SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 9 290K Plus + NVIDIA GeForce RTX 5070 SUPER

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

88 / 100
HIGH-END

Power Build

Top 12% of systems. Excellent for 1440p Ultra or 4K High gaming.

1440p Ultra4K High

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
98%
VS
GPU
79%
PROCESSOR

Intel Core Ultra 9 290K Plus

84,003 Benchmark Score
Top 2% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5070 SUPER

2,690 Benchmark Score
Top 21% 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

Strong Performance

Excellent for 1440p gaming. Most games will run at high/ultra settings smoothly.

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 Intel Core Ultra 9 290K Plus is a desktop-class processor that anchors this build, delivering top-tier multi-threaded performance that outpaces its closest rivals, while the NVIDIA GeForce RTX 5070 SUPER provides a modern GPU foundation. The benchmark data shows a dramatic disparity in performance tiers, with the CPU ranking in the 96th percentile among all CPUs and the GPU sitting in the 18th percentile among all GPUs, creating a system where the processor is the clear performance leader. This pairing is best understood as a workstation-class CPU with a capable, entry-level GPU, making it suitable for compute-heavy tasks rather than high-end gaming.

CPU Analysis

The Intel Core Ultra 9 290K Plus is built on the Arrow Lake Refresh architecture using a 3 nm process from TSMC, a significant manufacturing advantage that contributes to its efficiency. The CPU contains 24 cores and 24 threads, with a base clock of 3.70 GHz and a boost clock of 5.80 GHz, and it draws a TDP of 125 W. The 24 threads equal the core count, meaning there is no hyper-threading, but the sheer number of physical cores ensures strong parallel processing capabilities. The cache hierarchy includes 192 KB of L1 per core, 3 MB of L2 per core, and 36 MB of shared L3 cache, which is ample for feeding data to the cores during intensive workloads. The CPU supports DDR5 memory in a dual-channel configuration, with a memory bandwidth of 115.2 GB/s, and it supports ECC memory, making it suitable for error-sensitive computations. The processor also includes integrated Arc Xe-LPG Graphics with 64 execution units, providing a fallback display output, and it connects via PCIe Gen 5 with 20 lanes from the CPU.

Benchmark results show the CPU’s multi-core dominance. In Cinebench R23, the multicore score is 51731, which is exceptionally high, while the single-core score is 7303. The Cinebench R20 scores are 21727 for multicore and 3067 for single-core, and the older R15 test yields 5214 for multicore and 736 for single-core. PassMark tests reveal strengths in specialized tasks: the floating-point math score is 214760, the integer math score is 166194, and the extended instructions score is 52338. Data encryption scores 52563, while data compression scores 698346, indicating strong throughput for file archiving and cryptographic workloads. The multithread score is 60860, and the single-thread score is 4823, with a physics score of 3315. The average benchmark score is 84003, placing the CPU in the 96th percentile of all CPUs, meaning it outperforms the vast majority of processors on the market.

Relative to its nearest rivals, the CPU leads by a small margin. It is 0.2% ahead of the Intel Core Ultra 9 285K, which scores 83807, and 1.1% ahead of the AMD EPYC 4584PX, which scores 83090. It is also 1.2% ahead of the AMD EPYC 9135, which scores 82980, but it trails the AMD EPYC 7F72 by 1.3%, which scores 85072. These deltas are all within a couple of percent, indicating that the 290K Plus is at parity with the best server and enthusiast CPUs in its class, though the EPYC 7F72 holds a slight edge. For real workloads, this means the CPU will handle video rendering, software compilation, and scientific simulations with ease, as the multi-core scores are among the highest recorded.

Benchmark Performance

The CPU’s benchmark scores are the headline numbers for this build. In Cinebench R23, the multicore score of 51731 is a strong indicator of heavy multi-threaded performance, suitable for 3D rendering and batch processing. The single-core score of 7303 ensures responsiveness in lightly threaded applications like web browsing and office productivity. PassMark tests reinforce this: the multithread score of 60860 and the floating-point math score of 214760 show a processor that excels at parallel arithmetic, common in physics simulations and financial modeling. The single-thread score of 4823 is respectable, ensuring everyday tasks do not feel sluggish.

The GPU, however, presents a stark contrast. The NVIDIA GeForce RTX 5070 SUPER has a single benchmark result: a 3DMark Steel Nomad DX12 score of 2690. This places the GPU in the 18th percentile among all GPUs, which is a low ranking, and its average benchmark score is 2690. The nearest rivals are all older or lower-tier cards: the NVIDIA Quadro K1100M scores 2664 (1% behind), the NVIDIA GeForce GT 1030 scores 2662 (1.1% behind), the Intel Arc Pro B50 scores 2660 (1.1% behind), and the NVIDIA GeForce GT 440 scores 2645 (1.7% behind). The RTX 5070 SUPER is only marginally ahead of these, by 1% to 1.7%, meaning its raw 3D performance is comparable to entry-level GPUs from several generations ago. The GPU is built on the Blackwell 2.0 architecture with a GB205 chip, using a 5 nm process from TSMC, and it has 6400 shading units, 200 texture mapping units, and 80 raster operation units. It also includes 50 ray tracing cores and 200 tensor cores, with 18 GB of GDDR7 memory on a 192-bit bus providing 672.0 GB/s of bandwidth. The FP32 performance is 32.15 TFLOPS, and the pixel rate is 201.0 GPixel/s, yet the 3DMark score indicates that real-world gaming performance is limited.

The combined picture is a system where the CPU is a top-tier performer, but the GPU holds the system back in graphics-intensive applications. The combined percentile for the build is 57, reflecting the average of the two components, and this is dragged down by the GPU’s low percentile. For users who prioritize CPU-bound tasks like compiling code or rendering video, this is a strong machine, but for gaming, the GPU will be the limiting factor.

Balance and Bottleneck

The data clearly shows a CPU-bound system where the processor is overqualified relative to the GPU. The CPU’s 96th percentile ranking means it is in the top 4% of all processors, while the GPU’s 18th percentile places it in the bottom fifth of all graphics cards. In gaming workloads, the GPU will be the bottleneck because it cannot keep up with the CPU’s ability to feed it frames. The CPU can generate game logic and physics calculations far faster than the GPU can render them, leading to situations where the GPU utilization is at 100% while the CPU waits. This is the classic symptom of a GPU-limited system, where lowering resolution or graphics settings will not improve frame rates because the GPU is already maxed out.

Conversely, in CPU-heavy workloads such as video encoding, 3D rendering, or data compression, the CPU will be the primary workhorse, and the GPU’s role is minimal. The PassMark data compression score of 698346 and the multithread score of 60860 indicate that the CPU can process large datasets quickly, and the GPU’s low score will not interfere with these tasks. The FPS scaling, as estimated from the benchmark scores, will be poor in games because the GPU’s 3DMark Steel Nomad score of 2690 is close to the scores of much older GPUs, suggesting that frame rates will be lower than what a modern gaming GPU would deliver. The CPU will not bottleneck the GPU, but the GPU will bottleneck the CPU in any graphics-intensive scenario, making this an unbalanced pairing for gaming.

Upgrade Path and Platform

The CPU uses the Intel Socket 1851, which is the platform for the Core Ultra Series 2 processors. The CPU supports DDR5 memory in a dual-channel configuration, and it supports ECC memory, which is a feature geared toward workstation reliability. The memory bandwidth is 115.2 GB/s, and the CPU provides 20 PCIe Gen 5 lanes, which are reserved for the GPU and high-speed NVMe storage. The integrated Arc Xe-LPG Graphics with 64 execution units can serve as a backup display adapter, but the primary GPU is the RTX 5070 SUPER, which uses a PCIe 5.0 x16 interface.

The RTX 5070 SUPER has a TDP of 275 W, and while the suggested PSU is not specified in the data, the TDP suggests that a capable power supply is needed. The system’s total power draw will be dominated by the GPU, given that the CPU’s TDP is 125 W. The GPU requires a single 16-pin power connector, and it is a dual-slot card with dimensions of 245 mm in length, 115 mm in height, and 40 mm in width, so case compatibility is important. For a sensible next upgrade, the data points to replacing the GPU, as it is the weakest component. The CPU has headroom to support a much more powerful GPU without becoming a bottleneck, and the PCIe 5.0 x16 slot ensures that a future GPU will have full bandwidth. The platform itself is current, with support for DDR5 and PCIe Gen 5, so there is no need to change the motherboard or memory for several years.

Who Should Build It

This build is targeted at users who need extreme CPU performance for non-graphics workloads. Software developers compiling large codebases will benefit from the 24 cores and the Cinebench R23 multicore score of 51731, which shortens build times. Content creators working with video editing or 3D rendering will see fast export times in CPU-based renderers, as the PassMark floating-point math score of 214760 indicates strong arithmetic throughput. Students and researchers running simulations or data analysis will appreciate the ECC memory support and the high multithread score of 60860, ensuring data integrity and fast computation. Small business workstations that handle database processing or encryption will find the data compression score of 698346 and the data encryption score of 52563 to be valuable, as these tasks are CPU-bound and the GPU is not a factor.

For gamers, this build is not ideal. The GPU’s 18th percentile ranking means it will deliver low frame rates at any resolution, and the CPU’s power is wasted in most games that rely more on the GPU. However, for gamers who play CPU-intensive simulation or strategy games, the single-core score of 7303 in Cinebench R23 provides a responsive experience, though the GPU will still limit visual fidelity. This build is best suited for professionals who prioritize compute power over graphics, and who may pair this CPU with a better GPU later.

FAQ

Q: What is the CPU’s percentile ranking among all processors?

A: The Intel Core Ultra 9 290K Plus ranks in the 96th percentile among all CPUs, meaning it outperforms 96% of processors in benchmark tests.

Q: How does the CPU compare to its nearest rival, the Intel Core Ultra 9 285K?

A: The 290K Plus is 0.2% ahead of the 285K in average benchmark score, with the 290K Plus scoring 84003 versus 83807 for the 285K.

Q: What is the GPU’s 3DMark Steel Nomad score?

A: The NVIDIA GeForce RTX 5070 SUPER scores 2690 in the 3DMark Steel Nomad DX12 test, placing it in the 18th percentile among all GPUs.

Q: Does the CPU support ECC memory?

A: Yes, the Intel Core Ultra 9 290K Plus supports ECC memory, which is useful for error-correcting workloads in professional environments.

Q: What is the memory bandwidth of the CPU?

A: The CPU has a memory bandwidth of 115.2 GB/s, using dual-channel DDR5 memory.

Q: How many PCIe lanes does the CPU provide?

A: The CPU provides 20 PCIe Gen 5 lanes, which are used for the GPU and high-speed storage devices.

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

A: The GPU has 18 GB of GDDR7 memory on a 192-bit bus, providing 672.0 GB/s of bandwidth.

Gaming Performance

There are no measured FPS rows for this exact CPU+GPU combination, and the FACT PACK contains no measured FPS data for this pairing. Therefore, the following frame rate discussion is estimated from the benchmark scores, and the figures should be treated as estimates rather than verified results. The GPU’s 3DMark Steel Nomad score of 2690 is in the 18th percentile, and its nearest rivals include the NVIDIA GeForce GT 1030 and the GT 440, which are entry-level cards from previous generations. This suggests that the RTX 5070 SUPER will deliver low frame rates at 1080p resolution in modern games, likely in the range of 30-60 FPS on medium to low settings, and it will struggle to maintain playable frame rates at 1440p or 4K. The CPU’s high single-core score of 7303 in Cinebench R23 ensures that the processor can handle game logic, but the GPU will be the bottleneck, capping the frame rate regardless of the CPU’s speed. For competitive esports titles with low graphical demands, the frame rates may be higher, but for AAA games with high fidelity, the GPU will limit performance. Gamers should expect a suboptimal experience, and the GPU should be upgraded to a higher-tier card to unlock the CPU’s potential in gaming.

Build Overview

This is a desktop build combining the Intel Core Ultra 9 290K Plus and the NVIDIA GeForce RTX 5070 SUPER. The CPU is a high-end desktop processor from the Core Ultra Series 2, while the GPU is a current-generation GeForce 50-series card. The combined percentile for this build is 57, reflecting a system that is above average when considering both components together. However, this average is skewed by the CPU’s high 96th percentile, which is offset by the GPU’s low 18th percentile. The build is best described as a compute-focused workstation with a modest graphics capability, and it is not a balanced gaming machine. The CPU is the dominant component, and the GPU is the weakest link.

Usage Scenarios

High-refresh gaming: The GPU’s low 3DMark score of 2690 and 18th percentile ranking mean that high-refresh gaming is not achievable. The GPU will bottleneck the CPU, and frame rates will be too low for high-refresh monitors, so this scenario is not recommended.

Streaming: The CPU’s 24 cores and high multicore scores, such as the Cinebench R23 score of 51731, can handle video encoding for streaming while gaming, but the GPU’s low performance will limit game quality, making this a poor fit for streamers who play graphically demanding titles.

Video editing: The CPU excels in video editing, with a PassMark multithread score of 60860 and a floating-point math score of 214760, which handle timeline scrubbing and effects rendering well. The GPU’s limited performance will not accelerate GPU-accelerated effects as much as a better card, but CPU-based rendering will be fast.

3D rendering: The CPU is a powerhouse for CPU-based 3D rendering, as indicated by the Cinebench R23 multicore score of 51731, which is in the top percentile. The GPU’s 18 GB of memory is ample for scene data, but its low compute score of 2690 means GPU-based renderers will be slow.

Software development: Developers will benefit from the CPU’s high multithread score of 60860, which speeds up code compilation, and the ECC memory support ensures data integrity. The GPU is irrelevant for most development tasks, so this is a strong use case.

Student and office work: The CPU’s single-core score of 7303 in Cinebench R23 ensures snappy responsiveness in office applications, and the 24 cores provide future-proofing for multitasking. The GPU is sufficient for basic display output, making this an overkill but functional office machine.