SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 5 235 + NVIDIA GeForce RTX 5090 D V2

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

92 / 100
ULTIMATE READY

Apex Performer

Top 8% 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
93%
VS
GPU
90%
PROCESSOR

Intel Core Ultra 5 235

46,062 Benchmark Score
Top 7% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5090 D V2

16,504 Benchmark Score
Top 10% 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 Intel Core Ultra 5 235 and NVIDIA GeForce RTX 5090 D V2 form a desktop pairing that presents a striking contrast in performance tiers. The CPU sits in the 89th percentile among all processors, while the GPU, despite its flagship name and specifications, lands in the 59th percentile based on available benchmark data. This combination offers a high-core-count, efficient processor paired with a graphics card that has substantial memory resources but shows modest measured performance in its single available benchmark. The following analysis breaks down the components, their measured scores, and how they interact for various workloads.

CPU Analysis

The Intel Core Ultra 5 235 is a 14-core, 14-thread desktop processor built on the Arrow Lake architecture, representing the Core Ultra Series 2 generation. It is fabricated on a 3 nm process by TSMC, containing 17,800 million transistors on a 243 mm² die. The base clock is 3.40 GHz, with a boost clock reaching 5.00 GHz. The cache hierarchy includes 192 KB of L1 per core, 3 MB of L2 per core, and 24 MB of shared L3 cache. The processor supports dual-channel DDR5 memory with a bandwidth of 102.4 GB/s, and it connects to the system via PCIe Gen 5 with 20 CPU lanes.

Benchmark results show a multicore Cinebench R23 score of 14,769 points and a single-core score of 2,085 points. In Cinebench R20, the scores are 6,202 multicore and 875 single-core. The PassMark multithread score is 37,816, with a single-thread score of 4,516. The average benchmark score across all tests is 46,062, placing the CPU in the 89th percentile of all CPUs. This percentile ranking indicates strong overall performance, though the nearest rivals are notably close: the AMD Ryzen AI 9 HX 375 scores 46,030 (0.1% higher), the Intel Core i9-13900HX scores 46,098 (0.1% lower), and both the AMD EPYC 4364P and EPYC 7303 score within 0.2% of this processor.

For real workloads, the Cinebench scores suggest that the CPU handles heavily threaded tasks like video rendering and 3D modeling well, but the 14-thread count (without hyperthreading) means scaling in multi-threaded applications is limited compared to processors with more threads. The single-core performance, reflected in the 2,085 R23 score, is competitive for tasks like web browsing, office productivity, and lightly threaded applications. The PassMark data encryption score of 29,293 and data compression score of 390,711 indicate solid performance in data-centric workloads, while the floating-point math score of 117,951 and integer math score of 87,948 show balanced arithmetic capabilities. The extended instructions score of 32,752 suggests good support for modern SIMD workloads.

Upgrade Path and Platform

The Intel Core Ultra 5 235 uses the Intel Socket 1851 platform, which is specific to the Core Ultra Series 2 desktop processors. This socket supports DDR5 memory exclusively, and the dual-channel memory controller provides a peak bandwidth of 102.4 GB/s. The platform includes PCIe Gen 5 support with 20 lanes available from the CPU, which is sufficient for a high-end graphics card and a Gen 5 NVMe SSD. The processor has a TDP of 65 W, which is modest for a desktop CPU and indicates efficient power draw under load.

The GPU, however, has a TDP of 575 W and requires a suggested PSU of 950 W. This is the dominant power consideration in the system. The CPU’s 65 W TDP leaves substantial headroom for the graphics card and other components within the 950 W power budget. The platform supports one 16-pin power connector for the GPU, and the card is dual-slot wide, measuring 304 mm in length, 137 mm in height, and 48 mm in width. A sensible next upgrade path would involve focusing on the GPU rather than the CPU, as the 235 is already a high-percentile processor. Users could consider a more powerful graphics card in the future, though the current GPU’s 24 GB of VRAM and 384-bit memory bus are already substantial. The CPU is not multiplier-unlocked, so overclocking is not an option; instead, users should rely on the boost clock of 5.00 GHz. The platform does not support ECC memory, which is a consideration for workstation builds requiring error correction.

Balance and Bottleneck

The balance between the CPU and GPU in this build is asymmetric. The CPU is in the 89th percentile of all CPUs, with an average benchmark score of 46,062. The GPU, based on its only available benchmark (3DMark Steel Nomad DX12), scores 16,504, placing it in the 59th percentile of all GPUs. The combined percentile for this pairing is 74th. This indicates that the CPU is significantly stronger relative to its peers than the GPU is relative to its peers.

For CPU-bound workloads, such as data compression, encryption, and integer math, the processor will not be a limiting factor. The PassMark multithread score of 37,816 and single-thread score of 4,516 are both strong, meaning that tasks like software compilation, spreadsheet calculations, and database operations will run smoothly. In contrast, the GPU’s 59th percentile ranking suggests that in graphics-intensive tasks, the graphics card may be the limiting component. The GPU’s 3DMark Steel Nomad score of 16,504 is nearly identical to the NVIDIA T400 (16,508, 0% delta) and slightly above the AMD Radeon PRO W7500 (16,415, 0.5% delta) and the NVIDIA RTX PRO 6000 Blackwell (16,408, 0.6% delta). These rivals are not high-end gaming cards; they are entry-level or workstation-oriented products, which suggests the GPU’s actual gaming throughput may be underwhelming relative to its 24 GB VRAM and 1.34 TB/s bandwidth.

In gaming scenarios, the CPU can feed frames at high rates due to its strong single-core performance, but the GPU may fail to keep up at higher resolutions or with demanding settings. The data shows a clear imbalance: the CPU is capable of handling high-end graphics cards, but the current GPU’s benchmark score does not match the CPU’s tier. For non-gaming workloads like 3D rendering, the GPU’s compute capabilities (104.8 TFLOPS FP32) are theoretically high, but the single benchmark score does not reflect this, making it difficult to ascertain real-world rendering performance.

FAQ

Q: What is the CPU’s performance percentile and what does it mean?

A: The Intel Core Ultra 5 235 is in the 89th percentile of all CPUs, with an average benchmark score of 46,062. This means it outperforms roughly 89% of processors in the database, indicating a strong desktop CPU for most tasks.

Q: How does the CPU compare to its nearest rivals?

A: The nearest rival is the Intel Core i9-13900HX, with an average score of 46,098, which is 0.1% higher. The AMD Ryzen AI 9 HX 375 scores 46,030 (0.1% lower), and the AMD EPYC 4364P and EPYC 7303 score 45,970 and 45,960, respectively, both 0.2% lower.

Q: What is the GPU’s benchmark score and percentile?

A: The GPU has a single benchmark score of 16,504 in 3DMark Steel Nomad DX12, placing it in the 59th percentile of all GPUs. Its average benchmark score is 16,504.

Q: How much VRAM does the GPU have and what type?

A: The GPU has 24 GB of GDDR7 memory on a 384-bit bus, with a bandwidth of 1.34 TB/s. The memory clock is 1750 MHz, with an effective speed of 28 Gbps.

Q: What is the power requirement for this build?

A: The CPU has a TDP of 65 W, while the GPU has a TDP of 575 W. The suggested PSU for the system is 950 W.

Q: Does the CPU support ECC memory?

A: No, the CPU does not support ECC memory. It supports dual-channel DDR5 memory only.

Q: Is the CPU overclockable?

A: No, the multiplier is locked (multiplierUnlocked is false). The boost clock is 5.00 GHz, which is the maximum achievable frequency.

Who Should Build It

This build targets users who need a high-performance CPU for productivity and are less concerned about top-tier gaming GPU performance. The CPU’s 89th percentile ranking makes it suitable for professionals in data processing, software development, and content creation where multi-core performance matters. The PassMark multithread score of 37,816 and Cinebench R23 multicore score of 14,769 indicate the CPU can handle video editing, 3D rendering, and compilation tasks efficiently. The single-core score of 2,085 in R23 ensures responsive performance in office applications and web-based workflows.

For gamers, this build is best suited for those playing at lower resolutions where the CPU is the primary driver, or for games that are not heavily GPU-dependent. The GPU’s 59th percentile, however, limits high-refresh-rate gaming at higher resolutions. The build is less ideal for gamers seeking maximum frame rates in AAA titles at 1440p or 4K, as the GPU’s benchmark score suggests it will be the bottleneck. Students and small business users will benefit from the CPU’s speed in multitasking and spreadsheet-heavy work, while the 24 GB VRAM on the GPU can handle large datasets in visualization tasks, despite the lower overall GPU percentile.

Usage Scenarios

High-refresh gaming: The CPU’s single-core performance (4,516 PassMark single-thread) is strong enough to drive high frame rates in esports titles, but the GPU’s 59th percentile ranking means it may not hit the highest FPS in demanding games. Estimated performance at 1080p would be moderate, with the GPU likely limiting frame rates in graphically intense scenes.

Streaming: The CPU’s 14 cores and strong multithread score (37,816 PassMark) can handle encoding tasks, but the GPU’s modest benchmark score suggests that hardware encoding may not be as efficient as higher-tier GPUs. Streamers would rely more on the CPU for encoding, which is feasible given its performance.

Video editing: The CPU’s Cinebench R23 multicore score of 14,769 indicates good performance in rendering timelines and exporting video. The GPU’s 104.8 TFLOPS FP32 and 24 GB VRAM can accelerate effects and color grading, but the low benchmark score raises questions about real-world GPU acceleration.

3D rendering: The CPU’s 14 threads and PassMark floating-point score of 117,951 are adequate for CPU-based rendering. The GPU’s 104.8 TFLOPS FP32 suggests high compute potential, but the single 3DMark score does not validate this, so rendering performance is uncertain.

Software development: The CPU excels in compilation tasks, with a PassMark integer math score of 87,948 and data compression score of 390,711. The GPU is less relevant here, making this build a strong choice for developers.

Student and office work: The CPU’s single-core performance and low 65 W TDP make it efficient for everyday tasks. The GPU’s high VRAM is unnecessary for office work, but the system runs smoothly for productivity suites.

GPU Analysis

The NVIDIA GeForce RTX 5090 D V2 is built on the Blackwell 2.0 architecture, using the GB202 chip fabricated on a 5 nm process by TSMC. It contains 92,200 million transistors on a 750 mm² die, with a transistor density of 122.9M per mm². The GPU has 21,760 shading units, 680 TMUs, and 176 ROPs. It features 170 RT cores and 680 tensor cores, supporting DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The base clock is 2017 MHz with a boost clock of 2407 MHz. Memory is 24 GB of GDDR7 on a 384-bit bus, delivering a bandwidth of 1.34 TB/s.

The GPU’s only benchmark score is 16,504 in 3DMark Steel Nomad DX12, placing it in the 59th percentile of all GPUs. Its nearest rival is the NVIDIA T400, which scores 16,508 (0% delta), followed by the AMD Radeon PRO W7500 at 16,415 (0.5% delta), the NVIDIA RTX PRO 6000 Blackwell at 16,408 (0.6% delta), and the AMD Radeon RX 5700 XT at 16,361 (0.9% delta). These are all significantly lower-tier cards than the RTX 5090 D V2’s name suggests, indicating the benchmark result is surprisingly low for a card with this specification. The pixel rate is 423.6 GPixel/s, and the texture rate is 1,636.8 GTexel/s. FP32 and FP16 performance are both 104.8 TFLOPS (1:1). The GPU has a TDP of 575 W, uses a 16-pin power connector, and requires a 950 W PSU. It connects via PCIe 5.0 x16 and outputs via 1x HDMI 2.1b and 3x DisplayPort 2.1b.

For rendering workloads, the theoretical compute power (104.8 TFLOPS) and 24 GB VRAM are substantial, but the benchmark score does not reflect this strength. The low percentile suggests that in practice, the GPU may underperform relative to its specs, possibly due to driver issues or the specific test conditions. Users should temper expectations for high-end gaming or rendering performance based on this data.

Build Overview

This is a desktop build (buildClass is desktop) pairing the Intel Core Ultra 5 235 with the NVIDIA GeForce RTX 5090 D V2. The CPU is a high-tier processor in the 89th percentile, while the GPU is in the 59th percentile. The combined percentile for the pairing is 74th. This places the overall system in the upper-midrange tier, driven primarily by the CPU’s strong performance. The GPU, despite its flagship naming and massive memory pool, pulls the combined score down due to its low benchmark result. The build is best described as a productivity-focused workstation with a capable but underperforming graphics component.

Benchmark Performance

The CPU’s average benchmark score is 46,062, placing it in the 89th percentile of all CPUs. Key scores include Cinebench R23 multicore at 14,769 and single-core at 2,085, and PassMark multithread at 37,816. The GPU’s average benchmark score is 16,504, placing it in the 59th percentile of all GPUs, based solely on the 3DMark Steel Nomad DX12 test. The combined picture shows a significant gap: the CPU is far above the median, while the GPU is only slightly above it. This means the system’s overall performance is heavily weighted toward CPU-bound tasks. In a balanced system, users would expect the GPU to be the stronger component for gaming, but here the opposite is true.

Gaming Performance

No measured FPS rows exist for this exact CPU+GPU combination in the FACT PACK. Therefore, all FPS discussions are estimated from the benchmark scores. The CPU’s strong single-core performance (2,085 in Cinebench R23, 4,516 PassMark single-thread) suggests it can deliver high frame rates in CPU-bound scenarios, such as esports games at 1080p. However, the GPU’s 3DMark Steel Nomad score of 16,504, which is comparable to the NVIDIA T400 and AMD Radeon RX 5700 XT, indicates that in GPU-bound scenarios—like AAA titles at 1440p or 4K with ultra settings—the frame rates will be modest. At 1080p, users might see playable frame rates in less demanding games, but at higher resolutions, the GPU will likely be the limiting factor, with estimates suggesting frame rates well below what the CPU could support. The 24 GB VRAM is more than sufficient for any game, but the raw rendering throughput appears low based on the percentile. These figures are estimates and should be treated as such.