SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 5 235T + Intel Arc B570

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
92%
VS
GPU
91%
PROCESSOR

Intel Core Ultra 5 235T

38,561 Benchmark Score
Top 8% Market Ranking
View Full Specs →
GRAPHICS CARD

Intel Arc B570

20,556 Benchmark Score
Top 9% 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 235T and Intel Arc B570 combination represents a balanced mid-range desktop pairing, with the CPU performing at the 86th percentile among all processors and the GPU at the 65th percentile among all graphics cards. This system is built around Intel’s latest Arrow Lake architecture on the LGA 1851 socket, paired with the Battlemage-generation GPU, and the benchmark data indicates a capable 1440p gaming and productivity machine. The combined percentile ranking of 76 places this build firmly in the upper-middle tier of desktop systems.

GPU Analysis

The Intel Arc B570 is built on the Xe2-HPG architecture, codenamed Battlemage, and manufactured on a 5 nm process at TSMC. The GPU die contains 19,600 million transistors across a 272 mm² die, giving it a transistor density of 72.1 million transistors per mm². The card features 2,304 shading units, 144 texture mapping units, and 80 raster operation units, alongside 18 dedicated ray tracing cores. Notably, the tensor core count is not specified in the data, but the architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, indicating full modern API support.

Memory configuration is a critical strength for this GPU. The Arc B570 comes equipped with 10 GB of GDDR6 memory on a 160-bit bus, running at an effective 19 Gbps. This yields a memory bandwidth of 380.0 GB/s, which is substantial for the card’s performance class and helps sustain high-resolution textures and compute workloads. The base and boost clocks are both locked at 2500 MHz, which is unusual but simplifies power delivery expectations. The pixel rate is 200.0 GPixel/s, and the texture rate is 360.0 GTexel/s, providing 11.52 TFLOPS of FP32 compute and 23.04 TFLOPS of FP16 compute with a 2:1 ratio.

In benchmark terms, the Arc B570 scores 2649 in 3DMark Steel Nomad DX12, which is a modern, demanding test. Its Geekbench scores are 83514 in OpenCL and 96844 in Vulkan, indicating strong compute and graphics API performance respectively. PassMark results show a G3D score of 14195 and a GPU compute score of 7281. The GPU’s percentile ranking is 65th among all GPUs, placing it above the median but not in the enthusiast tier. Its nearest rival is the Intel Arc A750, which scores 20582 on average, a delta of -0.1%, meaning the B570 is essentially tied with its predecessor in average benchmark score. It also sits within 0.4% of the NVIDIA GeForce RTX 3070 Mobile (20534) and 0.5% of the AMD Radeon R9 M390X (20662), though these are mobile or older parts. The ray tracing hardware is present with 18 RT cores, and while no specific RT benchmark scores are listed, the DirectX 12 Ultimate support means the hardware is ready for ray-traced titles.

Benchmark Performance

The CPU’s average benchmark score is 38561, placing it in the 86th percentile of all CPUs. This is a strong showing, and the nearest rivals confirm its positioning. The Intel Core i5-14500 scores 38531 on average, a delta of only 0.1%, meaning the 235T is statistically identical in overall performance. The Intel Xeon w3-2525 scores 38392 (0.4% delta), the Intel Core 9 270H scores 38335 (0.6% delta), and the Intel Core Ultra 9 285H scores 38312 (0.7% delta). This puts the 235T in the same performance bracket as some higher-tier workstation and mobile chips, despite being a mainstream desktop part.

The GPU’s average benchmark score is 20556, placing it in the 65th percentile. The nearest rival, the Intel Arc A750, scores 20582, a delta of -0.1%, showing the B570 is a marginal improvement over its predecessor. The NVIDIA GeForce RTX 3070 Mobile is within 0.1% (20534), and the AMD Radeon R9 M390X is within 0.5% (20662). The combined percentile for this CPU-GPU pair is 76, indicating that the system as a whole outperforms three-quarters of all tested desktop configurations.

The combined picture is one of consistency: the CPU leads its class while the GPU is competitive but not dominant. This means the system will not be badly bottlenecked by either component in most workloads, but the CPU has more headroom relative to its peers than the GPU does. In CPU-bound tasks like data compression or encryption, the 235T will shine; in GPU-bound scenarios like high-resolution gaming, the B570 will be the limiting factor.

CPU Analysis

The Intel Core Ultra 5 235T is a 14-core, 14-thread processor based on the Arrow Lake architecture, manufactured on a 3 nm process at TSMC. The die contains 17,800 million transistors on a 243 mm² die. The base clock is 2.20 GHz with a boost clock of 5.00 GHz, and the TDP is a modest 65 W. The cache hierarchy includes 192 KB of L1 cache per core, 3 MB of L2 cache per core, and 24 MB of shared L3 cache. Memory support is DDR5 via a dual-channel bus, providing 102.4 GB/s of bandwidth. ECC memory is not supported, and the CPU provides 20 PCIe Gen 5 lanes.

Benchmark results show a well-rounded performance profile. In Cinebench, the CPU scores 2644 in R15 multicore and 373 in single-core; 11017 in R20 multicore and 1555 in single-core; and 26232 in R23 multicore and 3703 in single-core. These scores indicate strong multi-threaded performance for a 65 W part, likely due to the efficient 3 nm process and high boost clock. PassMark results reinforce this: a multithread score of 30918, single-thread score of 4339, and physics score of 2157. The data compression score of 295100 is particularly high, suggesting excellent throughput for archival or database workloads, while data encryption at 23457 and extended instructions at 23212 show robust security and vector processing capabilities. Integer math scores 84244 and floating point math scores 106546, indicating balanced arithmetic performance.

The 86th percentile ranking means the 235T outperforms the vast majority of CPUs on the market, including many higher-TDP parts. The fact that it matches the Core i5-14500 (0.1% delta) and edges out the Xeon w3-2525 (0.4% delta) is telling: this is a desktop chip that competes with workstation silicon in raw throughput. The 14 threads (not 28) mean it relies on high IPC and clock speeds rather than hyper-threading, which is a design choice that favors power efficiency. For real workloads, this translates to snappy single-threaded performance in applications like web browsing or office suites, and strong multi-threaded performance in video encoding or 3D rendering, as evidenced by the Cinebench R23 multicore score of 26232.

Gaming Performance

No measured FPS data exists for this exact CPU-GPU combination, and the FACT PACK contains no empirical frame rate rows. Therefore, all gaming performance figures discussed here are estimates derived from the benchmark scores and should be treated as approximations rather than tested results. The dataIsMeasured field is false, meaning the following expectations are qualitative and based on the GPU’s 65th percentile ranking and CPU’s 86th percentile ranking.

Based on the Arc B570’s 3DMark Steel Nomad score of 2649 and its PassMark G3D score of 14195, this GPU is positioned to handle 1080p gaming at high settings and 1440p gaming at medium-to-high settings in most modern titles. The 10 GB of VRAM is sufficient for 1440p textures, and the 380.0 GB/s bandwidth reduces stuttering in texture-heavy scenes. The CPU’s strong single-thread score of 4339 in PassMark suggests it will not bottleneck the GPU at lower resolutions, where frame rates are CPU-limited. For esports titles like competitive shooters, the 5.00 GHz boost clock should drive very high frame rates, though the exact numbers are unmeasured. For AAA single-player games, expect playable frame rates at 1440p with some settings adjustments needed for the most demanding releases. The 18 RT cores mean ray tracing is possible but will likely require upscaling or reduced resolutions to maintain smooth performance, as the raw FP32 compute of 11.52 TFLOPS is modest for heavy RT workloads.

Usage Scenarios

High-Refresh Gaming: The CPU’s 5.00 GHz boost clock and 86th percentile ranking provide ample headroom for high frame rates in CPU-bound scenarios. The GPU’s 65th percentile and 10 GB VRAM, however, will limit the system to 1080p or 1440p at high refresh rates, with estimated frame rates in the triple digits for lighter titles but more modest numbers for AAA games. This is a solid 144Hz 1080p system, but not a 240Hz 4K machine.

Streaming: The 14 cores and 14 threads, combined with a strong PassMark multithread score of 30918, allow for simultaneous gameplay and encoding without major frame drops. The GPU’s Xe2-HPG architecture supports modern encoding features, though no specific encoder benchmarks are listed. The system can handle x264 encoding at medium presets while gaming, given the CPU’s Cinebench R23 multicore score of 26232.

Video Editing: The CPU’s high floating-point math score of 106546 and data compression score of 295100 indicate strong performance in rendering and export tasks. The GPU’s 23.04 TFLOPS FP16 compute accelerates effects and previews. Expect smooth 4K timeline editing in software like Premiere Pro, with export times that are competitive with much more expensive workstation parts, given the CPU’s parity with the Xeon w3-2525.

3D Rendering: The Cinebench scores (26232 in R23 multicore) are the key metric here, and they show the CPU is capable of handling complex scenes. The GPU’s 11.52 TFLOPS FP32 compute and 18 RT cores provide hardware acceleration for ray-traced renders in Blender or similar tools. The 10 GB VRAM may be limiting for very large scenes, but the 380.0 GB/s bandwidth helps with texture streaming.

Software Development: The PassMark data encryption score of 23457 and extended instructions score of 23212 indicate strong performance in cryptographic operations and SIMD-heavy code. The single-thread score of 4339 ensures fast compilation of single files, while the multithread score of 30918 accelerates full builds. The 24 MB L3 cache reduces latency in large codebases.

Student and Office Work: The 65 W TDP means low power draw and easy cooling, making this a quiet system for dorms or offices. The CPU’s single-thread performance makes spreadsheet and word processing tasks feel instant, and the GPU is overkill for 2D workloads but ready for occasional light 3D or video tasks. The system is efficient enough for all-day operation without excessive heat.

Who Should Build It

This build targets gamers at 1080p and 1440p who want a balance between CPU and GPU performance without stepping into high-end pricing territory. The CPU’s 86th percentile ranking makes it a strong choice for content creators who need heavy multi-threaded performance for rendering or encoding, as it matches the Xeon w3-2525 (0.4% delta) at a fraction of the platform cost. Developers will appreciate the fast compilation times and encryption throughput, while students and office workers benefit from the low TDP and quiet operation. Small business workstations that run database or virtualization workloads will find the data compression score of 295100 and multithread performance of 30918 highly appealing. The GPU is suitable for users who want modern features like ray tracing and DirectX 12 Ultimate support without paying a premium, and the 10 GB VRAM is future-proof for 1440p textures. This is not a build for 4K gaming or heavy AI workloads, as the GPU’s 65th percentile ranking and lack of specified tensor cores limit those use cases.

Upgrade Path and Platform

The platform is based on the Intel Socket 1851, which is designed for the Core Ultra Series 2 processors. The CPU supports dual-channel DDR5 memory with a maximum bandwidth of 102.4 GB/s, and ECC is not supported. The CPU provides 20 PCIe Gen 5 lanes, while the GPU uses a PCIe 4.0 x8 interface. The suggested PSU for the GPU is 450 W, and the GPU has a TDP of 150 W with a single 8-pin power connector. The CPU’s TDP is 65 W, so the total system draw is manageable for a mid-range power supply.

The upgrade path is straightforward: the socket supports future Arrow Lake processors, so a user could move to a higher-tier Core Ultra 5 or Core Ultra 7 chip without changing the motherboard. For the GPU, the PCIe 4.0 x8 interface is compatible with all modern cards, though a faster GPU would require a more powerful PSU (the B570 suggests 450 W, but a higher-tier card would need more). The dual-slot GPU measures 272 mm in length and 115 mm in height, so case compatibility is standard. A sensible next upgrade would be a higher-core-count CPU on the same socket for more multithreaded throughput, or a GPU with more VRAM and compute for 4K gaming, provided the PSU is upgraded accordingly. The memory bandwidth of 102.4 GB/s is a limiting factor for CPU-intensive workloads, so moving to faster DDR5 modules would be a logical step, though the motherboard must support such speeds.

FAQ

Q: What is the CPU’s performance percentile ranking?

A: The Intel Core Ultra 5 235T ranks in the 86th percentile of all CPUs, with an average benchmark score of 38561.

Q: How does the Arc B570 compare to its nearest rival?

A: The Arc B570 scores 20556 on average, which is a 0.1% delta from the Intel Arc A750 (20582), meaning they are statistically identical in performance.

Q: What is the GPU’s memory configuration?

A: The Arc B570 has 10 GB of GDDR6 memory on a 160-bit bus, running at 2375 MHz (19 Gbps effective), providing 380.0 GB/s of bandwidth.

Q: Does the CPU support ECC memory?

A: No, the Intel Core Ultra 5 235T does not support ECC memory.

Q: What is the TDP of the CPU and GPU?

A: The CPU has a TDP of 65 W, and the GPU has a TDP of 150 W, with a suggested PSU rating of 450 W.

Q: What DirectX version does the GPU support?

A: The Arc B570 supports DirectX 12 Ultimate (12_2), along with OpenGL 4.6 and Vulkan 1.4.

Q: How much L3 cache does the CPU have?

A: The CPU has 24 MB of shared L3 cache, with 192 KB of L1 and 3 MB of L2 cache per core.

Balance and Bottleneck

The data shows a system where the CPU is significantly stronger relative to its peers than the GPU. The CPU’s 86th percentile ranking versus the GPU’s 65th percentile means that in heavily multi-threaded workloads like 3D rendering, video encoding, or data compression, the CPU will be the dominant performer, and the GPU may not be able to keep up with the CPU’s output. For example, the CPU’s Cinebench R23 multicore score of 26232 is exceptional for a 65 W part, but the GPU’s 3DMark Steel Nomad score of 2649 is merely average, indicating that render tasks using both will be GPU-limited.

Conversely, in gaming scenarios, the bottleneck shifts. At 1080p, the CPU’s strong single-thread performance (4339 in PassMark) can push frame rates higher than the GPU can render, making the GPU the limiting factor. At 1440p, the GPU becomes even more of a constraint, as its 10 GB VRAM and 11.52 TFLOPS FP32 compute are modest for that resolution. The combined percentile of 76 suggests the system is well-balanced overall, but the specific workload determines which component holds the system back. For office and productivity tasks, the CPU will rarely be stressed, and the GPU is idle. For gaming, the GPU is the clear bottleneck. For content creation, the CPU is the workhorse, and the GPU accelerates specific effects but does not define overall throughput. The upgrade path is clear: if gaming is the priority, the GPU should be replaced first; if productivity is the focus, the CPU can be upgraded to a higher-tier Arrow Lake part on the same socket, though the current chip already matches the Xeon w3-2525.