SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 9 290K Plus + NVIDIA GeForce RTX 3090

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
98%
VS
GPU
93%
PROCESSOR

Intel Core Ultra 9 290K Plus

84,003 Benchmark Score
Top 2% 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

# Intel Core Ultra 9 290K Plus + NVIDIA GeForce RTX 3090

This desktop build pairs Intel’s flagship Arrow Lake Refresh processor with NVIDIA’s end-of-life Ampere flagship, creating a high-end workstation-oriented configuration. The CPU sits in the 96th percentile among all processors, while the GPU lands in the 73rd percentile, making this a lopsided pairing where compute-heavy tasks clearly favor the processor. The combined percentile for the system is 85, reflecting a machine that excels at multi-threaded productivity but remains more modest in graphics-bound workloads.

CPU Analysis

The Intel Core Ultra 9 290K Plus is a 24-core, 24-thread desktop processor built on a 3 nm TSMC process with the Arrow Lake Refresh codename. It belongs to the Core Ultra Series 2 generation and fits the Intel Socket 1851 platform. The base clock sits at 3.70 GHz, boosting up to 5.80 GHz, and the chip carries a 125 W TDP. The processor is unlocked, so users can push clock speeds beyond stock settings. It integrates Arc Xe-LPG Graphics with 64 execution units, providing a basic display output capability without a discrete GPU.

The cache hierarchy is substantial: 192 KB of L1 per core, 3 MB of L2 per core, and 36 MB of shared L3 cache. Memory support is DDR5 over a dual-channel bus, yielding a theoretical memory bandwidth of 115.2 GB/s. ECC memory support is present, which is notable for workstation reliability. The CPU provides PCIe Gen 5 with 20 lanes from the processor itself, enabling fast NVMe storage and expansion cards.

Benchmark results confirm the CPU’s strength. In Cinebench R23, the multicore score reaches 51,731, while the single-core score is 7,303. The R20 run shows 21,727 multicore and 3,067 single-core. R15 results are 5,214 multicore and 736 single-core. PassMark tests reveal a multithread score of 60,860 and a single-thread score of 4,823. Integer math hits 166,194, floating-point math reaches 214,760, and data compression scores 698,346. Data encryption is 52,563, extended instructions are 52,338, and random string sorting is 79,744. The find prime numbers test scores 503, and physics simulation scores 3,315.

The average benchmark score for this CPU is 84,003, placing it in the 96th percentile of all CPUs. Compared to the nearest rivals, the Core Ultra 9 290K Plus is 0.2% ahead of the Intel Core Ultra 9 285K, 1.1% ahead of the AMD EPYC 4584PX, and 1.2% ahead of the AMD EPYC 9135. It trails the AMD EPYC 7F72 by 1.3%. These deltas are small, indicating that the 290K Plus trades blows with high-end server and desktop parts, though the margin over the 285K is razor-thin.

Real-world implications: the multicore performance is exceptional for rendering, compilation, and simulation workloads. The single-core score suggests strong responsiveness in everyday tasks and lightly threaded applications. The 24 threads (not 48, since Hyper-Threading is absent) mean the processor relies on physical cores alone, which is sufficient for most professional workloads but may lag heavily threaded server chips with more threads.

Benchmark Performance

The CPU’s benchmark scores are dominant across the board. The Cinebench R23 multicore result of 51,731 places it firmly in high-end desktop territory, and the single-core score of 7,303 indicates excellent per-thread performance. PassMark multithread at 60,860 reinforces the CPU’s capability in parallel tasks. The floating-point math score of 214,760 is particularly strong for scientific and engineering applications.

The GPU’s benchmark scores are more modest. In 3DMark Steel Nomad DX12, the RTX 3090 scores 5,118. Geekbench OpenCL reaches 172,758, and Vulkan scores 53,927. PassMark G3D is 26,645, while GPU compute is 15,356. DirectX tests show 182 for DX10, 220 for DX11, and 110 for DX12. DirectX 9 scores 268, and G2D is 1,063. The average GPU benchmark score is 27,565, placing it in the 73rd percentile of all GPUs.

Relative to rivals, the RTX 3090 is 0.5% ahead of the NVIDIA GeForce RTX 4070 Mobile and 0.5% ahead of the AMD Radeon RX 6700 XT. It trails the AMD Radeon Pro Vega 20 by 1% and the AMD Radeon RX 7800M by 1.1%. These tight margins show that the RTX 3090, while older, still competes with mid-range current parts, but it is far from the top of the GPU hierarchy.

The combined picture is a system with a 96th-percentile CPU and a 73rd-percentile GPU, yielding an overall 85th-percentile combined score. This suggests that the CPU is the star of the show, and the GPU, while capable, is the limiting factor in graphics-heavy workloads. The data indicates that users should prioritize CPU-intensive tasks, where this build punches well above its weight.

GPU Analysis

The NVIDIA GeForce RTX 3090 is based on the GA102 chip with the Ampere architecture, manufactured on Samsung’s 8 nm process. The die is massive at 628 mm², containing 28,300 million transistors. The GPU has 10,496 shading units, 328 texture mapping units, and 112 raster output units. Ray tracing hardware includes 82 RT cores, and tensor cores number 328. The FP32 throughput is 35.58 TFLOPS, with FP16 at the same 35.58 TFLOPS (1:1 ratio).

Memory is a standout feature: 24 GB of GDDR6X on a 384-bit bus, delivering a bandwidth of 936.2 GB/s. The memory clock runs at 1,219 MHz, translating to 19.5 Gbps effective. This large frame buffer is ideal for high-resolution textures and large datasets in rendering or machine learning. The base clock is 1,395 MHz, boosting to 1,695 MHz. Pixel rate is 189.8 GPixel/s, and texture rate is 556.0 GTexel/s.

The card draws 350 W TDP and requires a 750 W suggested PSU. It uses a triple-slot cooler, measures 336 mm in length, 140 mm in height, and 61 mm in width. Power comes from a single 12-pin connector. Display outputs include 1x HDMI 2.1 and 3x DisplayPort 1.4a. The bus interface is PCIe 4.0 x16. API support includes DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The GPU is end-of-life, released on August 31, 2020, with a launch MSRP of 1,499 USD.

Benchmark results show the RTX 3090’s strengths and weaknesses. The 3DMark Steel Nomad score of 5,118 is respectable but not top-tier. Geekbench OpenCL at 172,758 indicates strong compute performance, while Vulkan at 53,927 is lower, suggesting driver or architecture limitations in that API. PassMark G3D at 26,645 is mid-range, and GPU compute at 15,356 is modest. The DirectX scores are low across the board, with DX12 at 110, which is surprising for a card of this class, but these are synthetic PassMark tests that may not reflect real-world gaming.

For rendering workloads, the 24 GB VRAM and 936.2 GB/s bandwidth are the key assets. The 82 RT cores and 328 tensor cores support ray tracing and DLSS, though the FP32 and FP16 performance are identical, meaning no half-precision boost for AI tasks. The texture rate of 556.0 GTexel/s and pixel rate of 189.8 GPixel/s are sufficient for high-resolution output, but the GPU’s age shows in raw rasterization compared to newer architectures.

Gaming Performance

No measured FPS data exists for this exact CPU+GPU combination. The FACT PACK contains no measured FPS rows, so all gaming performance figures below are estimated qualitatively from the benchmark scores and should be treated as approximations, not measured results.

Based on the GPU’s 73rd-percentile standing and the CPU’s 96th-percentile score, the system should handle 1440p gaming comfortably in most titles. The RTX 3090’s 24 GB VRAM is overkill for gaming, but the 936.2 GB/s bandwidth ensures high texture throughput. At 4K, the GPU will likely be the limiting factor, with frame rates dropping in demanding titles due to the GPU’s mid-range percentile rank. The CPU’s strong single-core score of 7,303 in Cinebench R23 suggests it will not bottleneck the GPU at lower resolutions, but the GPU’s raw rasterization performance is the ceiling.

Esports titles at 1080p should exceed 144 Hz in many cases, given the CPU’s high boost clock of 5.80 GHz and strong single-thread performance. AAA games at 1440p with ultra settings will likely see 60-100 FPS depending on the title, while 4K ultra will push toward 30-60 FPS in the most demanding games. Ray tracing performance, supported by 82 RT cores, will be playable but not exceptional, with DLSS helping to recover frame rates.

The lack of measured data means these estimates carry uncertainty. The GPU’s PassMark DirectX 12 score of 110 is alarmingly low, but this is a synthetic result that may not translate to real gaming performance. The 3DMark Steel Nomad score of 5,118 is more representative, suggesting a mid-to-high-end gaming experience, but not flagship-level.

Balance and Bottleneck

The CPU’s 96th-percentile ranking versus the GPU’s 73rd-percentile ranking creates a clear imbalance. In CPU-bound workloads like video encoding, 3D rendering, and software compilation, the Core Ultra 9 290K Plus will dominate, with the GPU serving as a secondary accelerator. The Cinebench R23 multicore score of 51,731 and PassMark multithread of 60,860 indicate the CPU can handle massive parallel loads without breaking a sweat.

In gaming, the GPU becomes the bottleneck at higher resolutions. The 3DMark Steel Nomad score of 5,118 and PassMark G3D of 26,645 suggest the RTX 3090 will limit frame rates in 4K scenarios, while the CPU’s headroom remains unused. At 1080p, the CPU’s strong single-core performance may allow the GPU to be the primary limiter even at lower resolutions, but the GPU’s moderate percentile means it will cap FPS well before the CPU’s potential is exhausted.

For mixed workloads, such as streaming while gaming or rendering while running background tasks, the CPU’s 24 cores provide ample margin. The data shows the CPU is 0.2% ahead of the Core Ultra 9 285K and 1.1% ahead of the EPYC 4584PX, so it competes with server-grade parts, while the GPU trails the RTX 4070 Mobile by 0.5%, indicating it is closer to mobile mid-range performance than desktop high-end.

The combined percentile of 85 reflects the GPU dragging the system down. Users should expect the CPU to be the workhorse, with the GPU handling graphics tasks adequately but not spectacularly. Upgrading the GPU would yield the largest performance gains in graphics-bound applications, while the CPU is unlikely to be a limiting factor for years.

Who Should Build It

This system targets professionals and enthusiasts who prioritize CPU compute over GPU performance. Content creators working with video editing, 3D rendering, or software development will benefit most from the 24-core processor, which delivers a 96th-percentile ranking and a Cinebench R23 multicore score of 51,731. The CPU’s ECC memory support and 115.2 GB/s bandwidth make it suitable for workstation builds where data integrity matters.

Gamers at 1440p will find the RTX 3090 adequate, with its 24 GB VRAM and 936.2 GB/s bandwidth handling modern titles, but those seeking 4K high-refresh gaming will be disappointed by the GPU’s 73rd-percentile rank. Students and small business users running multi-threaded applications like compilers, simulations, or data analysis will see strong performance from the CPU, while the GPU covers basic graphics needs.

Developers compiling large codebases will appreciate the 24 threads and high boost clock, and the PassMark data compression score of 698,346 suggests fast file handling. The GPU’s 24 GB VRAM is useful for machine learning inference or large dataset visualization, but the tensor core count of 328 is modest for heavy AI training. This build is best suited for CPU-centric workflows where the GPU is a supporting player.

FAQ

Q: What is the combined percentile ranking of this CPU+GPU build?

A: The combined percentile is 85, with the CPU at 96 and the GPU at 73.

Q: How does the Intel Core Ultra 9 290K Plus compare to the Core Ultra 9 285K?

A: The 290K Plus has an average benchmark score of 84,003, which is 0.2% higher than the 285K’s average score of 83,807.

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

A: The RTX 3090 has 24 GB of GDDR6X memory on a 384-bit bus, with a bandwidth of 936.2 GB/s.

Q: Does the CPU support ECC memory?

A: Yes, the Intel Core Ultra 9 290K Plus supports ECC memory.

Q: What is the CPU’s boost clock speed?

A: The boost clock is 5.80 GHz, with a base clock of 3.70 GHz.

Q: Is measured gaming FPS data available for this build?

A: No, there are no measured FPS rows for this exact combination, so all gaming performance figures are estimates.

Q: What is the GPU’s production status?

A: The NVIDIA GeForce RTX 3090 is end-of-life, having been released on August 31, 2020.

Build Overview

This is a desktop-class build combining the Intel Core Ultra 9 290K Plus, a 24-core Arrow Lake Refresh processor on the Intel Socket 1851 platform, with the NVIDIA GeForce RTX 3090, an Ampere-based GPU with 24 GB of GDDR6X memory. The CPU is in the 96th percentile of all processors, while the GPU is in the 73rd percentile, resulting in an overall combined percentile of 85. The CPU leads its nearest rival, the Core Ultra 9 285K, by just 0.2%, while the GPU is 0.5% ahead of the RTX 4070 Mobile and 0.5% ahead of the RX 6700 XT.

The system is CPU-dominated, with the processor’s Cinebench R23 multicore score of 51,731 and PassMark multithread of 60,860 far exceeding the GPU’s 3DMark Steel Nomad score of 5,118. The GPU’s 24 GB VRAM and 936.2 GB/s bandwidth are its standout features, making it suitable for large datasets, but its raw compute is mid-range by current standards. This pairing is best described as a high-end workstation CPU with a capable but aging GPU, suited for productivity over pure gaming.

Usage Scenarios

High-refresh gaming: The CPU’s 5.80 GHz boost clock and single-core Cinebench R23 score of 7,303 provide ample headroom for 1080p esports at high frame rates, but the GPU’s 73rd-percentile rank will cap 1440p and 4K performance, making 144 Hz at high settings unlikely in AAA titles.

Streaming: The 24-core CPU can handle encoding and gaming simultaneously, with a PassMark multithread score of 60,860 ensuring smooth streaming, while the GPU’s NVENC (implied by the tensor cores) supports hardware encoding, though no specific streaming benchmark exists in the data.

Video editing: The CPU’s Cinebench R23 multicore score of 51,731 accelerates rendering and export times, and the GPU’s 24 GB VRAM allows for large timelines and effects, with the 936.2 GB/s bandwidth facilitating quick asset loading.

3D rendering: CPU-based renderers will excel, with the 24-core processor dominating multi-threaded workloads, while GPU rendering benefits from the RTX 3090’s 82 RT cores and 35.58 TFLOPS FP32, though the GPU’s 73rd-percentile rank limits ray-traced scenes.

Software development: Compilation speeds are strong, with the CPU’s PassMark integer math score of 166,194 and data compression of 698,346, and the 24 threads handle parallel builds efficiently, while the GPU is more than adequate for UI rendering.

Student and office work: This build is overkill for typical productivity, but the CPU’s single-core performance ensures snappy application response, and the integrated Arc graphics (64 EU) could handle basic display tasks if the discrete GPU is not needed, though the 350 W GPU TDP makes this an inefficient choice for light use.