SYSTEM ANALYZER

Rate My PC: Intel Core i9-13900HX + Intel Arc B390

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

85 / 100
HIGH-END

Power Build

Top 15% of systems. Excellent for 1440p Ultra or 4K High gaming.

1440p Ultra4K High

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
93%
VS
GPU
77%
PROCESSOR

Intel Core i9-13900HX

46,098 Benchmark Score
Top 7% Market Ranking
View Full Specs →
GRAPHICS CARD

Intel Arc B390

1,482 Benchmark Score
Top 23% 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 i9-13900HX is a 24-core, 32-thread mobile processor built on Intel’s Raptor Lake architecture, specifically the Raptor Lake-HX variant. Fabricated on Intel’s 10 nm process with a die size of 257 mm², this chip operates with a base clock of 2.20 GHz and a boost clock of 5.40 GHz. The core configuration is split with a hybrid design typical of the generation, combining performance and efficiency cores to deliver a maximum thread count of 32. The processor’s cache hierarchy includes 80 KB of L1 per core, 2 MB of L2 per core, and a shared 36 MB L3 cache, which is substantial for a mobile part and helps feed the high-core-count workload. Memory support includes both DDR4 and DDR5 in a dual-channel configuration, with ECC support available, and the CPU provides PCIe Gen 5 connectivity with 20 lanes from the CPU itself. The 55 W TDP is notably higher than typical mobile processors, indicating a design meant for performance-focused laptops.

Benchmark results place this CPU in the 89th percentile among all CPUs, which signals that it outperforms the vast majority of processors on the market. The average benchmark score is 46098, and the nearest rivals show a tightly clustered competition: the Intel Core Ultra 5 235 scores 46062 (0.1% ahead), the AMD Ryzen AI 9 HX 375 scores 46030 (0.1% ahead), the AMD Ryzen AI 5 440G scores 46187 (0.2% ahead), and the AMD EPYC 4364P scores 45970 (0.3% behind). This places the i9-13900HX in a virtual tie with these parts, meaning the performance difference is negligible in aggregate, though individual workload characteristics may vary. The single-thread score in 3DMark is 1102, while the max-thread score reaches 11738, showing strong scaling from 2 threads (2143) to 4 threads (4012) to 8 threads (6857) and up to the full 32-thread count. Cinebench scores reinforce this: R23 multicore hits 27900, while R23 single-core is 2056, indicating that the chip is nearly 13.5 times faster in multithreaded rendering than in single-threaded tasks, a ratio typical of high-core-count parts. Passmark results show strong integer math (156175), floating-point math (110470), and data compression (531224) scores, with a multithread score of 43062 and a single-thread score of 4081. These numbers suggest that the CPU excels in parallel workloads like video encoding, 3D rendering, and compilation, while still maintaining competitive single-core performance for everyday tasks and gaming. The 3DMark 16-thread score of 8929 versus the max-thread score of 11738 indicates that the additional threads beyond 16 provide a meaningful boost, roughly 31% more performance, which is beneficial for heavily threaded applications but less critical for gaming where 8 cores are often sufficient.

The Intel Arc B390 GPU is a mobile integrated graphics solution based on the Xe3-LPG architecture, part of the Panther Lake generation, and fabricated on Intel’s 3 nm process. It features 1536 shading units, 48 texture mapping units, and 24 raster operation units, with 12 ray tracing cores. The base clock is 300 MHz, boosting to 2500 MHz, and the memory is system shared, meaning the VRAM size, type, and bus width are all dependent on the system’s main memory configuration, with bandwidth listed as system dependent. The GPU’s pixel rate is 60.00 GPixel/s, and the texture rate is 120.0 GTexel/s, with FP32 performance at 7.680 TFLOPS and FP16 at 15.36 TFLOPS (2:1). It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, which covers modern gaming APIs. The TDP is 80 W, which for an integrated GPU is significant, and the slot width is IGP, meaning it is not a discrete card. The only benchmark available is 3DMark Steel Nomad DX12, with a score of 1482, placing the GPU in the 9th percentile among all GPUs. This is a very low ranking, with nearest rivals including the NVIDIA GeForce GT 520MX (1463, 1.3% ahead), the NVIDIA GeForce 800M (1460, 1.5% ahead), the NVIDIA GeForce GT 625 OEM (1446, 2.5% ahead), and the NVIDIA GeForce GT 710 (1443, 2.7% ahead). These comparisons place the Arc B390 in the entry-level segment, far below any modern discrete gaming GPU, which has major implications for the overall build’s gaming capability. The combined percentile for the CPU and GPU pairing is 49, placing it in the middle of the pack for all builds, but this is heavily skewed by the strong CPU and weak GPU.

Usage Scenarios

High-refresh gaming: The CPU’s strong single-thread performance, with a 3DMark single-thread score of 1102 and a Passmark single-thread score of 4081, is more than sufficient to drive high-refresh-rate gaming in terms of physics and game logic. However, the GPU’s 9th percentile ranking and 1482 Steel Nomad score indicate that frame rates will be severely limited at any resolution above low settings. The data suggests that this pairing cannot sustain high refresh rates in modern titles, as the GPU is a bottleneck that will cap FPS well below what the CPU can handle.

Streaming: For streaming, the CPU is a strong asset. The 24 cores and 32 threads, combined with a Cinebench R23 multicore score of 27900, provide ample headroom for encoding video while gaming. The Passmark data compression score of 531224 and integer math score of 156175 indicate that x264 encoding or software encoding will be effective without dropping frames. The GPU, however, offers no hardware encoding advantage beyond basic integrated capabilities, so streamers will rely on the CPU, which is well-suited for the task.

Video editing: Video editing software often leverages both CPU and GPU acceleration. The CPU’s multicore performance is excellent, with a Cinebench R20 multicore score of 14836 and a Passmark multithread score of 43062, which will speed up rendering and export times in applications like Premiere Pro or DaVinci Resolve. The GPU’s low FP32 performance of 7.680 TFLOPS and 9th percentile ranking mean that GPU-accelerated effects and timeline scrubbing will be sluggish, and the system will rely heavily on CPU rendering, which is fast but not optimal for real-time previews.

3D rendering: This workload is where the CPU shines. The Cinebench R15 multicore score of 4494.5 and R23 multicore score of 27900 indicate that the i9-13900HX can handle complex scenes in Blender or Maya with relative ease, especially when compared to the 0.1-0.3% delta from rivals like the AMD Ryzen AI 9 HX 375. The GPU’s 12 ray tracing cores are present, but with only 7.680 TFLOPS FP32 performance, GPU rendering in engines like Blender Cycles will be slow, making CPU rendering the preferred path, which is a viable strategy given the processor’s throughput.

Software development: Compilation is a parallel task, and the CPU’s 32 threads, with a Passmark find prime numbers score of 190 and floating-point math of 110470, suggest strong performance in build times for large codebases. The 36 MB L3 cache helps with frequently accessed data, and the dual-channel DDR5 support provides adequate memory bandwidth for compilers. The GPU is irrelevant for this use case, so the high CPU percentile of 89 makes this a solid choice for developers who need to compile frequently.

Student and office work: For productivity tasks like spreadsheets, document editing, and web browsing, the CPU’s single-thread performance is more than adequate, with a Passmark single-thread score of 4081. The integrated GPU is sufficient for 2D applications and video playback, though the 9th percentile ranking means any 3D or graphical workload will be poor. The 55 W TDP and mobile class mean this is a laptop, so portability is a factor, but the performance is overkill for basic office tasks, making it a niche choice for students who also need heavy compute.

Benchmark Performance

The CPU benchmark suite shows a processor that is firmly in the high-end mobile segment. The 3DMark scores scale from 1102 (single-thread) to 11738 (max threads), with intermediate scores of 2143 (2 threads), 4012 (4 threads), 6857 (8 threads), and 8929 (16 threads). This scaling demonstrates that the chip gains 31% performance when moving from 16 to 32 threads, which is a tangible benefit for multithreaded applications. Cinebench R23 scores of 27900 (multicore) and 2056 (single-core) put the CPU in a class where it competes with desktop parts from a few generations ago, and the 89th percentile ranking confirms its position above nearly all other CPUs. The Passmark results are equally impressive: multithread at 43062, single-thread at 4081, integer math at 156175, floating-point math at 110470, data encryption at 32130, extended instructions at 30550, and random string sorting at 59199. These scores indicate balanced performance across different instruction types, with the CPU showing particular strength in integer and floating-point operations that are common in scientific computing and financial modeling.

The GPU benchmark is sparse, with only a single 3DMark Steel Nomad DX12 score of 1482. This places the Arc B390 in the 9th percentile, meaning that 91% of GPUs perform better. The nearest rivals are all older NVIDIA entry-level parts, with the GT 520MX (1463) being 1.3% slower, the GeForce 800M (1460) being 1.5% slower, the GT 625 OEM (1446) being 2.5% slower, and the GT 710 (1443) being 2.7% slower. This shows that the Arc B390 is competitive with decade-old discrete GPUs, but it is not in the same league as any modern integrated GPU like those found in AMD’s RDNA 3 or Intel’s own Arc discrete line. The combined picture is a CPU that is in the top 11% of all processors paired with a GPU that is in the bottom 9% of all graphics processors. The combined percentile of 49 reflects this mismatch, meaning the build’s overall performance is average, but the individual components are at opposite extremes.

Who Should Build It

The target user for this CPU+GPU pairing is a professional or power user who needs extreme CPU compute in a laptop form factor but does not require discrete graphics performance. The 89th percentile CPU means that developers working on large codebases will see significant compilation speedups, and content creators doing CPU-based rendering or video encoding will benefit from the 32 threads. Specific industries include software engineering, where the Passmark multithread score of 43062 and integer math of 156175 will reduce build times; data science, where the floating-point math of 110470 aids in numerical simulations; and financial analysis, where the data encryption score of 32130 and compression score of 531224 are relevant for data processing. Gamers at 1080p with low settings might find the system usable for esports titles, but the GPU’s 9th percentile ranking means the experience will be poor for AAA games. Students in engineering or computer science programs who need to run simulations or compile code will find the CPU powerful, but they will need to accept that any GPU-accelerated coursework will be slow. Small business workstations that rely on CPU-intensive applications like accounting software or database management will perform well, but the system is overkill for general office tasks, where a lower-tier CPU would suffice, making this a specialized tool rather than a general-purpose machine.

FAQ

Q: What is the CPU’s performance percentile compared to all CPUs?

A: The Intel Core i9-13900HX is in the 89th percentile among all CPUs, with an average benchmark score of 46098.

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

A: The CPU is within 0.3% of its nearest rivals. The AMD Ryzen AI 5 440G is 0.2% ahead, the Intel Core Ultra 5 235 and AMD Ryzen AI 9 HX 375 are each 0.1% ahead, and the AMD EPYC 4364P is 0.3% behind.

Q: What is the GPU’s performance percentile, and what does that mean?

A: The Intel Arc B390 is in the 9th percentile among all GPUs, with a 3DMark Steel Nomad score of 1482, indicating it is outperformed by over 90% of graphics processors.

Q: What kind of memory does the GPU use?

A: The GPU uses system shared memory, meaning the VRAM size, type, and bus width are all dependent on the system’s main memory, and bandwidth is system dependent.

Q: What is the CPU’s boost clock and core count?

A: The CPU has 24 cores and 32 threads, with a boost clock of 5.40 GHz and a base clock of 2.20 GHz.

Q: Does the CPU support ECC memory?

A: Yes, the CPU supports ECC memory, and it supports both DDR4 and DDR5 in a dual-channel configuration.

Q: What is the CPU’s launch MSRP?

A: The launch MSRP is $668.

Gaming Performance

There are no measured FPS rows for this exact CPU+GPU combination, so all frame rate discussions are estimated from the benchmark scores. The CPU’s single-thread performance is strong, with a 3DMark single-thread score of 1102 and a Passmark single-thread score of 4081, which would allow it to drive high frame rates in CPU-bound scenarios. However, the GPU’s 3DMark Steel Nomad score of 1482 and 9th percentile ranking are the limiting factor. For esports titles like Counter-Strike 2 or Valorant, the system might achieve playable frame rates at 1080p with low settings, as these games are CPU-bound and can run on modest GPUs. For AAA games at 1080p, the GPU is expected to deliver very low frame rates, likely below 30 FPS on medium settings, and at 1440p or 4K, the performance would be unplayable. The GPU’s FP32 performance of 7.680 TFLOPS is a fraction of what discrete gaming GPUs offer, and the 12 ray tracing cores are insufficient for modern RT workloads. The pixel rate of 60.00 GPixel/s and texture rate of 120.0 GTexel/s are also low, further limiting resolution scaling. In summary, the gaming experience is dominated by the GPU, and the CPU’s potential is wasted in this context, as frame rates will be GPU-limited in nearly every scenario.

Balance and Bottleneck

The performance data reveals a severe imbalance between the CPU and GPU. The CPU is in the 89th percentile, while the GPU is in the 9th percentile, creating a massive bottleneck in graphics-intensive workloads. In gaming, the GPU is the limiting factor, as the 3DMark Steel Nomad score of 1482 is far below what is needed for modern titles, and the CPU’s single-thread performance is more than adequate to feed any frame rate the GPU can produce. The FPS scaling from the CPU’s perspective shows that it is not the constraint; the 3DMark 8-thread score of 6857 and max-thread score of 11738 indicate that even at lower thread counts, the CPU has headroom. In productivity tasks, the CPU is the dominant component, and the GPU is irrelevant, so the bottleneck shifts to the CPU, which is a strength. For video editing, the bottleneck depends on the task: CPU rendering will be fast, but GPU-accelerated effects will be slow, making the GPU a bottleneck in hybrid workflows. The combined percentile of 49 reflects this imbalance, showing that the build is average overall, but this is a misleading statistic because the CPU is exceptional and the GPU is below average. For any workload that relies on the GPU, the system will underperform, while CPU-only workloads will excel. The TDPs also indicate a power imbalance: the CPU has a 55 W TDP, and the GPU has an 80 W TDP, both of which are relatively high for a laptop, but the GPU’s power is not translating into performance, likely due to the integrated design and system-shared memory.

Build Overview

This build pairs the Intel Core i9-13900HX, a 24-core mobile processor, with the Intel Arc B390, an integrated GPU, in a laptop class configuration. The CPU is a high-end part, ranking in the 89th percentile, while the GPU is an entry-level integrated solution, ranking in the 9th percentile. The combined percentile is 49, placing the overall build in the middle of the database. This is a laptop, so the components are soldered or integrated, meaning the user cannot swap the GPU or CPU. The system is best described as a compute-focused laptop, where the CPU is the star and the GPU is a secondary consideration. The i9-13900HX is a top-tier mobile CPU, and the Arc B390 is an integrated GPU that is comparable to older discrete entry-level GPUs, as shown by its rivals. This pairing creates a system that is excellent for CPU-intensive tasks like rendering, compilation, and data analysis, but poor for gaming or GPU-accelerated workloads. The build’s overall tier is average, but the CPU tier is high, and the GPU tier is low, so the user must be selective about the workloads they run on this machine.

GPU Analysis

The Intel Arc B390 is built on the Xe3-LPG architecture, part of the Panther Lake generation, and is fabricated on Intel’s 3 nm process. It has 1536 shading units, 48 TMUs, and 24 ROPs, with 12 ray tracing cores. The clocks are set at a base of 300 MHz and a boost of 2500 MHz. The memory is system shared, so the VRAM size, type, and bus width are all dependent on the system’s main memory, and the bandwidth is system dependent. This is a critical limitation, as integrated GPUs rely on system memory bandwidth, which is typically lower than dedicated VRAM. The GPU’s pixel rate is 60.00 GPixel/s, and the texture rate is 120.0 GTexel/s, with FP32 performance at 7.680 TFLOPS and FP16 at 15.36 TFLOPS (2:1). The 3DMark Steel Nomad DX12 score is 1482, placing the GPU in the 9th percentile, which is near the bottom of the performance range. The nearest rivals are all older NVIDIA parts, with the GT 520MX being 1.3% faster, the GeForce 800M being 1.5% faster, the GT 625 OEM being 2.5% faster, and the GT 710 being 2.7% faster. For rendering, the GPU’s FP32 performance of 7.680 TFLOPS is insufficient for modern GPU-accelerated rendering, and the 12 ray tracing cores are too few for real-time RT workloads. The API support is modern, including DirectX 12 Ultimate and Vulkan 1.4, but the hardware is too weak to take advantage of these features in a meaningful way. The TDP of 80 W is high for an integrated GPU, indicating that it consumes power but does not deliver proportional performance, likely due to the shared memory bottleneck and the limitations of the integrated design.

Upgrade Path and Platform

The CPU is socketed on Intel BGA 1964, which is a mobile socket, meaning the CPU is soldered to the motherboard and cannot be upgraded. The GPU is also integrated, so there is no upgrade path for graphics either. The memory support is DDR4 and DDR5 in a dual-channel configuration, and the user can potentially upgrade the RAM if the laptop allows it, but the maximum capacity is not specified. The CPU provides PCIe Gen 5 with 20 lanes from the CPU, but the GPU uses an IGP bus interface, so the PCIe lanes are not used for graphics. The CPU’s TDP is 55 W, and the GPU’s TDP is 80 W, so the total power draw is around 135 W, which requires a laptop power adapter that can supply this wattage. There is no suggested PSU for the GPU because it is integrated, and the power connectors are listed as none. For a sensible next upgrade, the user would need to look at a completely new laptop, as the CPU and GPU are both non-upgradeable. The platform is tied to the Raptor Lake-HX generation, so any future upgrade would involve moving to a newer platform entirely. The ECC memory support is a niche feature that is beneficial for certain workstation tasks, but the dual-channel memory bus may limit bandwidth in memory-intensive workloads. The PCIe Gen 5 lanes are available for storage devices like NVMe SSDs, which could be upgraded for faster data access, but the overall system’s performance is capped by the GPU, which cannot be improved.