SYSTEM ANALYZER

Rate My PC: Intel Core i9-13900 + NVIDIA GeForce RTX 5090

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

97 / 100
ULTIMATE READY

Apex Performer

Top 3% 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
95%
VS
GPU
98%
PROCESSOR

Intel Core i9-13900

60,676 Benchmark Score
Top 5% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5090

79,842 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

CPU Analysis

The Intel Core i9-13900 is a 24-core, 32-thread desktop processor built on the Raptor Lake architecture and manufactured on Intel's 10 nm process. It belongs to the Core 13th Gen family, and its hybrid design combines performance and efficiency cores to deliver a base clock of 2000 MHz and a boost clock of 5.60 GHz. The chip carries a 65 W TDP, which is notably modest for a 24-core part, and it supports both DDR4 and DDR5 memory through a dual-channel memory bus, with ECC memory support included. The CPU also integrates UHD Graphics 770, making it a viable option for systems that need a fallback display output without a discrete GPU.

In Cinebench R23, the processor scores 37,931 in multi-core and 5,355 in single-core. These are strong figures that place it in the top tier of desktop CPUs. The multi-core result indicates that the chip can handle heavily threaded workloads such as video rendering, 3D scene compilation, and software builds with ease. The single-core score of 5,355 is equally important for everyday responsiveness and lightly threaded applications. In Cinebench R20, the scores are 15,931 multi-core and 2,249 single-core, while Cinebench R15 shows 3,823 multi-core and 539 single-core. The scaling across these versions is consistent, confirming that the processor maintains its performance advantage regardless of the benchmark generation.

Geekbench results reinforce the picture: a multi-core score of 21,164 and a single-core score of 2,604. These numbers align with what one would expect from a high-end desktop chip with 32 threads. The Passmark suite provides additional insight into specific workload types. The multi-thread score is 45,680, while single-thread is 4,309. Integer math scores 176,107, and floating-point math scores 120,492. Data compression reaches 577,285, and data encryption is 35,242. Extended instructions hit 32,760, and random string sorting is 64,396. The find prime numbers test is lower at 186, which is typical for a CPU that prioritizes parallel throughput over single-thread integer iteration. Physics simulation scores 2,484.

The CPU's average benchmark score is 60,676, and it sits at the 92nd percentile among all CPUs. Its nearest rivals include the Intel Xeon Gold 6338T with an average score of 60,572 (0.2% delta), the AMD Ryzen 7 8745HX at 60,104 (1% delta), the AMD Ryzen 9 7945HX at 60,099 (1% delta), and the Intel Core i9-14900F at 60,008 (1.1% delta). The deltas are narrow, which means the i9-13900 is effectively trading blows with these chips. It is marginally ahead of the Xeon Gold 6338T and the two Ryzen mobile-derived parts, and it leads the i9-14900F by just over one percent. For real workloads, this translates to near-identical performance in multi-threaded tasks, with the i9-13900 holding a slight edge that may not be perceptible outside of extended renders or batch processing.

The cache hierarchy consists of 80 KB of L1 per core, 2 MB of L2 per core, and 36 MB of shared L3. This large L3 pool benefits workloads that repeatedly access a working set, such as database queries or certain scientific simulations. The PCIe implementation is Gen 5 with 16 CPU lanes, which is sufficient for a single high-end graphics card and fast NVMe storage. The processor was released on 2023-01-03 with a launch MSRP of $549, and its part number is SRMB6.

FAQ

Q: What is the core and thread count of the Intel Core i9-13900?

A: The CPU has 24 cores and 32 threads, combining performance and efficiency cores in the Raptor Lake architecture.

Q: How does the i9-13900 compare to the Intel Core i9-14900F in average benchmark score?

A: The i9-13900 has an average score of 60,676, which is 1.1% higher than the i9-14900F's 60,008.

Q: What is the boost clock speed of this processor?

A: The maximum boost clock is 5.60 GHz, with a base clock of 2000 MHz.

Q: Does the CPU support DDR4 and DDR5 memory?

A: Yes, the memory support includes both DDR4 and DDR5, using a dual-channel memory bus. ECC memory is also supported.

Q: What is the TDP of the Core i9-13900?

A: The thermal design power is 65 W, which is low for a 24-core part and enables more flexible cooling solutions.

Q: What integrated graphics does the CPU include?

A: It includes UHD Graphics 770, which provides basic display output without requiring a discrete GPU.

Q: What is the process node for this chip?

A: The processor is manufactured on Intel's 10 nm process, with a die size of 257 mm².

Benchmark Performance

The Intel Core i9-13900 and NVIDIA GeForce RTX 5090 pairing has no measured FPS data in the database for this exact combination. The FACT PACK contains no measuredFps rows, so all frame rate discussion here is estimated from the individual benchmark scores of each component.

The CPU's average benchmark score is 60,676, placing it at the 92nd percentile among all CPUs. The GPU's average benchmark score is 79,842, also at the 92nd percentile among all GPUs. The combined percentile for the system is 92. This symmetry means neither component is dragging the other down in terms of tier; both are top-tier parts that should deliver high frame rates in most scenarios.

The GPU reports a 3DMark Steel Nomad DX12 score of 18,355. This is a modern rasterization test that stresses the graphics pipeline heavily. A score in this range indicates very high throughput for current-generation games. Geekbench OpenCL scores 334,370, and Vulkan scores 376,728. The Vulkan score being higher than OpenCL suggests the architecture scales well with modern low-level APIs. Passmark G3D scores 39,650, while G2D is 1,413. The DirectX tests show 226 for DX10, 341 for DX11, 185 for DX12, and 395 for DX9. These Passmark DX scores are metrics of specific API paths rather than direct gaming proxies, but they confirm broad API support. GPU compute scores 26,756.

The CPU's Cinebench R23 multi-core score of 37,931 is the headline number for productivity. Combined with the GPU's 3DMark Steel Nomad score, the system is well-suited for both high-refresh gaming and rendering. In gaming, the CPU can feed the GPU without bottlenecking in most titles, given its strong single-thread score of 5,355 in R23. For rendering, the CPU handles the geometry and physics while the GPU handles rasterization and ray tracing. The estimated FPS for this pairing would be high at both 1080p and 1440p, with 4K performance limited more by the GPU's raw throughput than the CPU.

The CPU's percentile position of 92 means it outperforms 92% of all CPUs in the database. The GPU's 92nd percentile is identical. This alignment indicates a balanced system in terms of tier, though balance at the workload level depends on resolution and game settings. At lower resolutions, the CPU will matter more; at higher resolutions, the GPU becomes the dominant factor.

Upgrade Path and Platform

The Intel Core i9-13900 uses the Intel Socket 1700 platform, which is a mature socket for the 13th Gen Core series. Memory support covers both DDR4 and DDR5, giving builders flexibility. Using DDR5 with a dual-channel configuration will maximize bandwidth for the CPU's 36 MB L3 cache, while DDR4 offers a lower-cost entry point. ECC memory support is present, which is unusual for a consumer desktop chip and may appeal to small workstation builders who want error correction without moving to a Xeon platform.

The PCIe implementation is Gen 5 with 16 lanes from the CPU. This provides ample bandwidth for a single high-end GPU like the RTX 5090, which uses a PCIe 5.0 x16 interface. Storage devices that use Gen 5 lanes can also be attached, though 16 lanes total means a balance must be struck between GPU and NVMe allocation. The CPU's TDP is 65 W, which is low for its core count, so most mid-range air coolers or all-in-one liquid coolers will handle it comfortably. The socket 1700 platform has been used across multiple generations, so there is a wide ecosystem of motherboards with varied feature sets.

The RTX 5090 has a TDP of 575 W and a suggested PSU rating of 950 W. This power supply headroom is critical. A 950 W PSU provides enough capacity for the CPU and GPU under full load, plus overhead for other components. The GPU uses a single 16-pin power connector, so the PSU must have the appropriate cable or an adapter. The card is dual-slot and measures 304 mm in length, 137 mm in height, and 40 mm in width, so case compatibility requires checking clearance.

A sensible next upgrade for this platform would be a higher-core-count Raptor Lake or a newer generation CPU that fits Socket 1700, if one exists. The i9-13900 already sits near the top of the consumer stack, so the upgrade headroom is limited. For memory, moving to faster DDR5 kits could yield marginal gains in bandwidth-sensitive tasks. For storage, adding a Gen 5 NVMe drive would take advantage of the CPU's PCIe lanes. The platform is otherwise well-balanced, and the most impactful upgrade would be a larger capacity GPU, though the RTX 5090 is already at the high end. The PSU at 950 W leaves little room for additional power-hungry components, so any future upgrade should respect the power budget.

GPU Analysis

The NVIDIA GeForce RTX 5090 is built on the Blackwell 2.0 architecture, using the GB202 chip manufactured at TSMC's 5 nm process. The die contains 92,200 million transistors across a 750 mm² area, giving a transistor density of 122.9 million per mm². The GPU has 32 GB of GDDR7 memory on a 512-bit bus, yielding a bandwidth of 1.79 TB/s. This memory capacity and bandwidth are exceptional, making the card suitable for large datasets, high-resolution textures, and compute workloads that exceed the VRAM of most other cards.

Clock speeds are a base of 2017 MHz and a boost of 2407 MHz, with memory running at 1750 MHz or 28 Gbps effective. The shading units number 21,760, with 680 texture mapping units and 176 render output units. Ray tracing is handled by 170 RT cores, and 680 tensor cores accelerate AI workloads. Pixel rate is 423.6 GPixel/s, texture rate is 1,636.8 GTexel/s, and FP32 throughput is 104.8 TFLOPS, with FP16 at the same 104.8 TFLOPS (1:1). These raw numbers place the card at the top of the consumer GPU stack.

The benchmark results confirm the hardware's capability. The 3DMark Steel Nomad DX12 score of 18,355 is a strong indicator of rasterization performance in modern games. Geekbench Vulkan scores 376,728, which is higher than the OpenCL score of 334,370, showing that the card excels with low-level APIs. Passmark G3D scores 39,650, placing it in the top percentile among GPUs. GPU compute scores 26,756, which reflects the tensor and compute throughput. The average benchmark score is 79,842, at the 92nd percentile. Nearest rivals include the NVIDIA Tesla P100 PCIe 16 GB at 79,605 (0.3% delta), the Tesla P100 PCIe 12 GB at 79,396 (0.6% delta), the AMD Radeon RX 6850M XT at 78,940 (1.1% delta), and the AMD Radeon Pro Vega 64X at 80,959 (-1.4% delta). The deltas are small, but the RTX 5090 leads three of these four rivals, and trails the Pro Vega 64X by 1.4%.

For rendering, the combination of 32 GB VRAM and 104.8 TFLOPS FP32 means large scenes can be loaded entirely into memory without streaming from system RAM. The ray tracing cores accelerate path tracing and global illumination, while the tensor cores enable DLSS and other AI-based features. The 512-bit memory bus provides the bandwidth needed to feed the 21,760 shading units at high resolutions. The card supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, ensuring broad compatibility with current software. Display outputs include 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Who Should Build It

This system is for users who demand top-tier performance in both CPU and GPU workloads. Gamers targeting high refresh rates at 1440p or 4K will benefit from the CPU's strong single-thread score of 5,355 in Cinebench R23 and the GPU's 18,355 in 3DMark Steel Nomad. The 32 GB VRAM ensures that texture-heavy games at 4K will not run out of memory, and the 1.79 TB/s bandwidth supports high-resolution assets.

Content creators who edit video or work with large image sequences will see fast render times from the CPU's 37,931 multi-core R23 score, while the GPU accelerates effects and exports. 3D artists using ray-traced renderers will find the 170 RT cores and 104.8 TFLOPS FP32 performance valuable. The 32 GB VRAM allows for complex scenes with many objects and high-resolution textures.

Software developers compiling large codebases will benefit from the 24 cores and 32 threads. The Passmark integer math score of 176,107 indicates strong parallel integer throughput. Data compression at 577,285 helps with build artifacts and version control operations. Developers using AI frameworks can leverage the 680 tensor cores for training and inference.

Students in engineering or computer science programs can use this system for CAD, simulation, and programming assignments. The ECC memory support adds reliability for long-running computations. Small business workstations that run virtualization, databases, or financial modeling will find the CPU's 36 MB L3 cache and the GPU's compute capability useful. The dual-slot, 304 mm GPU requires a roomy case, and the 950 W PSU recommendation should be followed strictly.

Balance and Bottleneck

The CPU and GPU both sit at the 92nd percentile, which suggests a balanced pairing in terms of overall tier. However, workload-specific balance varies. In gaming at 1080p, the CPU's single-thread performance will often be the limiting factor, as lower resolutions put more pressure on the processor to feed frames to the GPU. The i9-13900's single-core score of 5,355 in R23 is high, so it will handle most titles well, but the RTX 5090 is so fast that even a top-tier CPU may occasionally hold it back at very low resolutions.

At 1440p and 4K, the GPU becomes the bottleneck. The RTX 5090's raw throughput is massive, but higher resolutions increase pixel count and shading load, shifting the balance toward the GPU. The 32 GB VRAM and 1.79 TB/s bandwidth ensure that memory capacity is not a constraint, but the shader and RT core throughput will cap frame rates. The 3DMark Steel Nomad score of 18,355 suggests that the GPU can handle demanding rasterization, but the CPU's role diminishes as resolution increases.

For productivity workloads, the balance depends on the task. Video editing uses both the CPU and GPU: the CPU handles timeline and encoding, while the GPU accelerates effects and color grading. The CPU's 37,931 multi-core R23 score and the GPU's compute score of 26,756 complement each other. 3D rendering with ray tracing will favor the GPU heavily, given the 170 RT cores, while physics simulation may use the CPU's 24 cores. The Passmark physics score of 2,484 indicates the CPU handles physics calculations well, but the GPU's FP32 throughput is far higher for parallel compute.

In games that rely heavily on single-threaded game logic, the CPU may limit frame rates even at high resolutions. The single-core Geekbench score of 2,604 is strong, but some engines are sensitive to core-to-core latency. In contrast, games with good multi-threaded scaling will leverage the 32 threads. The estimated FPS picture, derived from benchmark scores, shows that this system is unlikely to be CPU-bound in most modern titles at 1440p or higher, but at 1080p with a fast GPU, the CPU will be the limiting factor in many cases.

Build Overview

This is a desktop build combining the Intel Core i9-13900 with the NVIDIA GeForce RTX 5090. The CPU is a 24-core, 32-thread Raptor Lake part with a 65 W TDP and a 5.60 GHz boost clock. The GPU is a Blackwell 2.0 flagship with 32 GB GDDR7 on a 512-bit bus, 21,760 shading units, and a 575 W TDP. Both components sit at the 92nd percentile in their respective categories, and the combined percentile is also 92.

The CPU's average benchmark score of 60,676 places it just above the Intel Xeon Gold 6338T, AMD Ryzen 7 8745HX, AMD Ryzen 9 7945HX, and Intel Core i9-14900F. The GPU's average score of 79,842 places it above the Tesla P100 variants and the RX 6850M XT, while trailing the Radeon Pro Vega 64X by 1.4%. This build is a high-end desktop configuration intended for demanding workloads. The CPU provides strong multi-threaded performance for productivity, and the GPU delivers top-tier rasterization and ray tracing. The system requires a 950 W PSU and a case that can accommodate a dual-slot, 304 mm GPU.

The launch MSRP for the CPU is $549, and the GPU has a launch MSRP of 1,999 USD. This is a premium build for users who need maximum performance in both CPU and GPU-bound tasks.

Usage Scenarios

High-refresh gaming: At 1080p and 1440p, the CPU's single-core Cinebench R23 score of 5,355 ensures that frame rates are not limited by the processor in most titles. The GPU's 18,355 in 3DMark Steel Nomad provides the raw throughput to drive high refresh rates. At 4K, the GPU becomes the primary driver, and the 32 GB VRAM prevents texture-related stuttering.

Streaming: The CPU has 24 cores and 32 threads, which can handle game encoding alongside the game itself. The Passmark data compression score of 577,285 indicates fast encoding throughput. The GPU's tensor cores can also accelerate encoding tasks, offloading work from the CPU.

Video editing: The CPU's multi-core R23 score of 37,931 speeds up timeline preview and export. The GPU's 104.8 TFLOPS FP32 accelerates effects, color grading, and rendering. The 32 GB VRAM allows for large projects to reside entirely on the GPU.

3D rendering: The GPU's 170 RT cores and 104.8 TFLOPS FP32 provide fast ray-traced rendering. The 32 GB VRAM holds large scenes. The CPU's 24 cores handle geometry processing and scene setup, with the 36 MB L3 cache reducing memory latency.

Software development: Compilation is parallelized across 32 threads, and the Passmark integer math score of 176,107 reflects strong integer throughput. The ECC memory support adds stability for long builds. The GPU's compute capability is available for developers working on GPU-accelerated applications.

Student and office work: While this system is overkill for basic office tasks, the CPU's single-thread score of 4,309 in Passmark ensures snappy responsiveness. The UHD Graphics 770 provides a fallback if the discrete GPU is disabled. For data analysis or engineering software, the CPU's multi-threaded performance and the GPU's compute power are valuable.