SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 7 265F + NVIDIA GeForce RTX 5090 D

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
96%
VS
GPU
98%
PROCESSOR

Intel Core Ultra 7 265F

64,438 Benchmark Score
Top 4% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5090 D

77,712 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

# Intel Core Ultra 7 265F + NVIDIA GeForce RTX 5090 D

This desktop pairing combines Intel's 20-core Arrow Lake processor with NVIDIA's flagship Blackwell 2.0 GPU, placing it in the 93rd percentile of all CPU-GPU combinations. The CPU delivers a Cinebench R23 multi-core score of 41,980 and a single-core score of 5,926, while the GPU posts a 3DMark Steel Nomad DX12 score of 14,326 and a Passmark G3D score of 44,065. No measured FPS data exists for this exact combination; all frame-rate discussion below is estimated from benchmark scores rather than direct game testing.

CPU Analysis

The Intel Core Ultra 7 265F is a 20-core, 20-thread desktop processor built on Arrow Lake architecture and manufactured on a 3 nm TSMC process. It has no hyper-threading, so the thread count equals the core count, a design choice that prioritizes power efficiency over traditional multi-threading. The base clock is 2.40 GHz with a boost clock of 5.30 GHz, and the chip carries a 65 W TDP, making it a relatively modest power draw for a 20-core part.

Cache hierarchy consists of 192 KB L1 per core, 3 MB L2 per core, and 30 MB shared L3. Memory support is dual-channel DDR5 with a bandwidth of 102.4 GB/s, and ECC memory is not supported. PCIe connectivity includes Gen 5 with 20 CPU lanes. The chip fits Intel Socket 1851 and has no integrated graphics, requiring a discrete GPU.

Cinebench R15 multi-core scores 4,231, while single-core reaches 597. Scaling to R20, multi-core hits 17,631 and single-core 2,488. The R23 results of 41,980 multi-core and 5,926 single-core indicate strong sustained multi-threaded performance for a 65 W part. Passmark results reinforce this: multi-thread score is 49,410, integer math scores 138,078, floating-point math scores 173,855, and extended instructions score 39,235. Data compression scores 507,018, while encryption scores 39,468.

The CPU's average benchmark score is 64,438, placing it in the 93rd percentile of all CPUs. Compared to the nearest rivals, the 265F trails the Intel Core Ultra 7 265 by 0.3% (64,640 vs. 64,438) and the AMD EPYC 4464P by 0.6% (64,823 vs. 64,438), but leads the AMD EPYC 7343 by 0.4% (64,202 vs. 64,438) and the Intel Core i9-13900KS by 0.6% (64,051 vs. 64,438). These deltas are all within 1%, meaning the 265F sits in a tightly contested performance band.

For real workloads, the 20 cores without hyper-threading mean heavily threaded rendering and compilation tasks will see near-linear scaling across physical cores, but tasks that rely on SMT gains—like some database or virtualization workloads—will not get the extra thread headroom. The 5.30 GHz boost helps single-threaded responsiveness, evidenced by the 5,926 R23 single-core score, which positions it well for interactive applications. The 30 MB shared L3 is adequate for most productivity loads, though cache-sensitive workloads may prefer larger pools.

Benchmark Performance

The CPU's average benchmark score of 64,438 places it at the 93rd percentile among all CPUs, with its nearest rival being the Intel Core Ultra 7 265 at 64,640 (0.3% higher). On the GPU side, the RTX 5090 D achieves an average benchmark score of 77,712, sitting in the 92nd percentile of all GPUs. Its nearest rivals show a tight cluster: the AMD Radeon RX 6650M XT scores 76,904 (1.1% lower), the AMD Radeon RX 6850M XT scores 78,940 (1.6% higher), and NVIDIA Tesla P100 variants score 79,396 and 79,605 (2.1% and 2.4% higher, respectively).

The combined percentile for this pairing is 93, indicating that the CPU carries the pair's percentile ranking slightly above the GPU's standalone 92nd percentile. In 3DMark Steel Nomad DX12, the GPU scores 14,326, a strong result for a DX12 workload. Geekbench OpenCL scores 310,674 and Vulkan scores 376,915, showing the GPU scales well across compute APIs. Passmark G3D scores 44,065 with a G2D score of 1,487, while DirectX 9, 10, 11, and 12 Passmark scores are 434, 231, 371, and 219, respectively. Passmark GPU compute scores 28,396.

The combined picture is a CPU that is near the top of the desktop stack and a GPU that is similarly high, but the pair's overall 93rd percentile suggests the CPU slightly boosts the combination. The deltaPct values to nearest rivals—none exceeding 2.4%—indicate both components are in a performance tier where small benchmark variations translate to minimal real-world differences. The CPU's 0.6% lead over the i9-13900KS in average score is notable, as it shows the 265F can match a previous-generation flagship despite a 65 W TDP.

GPU Analysis

The NVIDIA GeForce RTX 5090 D is built on the GB202 chip using Blackwell 2.0 architecture on a 5 nm TSMC process. It packs 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9 million per mm². The GPU features 21,760 shading units, 680 texture mapping units, and 176 raster output units. Ray tracing hardware includes 170 RT cores, and tensor hardware comprises 680 tensor cores.

Memory is 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The memory clock runs at 1750 MHz with 28 Gbps effective speed. Base clock is 2017 MHz with a boost of 2407 MHz. Pixel rate is 423.6 GPixel/s, texture rate is 1,636.8 GTexel/s, and FP32 performance is 104.8 TFLOPS with FP16 at the same 104.8 TFLOPS (1:1 ratio).

The GPU's TDP is 575 W, requiring a 950 W suggested PSU and a single 16-pin power connector. It occupies a dual-slot form factor measuring 304 mm in length, 137 mm in height, and 48 mm in width. Display outputs include one HDMI 2.1b and three DisplayPort 2.1b connectors. API support covers DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Benchmark results indicate strong compute and raster performance. The 3DMark Steel Nomad DX12 score of 14,326 reflects a high-end DX12 workload, while Geekbench Vulkan at 376,915 outperforms OpenCL at 310,674. Passmark G3D at 44,065 is substantially higher than the G2D score of 1,487, which is typical for a discrete GPU where 2D acceleration is secondary. The DirectX 9 score of 434 outpaces DirectX 11's 371 and DirectX 12's 219, an artifact of Passmark's older workloads not scaling with modern architectures. GPU compute at 28,396 shows the tensor and shading hardware working together.

For rendering workloads, the 32 GB VRAM and 1.79 TB/s bandwidth provide ample headroom for large textures and complex scenes. The 170 RT cores handle ray-traced effects, while 680 tensor cores accelerate AI-based features like DLSS. The 104.8 TFLOPS FP32 throughput is substantial for simulation and scientific computing, though FP16 at the same rate suggests a design that does not boost half-precision throughput, which may limit some AI training workloads that rely on FP16 speedups.

Gaming Performance

No measured FPS data exists for this exact CPU-GPU combination. The FACT PACK contains no per-game frame rate rows, so all gaming performance figures below are estimates derived from benchmark scores rather than direct testing. The CPU's 93rd percentile and GPU's 92nd percentile suggest high frame rates at most resolutions, but specific FPS numbers cannot be confirmed.

Based on the GPU's 3DMark Steel Nomad score of 14,326 and Passmark G3D of 44,065, the RTX 5090 D should deliver very high frame rates at 1080p and 1440p in most titles, with 4K performance limited primarily by the CPU's ability to feed the GPU. The CPU's 5,926 Cinebench R23 single-core score indicates strong per-thread performance, which is critical for maintaining high FPS in CPU-bound scenarios. The 20 physical cores provide ample multi-threading for games that scale beyond 8 threads, though the lack of SMT may show in titles that expect logical thread counts.

At 1080p, the GPU is unlikely to be the bottleneck in most games, meaning the CPU's single-core score will dictate frame rates. The 5.30 GHz boost clock and 5,926 R23 single-core score place it among top desktop processors, so esports titles should run well above 144 FPS, though exact numbers are estimates. At 1440p, the GPU's 32 GB VRAM and 1.79 TB/s bandwidth handle high-resolution textures without memory pressure, and the 104.8 TFLOPS FP32 throughput supports high detail settings. At 4K, the GPU becomes the primary limiter in most titles, but the 575 W TDP and 21,760 shading units suggest it can sustain high settings, subject to per-game optimization.

Ray tracing performance relies on the 170 RT cores, which should handle RT effects at playable frame rates, especially with DLSS enabled via the 680 tensor cores. The 92nd GPU percentile indicates this is a top-tier part, but the exact FPS by game and resolution cannot be stated because no measured data exists.

Balance and Bottleneck

The CPU and GPU percentiles are closely matched—93rd for the CPU and 92nd for the GPU—so neither component dramatically outclasses the other. The combined percentile of 93 suggests a balanced pairing where both components contribute roughly equally to overall performance. However, workload type determines which component limits throughput.

In CPU-bound workloads like data compression (Passmark score 507,018), encryption (39,468), and integer math (138,078), the 265F's 20 cores and 5.30 GHz boost drive performance, and the GPU is largely idle. The CPU's 65 W TDP means it can sustain high clocks without thermal throttling, but the lack of SMT may cap performance in workloads that expect more threads than physical cores. The 0.3-0.6% deltaPct to nearest rivals shows the CPU is not a differentiator in either direction—it is right at the edge of its performance class.

In GPU-bound workloads like 3DMark Steel Nomad (14,326) and Passmark G3D (44,065), the RTX 5090 D dominates, and the CPU need only feed it data quickly enough. The 102.4 GB/s memory bandwidth of the CPU is a potential bottleneck for data transfer, but the PCIe Gen 5 x16 interface provides high bandwidth to the GPU. In gaming, the balance shifts with resolution: at 1080p, the CPU's single-core score determines frame rates; at 4K, the GPU's 21,760 shading units and 1.79 TB/s bandwidth become the limiting factor. The FPS scaling across resolutions cannot be quantified without measured data, but the benchmark scores imply a system that is CPU-limited at low resolutions and GPU-limited at high resolutions.

Who Should Build It

This pairing targets users who need both high-end CPU throughput and flagship GPU compute. Gamers at 1440p or 4K will benefit from the GPU's 32 GB VRAM and 104.8 TFLOPS FP32, which handle high-resolution textures and ray tracing, while the CPU's 93rd percentile ensures minimal bottlenecking at lower resolutions. Content creators working with video editing or 3D rendering will use the CPU's 20 cores for encoding and the GPU's tensor cores for AI-accelerated effects.

Software developers compiling large codebases will see strong multi-threaded performance from the 41,980 Cinebench R23 multi-core score, and the 30 MB L3 cache helps with repeated compilation passes. Students and small business users building workstations will benefit from the 65 W CPU TDP for lower cooling requirements, though the GPU's 575 W TDP necessitates robust power delivery. The 16-pin power connector and 950 W suggested PSU indicate this is not a casual build—it requires deliberate power and cooling planning. The lack of integrated graphics means a GPU is mandatory, but this pairing already includes a high-end one.

FAQ

Q: Does this CPU support hyper-threading?

A: No. The Intel Core Ultra 7 265F has 20 cores and 20 threads, meaning there is no SMT—each core handles one thread.

Q: What is the GPU's memory capacity and type?

A: The RTX 5090 D has 32 GB of GDDR7 memory on a 512-bit bus, providing 1.79 TB/s of bandwidth.

Q: How does the CPU compare to the Intel Core i9-13900KS?

A: The 265F has an average benchmark score of 64,438, which is 0.6% higher than the i9-13900KS's 64,051.

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

A: The CPU-GPU combination sits in the 93rd percentile of all pairings, matching the CPU's individual 93rd percentile and exceeding the GPU's 92nd percentile.

Q: Is ECC memory supported?

A: No, the CPU does not support ECC memory. It uses dual-channel DDR5 with 102.4 GB/s bandwidth.

Q: What power supply is suggested for this GPU?

A: The suggested PSU is 950 W, and the GPU uses a single 16-pin power connector. The GPU's TDP is 575 W, while the CPU's TDP is 65 W.

Q: Does the CPU have integrated graphics?

A: No, the integrated graphics field is listed as N/A, so a discrete GPU is required for display output.

Build Overview

This is a desktop build pairing the Intel Core Ultra 7 265F with the NVIDIA GeForce RTX 5090 D. The CPU is a 20-core Arrow Lake processor on Intel Socket 1851, and the GPU is a Blackwell 2.0 architecture card with 32 GB GDDR7. Both components are active production parts, released in January 2025—the CPU on January 6 and the GPU on January 29. The CPU's launch MSRP is $379, and the GPU's launch MSRP is 2,299 USD.

The combined percentile of 93 places this pairing among the top 7% of all CPU-GPU combinations. The CPU's average benchmark score of 64,438 is within 0.6% of its nearest rivals (the Core Ultra 7 265, EPYC 7343, EPYC 4464P, and i9-13900KS), while the GPU's average score of 77,712 is within 2.4% of its nearest rivals. This is a high-tier desktop configuration, though the GPU's 92nd percentile is slightly below the CPU's 93rd, indicating the CPU is the marginally stronger component relative to its peers.

Usage Scenarios

High-refresh gaming: At 1080p, the CPU's 5,926 Cinebench R23 single-core score and 5.30 GHz boost clock should sustain frame rates above 144 FPS in most titles, though exact numbers are estimates. The GPU's 32 GB VRAM prevents memory bottlenecks at high detail settings.

Streaming: The CPU's 20 physical cores handle encoding workloads, with a Passmark multi-thread score of 49,410 and data compression score of 507,018, while the GPU's 680 tensor cores can offload AI-based encoding. The 575 W GPU TDP means power draw is high during simultaneous gaming and streaming.

Video editing: The CPU's 41,980 Cinebench R23 multi-core score accelerates timeline rendering and export, while the GPU's 104.8 TFLOPS FP32 and 1.79 TB/s bandwidth handle effects and color grading. The 32 GB VRAM supports large 4K or 8K projects without spilling to system memory.

3D rendering: The GPU's 170 RT cores and 21,760 shading units drive ray-traced renders, and the 104.8 TFLOPS FP16 performance accelerates denoising. The CPU's 20 cores provide complementary CPU-based rendering, with a Passmark floating-point math score of 173,855.

Software development: The CPU's 20 cores compile large codebases efficiently, with integer math at 138,078 and extended instructions at 39,235. The 30 MB L3 cache reduces memory latency for frequently accessed code, though the lack of SMT may slow builds that spawn more threads than physical cores.

Student and office work: The 65 W CPU TDP allows for a quieter, cooler system, and the 5,926 single-core R23 score ensures responsive daily use. The GPU is overkill for office tasks, but the combined percentile of 93 means the system will handle any productivity software without slowdown.

Upgrade Path and Platform

The CPU uses Intel Socket 1851, which is the LGA 1851 platform for Core Ultra Series 2. Memory support is dual-channel DDR5 with no ECC option. PCIe connectivity includes Gen 5 with 20 CPU lanes, and the GPU uses a PCIe 5.0 x16 interface, so the platform fully supports the RTX 5090 D's bus bandwidth.

The CPU's 65 W TDP and the GPU's 575 W TDP combine for a total of 640 W of component power draw, leaving headroom within the 950 W suggested PSU for drives, cooling, and motherboard components. The 1x 16-pin GPU power connector is the sole power input, simplifying cable management. The dual-slot GPU design fits most mid-tower cases, with a length of 304 mm and height of 137 mm.

A sensible next upgrade would be a higher-core-count Arrow Lake CPU if multi-threaded workloads expand, as the socket supports the same generation. The 32 GB GPU VRAM is unlikely to need replacement for several years, and the 92nd GPU percentile means it is near the top of the market. The CPU's locked multiplier (unlocked is false) limits overclocking, so performance gains would come from a CPU upgrade rather than clock tuning. The platform's 20 PCIe Gen 5 lanes allow for fast NVMe storage, and the 102.4 GB/s memory bandwidth is sufficient for current DDR5 modules, though future higher-speed kits may improve bandwidth-sensitive workloads.