SYSTEM ANALYZER

Rate My PC: AMD Ryzen 7 5700 + NVIDIA GeForce RTX 3090

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

Build Configuration

Select your components

PROCESSOR (CPU)

▼

GRAPHICS CARD (GPU)

▼

90 Score

Top 10% Ranking

90 / 100

ULTIMATE READY

Apex Performer

Top 10% 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

87%

GPU

93%

PROCESSOR

AMD Ryzen 7 5700

25,517 Benchmark Score

Top 13% Market Ranking

View Full Specs →

GRAPHICS CARD

NVIDIA GeForce RTX 3090

27,565 Benchmark Score

Top 7% 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

# CPU Analysis

The AMD Ryzen 7 5700 is an 8-core, 16-thread desktop processor built on the Zen 3 architecture, specifically the Cezanne die, manufactured on TSMC's 7 nm process. This is a 5000-series part that occupies an interesting position in AMD's lineup: it uses the Cezanne chip originally designed for mobile APUs, but it is sold as a desktop processor on the AMD Socket AM4 platform. The CPU carries 10,700 million transistors on a 180 mm² die, which is notably smaller than the desktop Matisse dies, yet it retains full Zen 3 performance characteristics.

The clock behavior is telling. The base clock sits at 3.70 GHz with a boost clock of 4.60 GHz, and the multiplier is unlocked, meaning the 65 W TDP does not preclude overclocking. The 65 W TDP is remarkably low for an 8-core part, which suggests this chip can sustain heavy multi-threaded loads without the cooling demands of higher-TDP alternatives. The memory controller supports DDR4 in dual-channel configuration with 51.2 GB/s of bandwidth, and ECC memory is supported, which is a feature typically associated with workstation-class processors rather than mainstream desktop parts.

Benchmark data reveals a processor that is well-balanced across thread counts. The 3DMark scores scale from 901 in single-thread, to 1,762 at 2 threads, 3,382 at 4 threads, 5,585 at 8 threads, and 6,617 at max threads. The scaling from 8 to 16 threads is modest — only about 18% improvement from the 8-thread score to the max-thread score — which indicates that the simultaneous multi-threading (SMT) implementation provides diminishing returns once all eight physical cores are engaged. This is consistent with Zen 3's architecture where each core is fully independent with its own 64 KB L1 and 512 KB L2 cache, sharing a 16 MB L3 pool.

Cinebench results reinforce the multi-core capability. The R23 multi-core score of 20,655 is strong for an 8-core part, while the R23 single-core score of 2,916 shows competitive per-thread performance. The R20 scores of 8,675 multi-core and 1,224 single-core follow the expected scaling pattern. Geekbench reports 9,959 multi-core and 1,907 single-core, placing this CPU in a range where it can handle both lightly-threaded and heavily-threaded workloads without a dramatic drop-off in either direction.

The PassMark suite provides additional insight into specific workload characteristics. Integer math scores 90,091, while floating-point math scores 51,427 — the integer advantage suggests strong performance in general-purpose computing tasks. Data compression scores 316,699, which is an extremely high figure that points to excellent memory subsystem efficiency. Data encryption scores 20,096, and extended instructions score 21,945, both indicating solid cryptographic and SIMD throughput. The random string sorting score of 33,138 and find prime numbers score of 58 complete the picture of a CPU that handles diverse computational patterns well.

The average benchmark score of 25,517 places this processor at the 78th percentile among all CPUs. Compared to its nearest rivals, the Ryzen 7 5700 sits within 0.3% of the AMD Ryzen 7 5825U (which scores 25,446, a 0.3% deficit for the rival), 0.1% above the AMD Ryzen 5 7640U (25,485), 0.1% below the Intel Xeon D-2752TER (25,530), and 0.1% below the AMD Ryzen 5 6600H (25,550). This clustering indicates that the Ryzen 7 5700 delivers performance essentially identical to a range of mobile and server processors, which is noteworthy for a desktop chip with a 65 W TDP.

# Benchmark Performance

The combined picture of CPU and GPU benchmark scores tells a story of a system that is strong in both compute domains but with the GPU clearly dominating the performance envelope. The CPU's average benchmark score of 25,517 places it at the 78th percentile, while the GPU's average benchmark score of 27,565 places it at the 73rd percentile. The combined percentile for this pairing is 76, which reflects a balanced but GPU-heavy system.

The GPU's benchmark results are dominated by the 3DMark Steel Nomad DX12 score of 5,118, which is a modern DirectX 12 test that stresses the graphics pipeline. The Geekbench OpenCL score of 172,758 and Vulkan score of 53,927 provide cross-API comparisons, with the OpenCL figure being substantially higher, suggesting that compute workloads using OpenCL will perform better than those using Vulkan compute. The PassMark suite shows a G3D score of 26,645, with DirectX 9, 10, 11, and 12 scores of 268, 182, 220, and 110 respectively — these DirectX scores are oddly low compared to the G3D score, which may indicate that the PassMark DirectX tests are not fully utilizing the GPU's capabilities or are bottlenecked by driver overhead in specific scenarios. The G2D score of 1,063 and GPU compute score of 15,356 round out the benchmark picture.

The CPU's benchmark scores are more uniformly strong across tests. The Cinebench R23 multi-core score of 20,655 is particularly relevant for rendering workloads, while the 3DMark max-thread score of 6,617 shows how the CPU performs under gaming-related multi-threaded loads. The PassMark multi-thread score of 24,303 and single-thread score of 3,296 indicate that the CPU does not sacrifice single-thread performance for its multi-core capabilities.

When comparing the GPU to its nearest rivals, the RTX 3090 sits within 0.5% of the NVIDIA GeForce RTX 4070 Mobile (27,435, a 0.5% deficit for the rival), 0.5% above the AMD Radeon RX 6700 XT (27,425), 1% below the AMD Radeon Pro Vega 20 (27,839), and 1.1% below the AMD Radeon RX 7800M (27,883). This tight clustering around the 27,500–27,900 range suggests that the RTX 3090's average benchmark score is representative of a performance tier that includes both desktop and mobile GPUs, despite the RTX 3090 being a flagship desktop part with significantly higher memory bandwidth and compute resources.

The combined benchmark picture indicates that this system is capable of handling both CPU-intensive and GPU-intensive workloads, but the GPU will be the limiting factor in scenarios where both are heavily loaded simultaneously. The CPU's 78th percentile ranking versus the GPU's 73rd percentile suggests that the CPU has slightly more headroom relative to its peers, which has implications for bottleneck analysis.

# FAQ

Q: What is the CPU's single-threaded performance relative to its multi-threaded performance?

A: The CPU scores 901 in 3DMark single-thread and 6,617 in max-thread, a ratio of about 7.3x. In Cinebench R23, the single-core score is 2,916 versus 20,655 multi-core, a ratio of about 7.1x. This indicates strong scaling from one to eight cores, with SMT providing a smaller additional boost.

Q: How does the Ryzen 7 5700 compare to its closest rival, the AMD Ryzen 7 5825U?

A: The Ryzen 7 5700 has an average benchmark score of 25,517, which is 0.3% higher than the Ryzen 7 5825U's 25,446. Both are 8-core Zen 3 parts, but the Ryzen 7 5700 is a desktop processor with a 65 W TDP while the 5825U is a mobile part.

Q: What memory bandwidth does the CPU support?

A: The CPU supports dual-channel DDR4 memory with a bandwidth of 51.2 GB/s. It also supports ECC memory, which is uncommon for mainstream desktop processors and may appeal to workstation users.

Q: Does the GPU support hardware ray tracing?

A: Yes, the RTX 3090 has 82 RT cores dedicated to ray tracing acceleration. It also has 328 tensor cores for AI and deep learning workloads, and supports DirectX 12 Ultimate (12_2), which includes ray tracing and mesh shaders.

Q: What is the GPU's memory configuration?

A: The RTX 3090 has 24 GB of GDDR6X memory on a 384-bit bus, providing 936.2 GB/s of bandwidth. The memory clock is 1219 MHz with an effective data rate of 19.5 Gbps.

Q: How does the GPU compare to the AMD Radeon RX 6700 XT?

A: The RTX 3090's average benchmark score of 27,565 is 0.5% higher than the RX 6700 XT's 27,425. Both GPUs sit in the same performance tier according to the average benchmark scores, despite the RTX 3090 having significantly more memory and compute resources.

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

A: The combined percentile is 76, which reflects the CPU's 78th percentile ranking and the GPU's 73rd percentile ranking. This indicates the system performs better than 76% of all CPU+GPU combinations in the database.

# Usage Scenarios

High-refresh gaming: The RTX 3090's benchmark scores suggest it can drive high refresh rates at high resolutions. The GPU's 3DMark Steel Nomad DX12 score of 5,118 and PassMark G3D score of 26,645 indicate strong raw graphics performance. The CPU's 3DMark single-thread score of 901 and 2-thread score of 1,762 suggest it can keep up with the GPU's frame generation in most gaming scenarios, though the GPU will likely be the primary bottleneck at lower resolutions.

Streaming: The CPU's 8 cores and 16 threads provide ample capacity for encoding and streaming workloads alongside gaming. The PassMark multi-thread score of 24,303 and Cinebench R23 multi-core score of 20,655 indicate that the CPU can handle simultaneous gaming and streaming without significant frame drops, especially given the GPU's tensor cores which can offload encoding tasks.

Video editing: The combination of CPU multi-core performance and GPU compute power makes this system well-suited for video editing. The CPU's Cinebench R23 multi-core score of 20,655 handles timeline operations and effect rendering, while the GPU's OpenCL score of 172,758 accelerates GPU-accelerated effects and exports. The GPU's 24 GB of VRAM provides ample capacity for large video projects and multi-layer timelines.

3D rendering: The CPU's Cinebench R20 multi-core score of 8,675 and R23 multi-core score of 20,655 indicate strong CPU-based rendering performance. The GPU's 35.58 TFLOPS of FP32 compute and 82 RT cores make it a capable GPU renderer as well, though the CPU will likely be the bottleneck in GPU-accelerated rendering pipelines due to scene preparation and data transfer.

Software development: The CPU's balanced performance profile suits compilation workloads. The PassMark integer math score of 90,091 and data compression score of 316,699 indicate strong performance in code compilation and build processes. The 16 threads allow for parallel builds, while the single-thread score of 3,296 in PassMark ensures responsive IDE interaction.

Student and office work: The 65 W TDP means this CPU can run in systems with modest cooling and power delivery, making it suitable for office workstations. The PassMark multi-thread score of 24,303 handles office multitasking with ease, while the GPU's capabilities are overkill for typical office workloads but provide headroom for future graphics-intensive tasks.

# Upgrade Path and Platform

The CPU uses the AMD Socket AM4 platform, which has been one of the longest-lived socket designs in recent desktop computing history. Memory support is dual-channel DDR4, and the platform supports ECC memory, which is an unusual feature for a mainstream desktop socket. The CPU provides PCIe Gen 3 with 20 lanes, which is adequate for most expansion cards but does not support PCIe Gen 4 or Gen 5 devices at full bandwidth. This is a potential limitation for future GPU upgrades, as newer graphics cards may be designed for PCIe Gen 4 or Gen 5 interfaces.

The GPU uses a PCIe 4.0 x16 interface, which is fully compatible with the CPU's PCIe Gen 3 slots but will operate at Gen 3 bandwidth. For the RTX 3090's 24 GB of VRAM and 936.2 GB/s of bandwidth, the PCIe Gen 3 x16 connection provides sufficient bandwidth for most workloads, though PCIe Gen 4 would reduce data transfer bottlenecks in scenarios where the GPU needs to stream large amounts of data from system memory.

The GPU's suggested PSU is 750 W, and the GPU itself has a 350 W TDP. The CPU's 65 W TDP is modest, so a system with this CPU and GPU would have a total component power draw of approximately 415 W under full load, leaving headroom for other components within a 750 W PSU. The GPU requires a single 12-pin power connector, which may require an adapter for PSUs that do not natively support this connector type.

For a sensible next upgrade, the CPU could be replaced with a newer AM4 part that supports PCIe Gen 4, which would allow the GPU to run at full bandwidth. However, the CPU's 78th percentile ranking suggests it is not yet a bottleneck in most workloads. The GPU is end-of-life according to its production status, so a future upgrade would likely involve moving to a newer GPU generation, though the current RTX 3090's 73rd percentile ranking indicates it remains competitive.

# Who Should Build It

This system targets users who need strong multi-core CPU performance and flagship-class GPU compute capabilities. Gamers at 1440p or 4K resolutions will benefit from the RTX 3090's high benchmark scores, particularly the 3DMark Steel Nomad DX12 score of 5,118 and the PassMark G3D score of 26,645. The CPU's 78th percentile ranking ensures it will not bottleneck the GPU in most gaming scenarios, especially at higher resolutions where the GPU becomes the limiting factor.

Content creators working with video editing, 3D rendering, or motion graphics will find the combination of the CPU's Cinebench R23 multi-core score of 20,655 and the GPU's 35.58 TFLOPS of FP32 compute to be a powerful pairing. The GPU's 24 GB of VRAM is particularly valuable for large projects that exceed the memory capacity of smaller GPUs, and the CPU's ECC memory support adds reliability for long render sessions.

Developers compiling large codebases will benefit from the CPU's PassMark integer math score of 90,091 and data compression score of 316,699, which indicate strong performance in build processes. The 16 threads allow for parallel compilation, and the single-thread performance ensures responsive development environments.

Students and small business workstations can leverage the 65 W TDP for energy-efficient operation, and the ECC memory support adds data integrity for financial or research workloads. The GPU's capabilities are overkill for typical office work, but the system provides headroom for future graphics-intensive applications or GPU-accelerated computing tasks.

# Gaming Performance

The FACT PACK contains no measured FPS data for this exact CPU+GPU combination, so all frame rate discussions are estimated from the benchmark scores. The GPU's 3DMark Steel Nomad DX12 score of 5,118 and PassMark G3D score of 26,645 indicate strong raw graphics performance that should translate to high frame rates at 1440p and 4K resolutions in most modern games.

The CPU's 3DMark single-thread score of 901 and 2-thread score of 1,762 suggest it can maintain high frame rates in CPU-bound scenarios, though the GPU will be the primary bottleneck at lower resolutions where the CPU's per-thread performance becomes more critical. The CPU's 8-thread score of 5,585 indicates that it can handle the multi-threaded workloads present in modern game engines, which often use 4-8 threads for game logic, physics, and streaming.

At 4K resolution, the GPU's 24 GB of VRAM and 936.2 GB/s of bandwidth provide ample resources for high-resolution textures and detailed geometry. The GPU's 82 RT cores enable ray tracing at playable frame rates, though enabling ray tracing will reduce overall FPS compared to rasterized rendering. The GPU's FP32 compute of 35.58 TFLOPS provides headroom for future games that may leverage more compute-intensive rendering techniques.

For esports titles running at 1080p, the CPU's single-thread performance of 901 in 3DMark and 3,296 in PassMark single-thread should be sufficient to drive high refresh rates, though the GPU's performance at lower resolutions may be limited by the CPU in some scenarios. The overall picture is that this system is best suited for high-resolution gaming where the GPU's massive memory bandwidth and compute resources can be fully utilized.

# Build Overview

This is a desktop build combining the AMD Ryzen 7 5700 CPU with the NVIDIA GeForce RTX 3090 GPU. The CPU is an 8-core, 16-thread Zen 3 part with a 65 W TDP, while the GPU is a 24 GB GDDR6X Ampere flagship with a 350 W TDP. The combined percentile of 76 indicates that this system outperforms 76% of all CPU+GPU pairings in the database, placing it in the upper tier of desktop systems.

The CPU's 78th percentile ranking and the GPU's 73rd percentile ranking are both strong, but the CPU's slightly higher percentile suggests that the CPU has more relative headroom compared to its peers than the GPU does. This is an unusual configuration in that the GPU is a former flagship part that is now end-of-life, while the CPU is a mainstream part that remains in active production.

The system's performance tier is defined by the GPU's capabilities, which include 10,496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The GPU's 936.2 GB/s of memory bandwidth and 35.58 TFLOPS of FP32 compute place it in a performance class that was flagship-level at its release. The CPU's 16 MB of L3 cache and dual-channel DDR4 support provide a solid foundation for feeding the GPU's data demands.

# Balance and Bottleneck

The balance between CPU and GPU performance is a key consideration for this system. The CPU's 78th percentile ranking versus the GPU's 73rd percentile ranking suggests that the CPU is slightly stronger relative to its peers than the GPU is. This means that in most workloads, the GPU will be the limiting factor, which is typical for a system pairing a mainstream CPU with a high-end GPU.

In gaming workloads, the bottleneck will shift depending on resolution and settings. At 1080p with low settings, the CPU's single-thread performance of 901 in 3DMark may become the limiting factor, as the GPU has ample headroom to render frames faster than the CPU can feed it. At 1440p and 4K with high settings, the GPU's rendering workload increases, and the bottleneck moves to the GPU, which is the intended operating range for this system.

In compute workloads, the bottleneck depends on the specific task. For CPU-bound tasks like code compilation, the CPU's PassMark multi-thread score of 24,303 and integer math score of 90,091 will be the primary determinants of performance. For GPU-bound tasks like 3D rendering or machine learning inference, the GPU's 35.58 TFLOPS of FP32 compute and tensor cores will be the limiting factor.

The FPS scaling between resolutions will show diminishing returns as resolution increases, because the GPU's frame rate will drop as pixel count increases, while the CPU's frame generation capability remains constant. This means that the system will show a larger CPU bottleneck at lower resolutions and a larger GPU bottleneck at higher resolutions, which is the expected behavior for a balanced system with a slight CPU advantage.

# GPU Analysis

The NVIDIA GeForce RTX 3090 is based on the GA102 chip, built on Samsung's 8 nm process with 28,300 million transistors on a 628 mm² die. This is a large chip with a transistor density of 45.1M per mm², and it contains 10,496 shading units, 328 TMUs, and 112 ROPs. The GPU operates at a base clock of 1395 MHz and a boost clock of 1695 MHz, with a memory clock of 1219 MHz providing an effective data rate of 19.5 Gbps.

The memory subsystem is a defining feature of this GPU. It has 24 GB of GDDR6X memory on a 384-bit bus, providing 936.2 GB/s of bandwidth. This is an enormous amount of memory bandwidth that enables high-resolution textures, large datasets for compute workloads, and smooth performance in memory-intensive applications. The 24 GB capacity is particularly valuable for professional workloads like video editing, 3D rendering, and machine learning, where model sizes and working sets can exceed the memory capacity of smaller GPUs.

The GPU's compute capabilities are substantial. It delivers 35.58 TFLOPS of FP32 and FP16 compute (at a 1:1 ratio), with a pixel rate of 189.8 GPixel/s and a texture rate of 556.0 GTexel/s. The 82 RT cores provide hardware acceleration for ray tracing, while the 328 tensor cores accelerate AI and deep learning workloads. The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it compatible with modern graphics APIs.

The GPU's benchmark scores reflect its capabilities. The 3DMark Steel Nomad DX12 score of 5,118 is a strong result for a modern DirectX 12 test, while the Geekbench OpenCL score of 172,758 indicates excellent compute performance. The Vulkan score of 53,927 is lower than the OpenCL score, suggesting that Vulkan compute workloads may not fully utilize the GPU's capabilities. The PassMark G3D score of 26,645 and GPU compute score of 15,356 provide additional data points for performance comparison.

The GPU's 73rd percentile ranking places it above 73% of all GPUs in the database, which is notable for a part that is now end-of-life. Its nearest rivals — the RTX 4070 Mobile, RX 6700 XT, Radeon Pro Vega 20, and RX 7800M — all score within 1.1% of the RTX 3090's average benchmark score, indicating that the RTX 3090 remains competitive with newer parts despite its age. The GPU's 350 W TDP and suggested 750 W PSU indicate that it requires substantial power delivery, and its triple-slot width and 336 mm length require a spacious case.

Rate My PC: AMD Ryzen 7 5700 + NVIDIA GeForce RTX 3090

Apex Performer

System Balance Analysis

AMD Ryzen 7 5700

NVIDIA GeForce RTX 3090

Market Position

Game Performance Benchmarks

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

Performance Insights

Optimal Performance

4K Gaming Ready

Performance Tiers Explained

Ultimate

High-End

Mid-Range

Entry Level

Legacy

4K Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

1440p Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

1080p Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

Related Processors

Related Graphics Cards

Compare Your CPU

Compare Your GPU

Related PC Builds

Same CPU with Different GPUs

Same GPU with Different CPUs

Other Popular Builds