business workstations that run virtual machines, databases, or complex simulations will benefit from the 12 cores and ECC memory support. The system is not budget-oriented, but the data shows it is a high-performance option for those who need it.