SYSTEM ANALYZER

Rate My PC: Intel Core Ultra 5 115U + Intel Arc A370M

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
82%
VS
GPU
93%
PROCESSOR

Intel Core Ultra 5 115U

16,753 Benchmark Score
Top 18% Market Ranking
View Full Specs →
GRAPHICS CARD

Intel Arc A370M

29,175 Benchmark Score
Top 7% 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 5 115U and Intel Arc A370M form a mobile pairing aimed at thin-and-light laptops, blending a low-power Meteor Lake processor with a discrete-class GPU built on Intel’s Xe-HPG architecture. Benchmark data places this combination at the 72nd percentile overall, indicating a system that outperforms roughly three-quarters of tested configurations, but the data also shows clear limits in both CPU and GPU headroom that define its role as a capable mainstream solution rather than a high-end performer.

GPU Analysis — VRAM, bandwidth, clocks, RT/tensor hardware, what the benchmark scores mean for rendering

The Intel Arc A370M is built on the DG2-128 chip using TSMC’s 6 nm process, with a die size of 157 mm² and a transistor count of 7,200 million. Its clock behavior is straightforward: a base clock of 1550 MHz and a boost clock of 2050 MHz. Memory consists of 4 GB of GDDR6 on a 64-bit bus, delivering 112.0 GB/s of bandwidth, with memory clocks at 1750 MHz (14 Gbps effective). This is a modest memory subsystem by modern standards, but the 4 GB allocation is consistent with the card’s target segment of 1080p gaming and light creative work.

The GPU’s compute configuration includes 1024 shading units, 64 texture mapping units, and 32 raster operation units, yielding a pixel rate of 65.60 GPixel/s and a texture rate of 131.2 GTexel/s. Floating-point throughput is rated at 4.198 TFLOPS for FP32 and 8.397 TFLOPS for FP16 (2:1 ratio). More notable is the presence of 8 dedicated ray tracing cores, which places the A370M in the feature-rich camp for its class, supporting DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The PCIe interface is Gen 4.0 x8, which provides adequate bandwidth for the card’s VRAM and compute capabilities.

In benchmark terms, the A370M scores 29676 in Geekbench OpenCL and 28673 in Geekbench Vulkan, with an average benchmark score of 29175. That average places it at the 74th percentile among all GPUs, a strong showing for a mobile discrete part. The nearest rivals are highly instructive: the AMD Radeon RX Vega M GH scores 29197 (0.1% higher), the AMD FirePro W8000 scores 29211 (0.1% higher), the AMD Radeon RX 470 scores 28996 (0.6% lower), and the AMD Radeon RX 6800M scores 28874 (1.0% lower). The data indicates the A370M sits in a tight performance cluster, essentially matching older desktop midrange cards like the RX 470 while trailing the RX Vega M GH by a negligible margin. For rendering workloads, the ray tracing cores offer hardware acceleration for effects like reflections and shadows, but the 4.198 TFLOPS FP32 ceiling means complex scenes will require careful settings management. The Vulkan score of 28673 suggests strong API-level efficiency, which is relevant for modern game engines and compute-heavy rendering tasks.

Benchmark Performance — exact CPU and GPU scores, percentile positions, and what the combined picture is

The CPU side of this pairing is the Intel Core Ultra 5 115U, a Meteor Lake part with 8 cores and 10 threads, base clock at 1500 MHz and boost clock up to 4.20 GHz. Its benchmark results are consistent across Cinebench versions: R15 multicore scores 1094 and singlecore 154, R20 multicore scores 4559 and singlecore 643, and R23 multicore scores 10855 and singlecore 1532. PassMark results further break down the workload profile: multithread score is 13024, single thread is 3057, integer math is 41043, floating point math is 30538, data encryption is 8606, data compression is 141945, extended instructions score 8620, physics 898, random string sorting 15124, and find prime numbers 53. The average benchmark score for the CPU is 16753, placing it at the 70th percentile among all CPUs.

The GPU’s average benchmark score of 29175 places it at the 74th percentile, and the combined system percentile is 72. This creates a balanced picture where neither component dramatically outshines the other, though the GPU holds a slight percentile advantage. Comparing CPU rivals shows a tightly packed field: the Intel Core i5-1235U averages 16770 (0.1% higher), the AMD Ryzen 3 7335U averages 16827 (0.4% higher), the AMD Ryzen 3 8440U averages 16663 (0.5% lower), and the Intel Core i3-12100E averages 16853 (0.6% higher). The deltaPct values are all within one percent, meaning the Ultra 5 115U’s performance is essentially interchangeable with these competitors in aggregate benchmarks. For real workloads, this means the CPU is not a standout but is also not a bottleneck in most mainstream tasks. The combined picture is of a laptop that can handle productivity, light creative work, and 1080p gaming with settings adjusted, but it will not compete with high-core-count desktop or high-end mobile parts in heavily threaded workloads. The gap between Cinebench R23 multicore (10855) and singlecore (1532) scores suggests scaling efficiency across the 8 cores, though the modest thread count (10) limits extreme parallelism.

Upgrade Path and Platform — socket, memory support, PCIe, PSU headroom from suggestedPsu/tdp, what a sensible next upgrade looks like

The Intel Core Ultra 5 115U uses the Intel BGA 2049 socket, which is a soldered mobile package, meaning the CPU is not user-upgradable. The platform supports DDR5 memory with dual-channel configuration, and memory bandwidth is rated at 89.6 GB/s; however, the FACT PACK notes that memory support is dependent on the motherboard, so actual speeds may vary by laptop design. The CPU provides PCIe Gen 4 with 12 lanes, while the GPU uses a separate PCIe 4.0 x8 interface. The integrated graphics are Arc Xe-LPG with 48 execution units, which offers a fallback display option but is not a primary gaming solution.

Power characteristics are defined by the CPU’s TDP of 15 watts and the GPU’s TDP of 35 watts, totaling 50 watts for the two primary compute components. No suggested PSU is listed, and the GPU’s slot width is marked as IGP, indicating this is intended for integrated or preconfigured laptop designs rather than user-assembled systems. Given the soldered CPU and the absence of standard power connectors on the GPU, there is no meaningful upgrade path for the processor or the discrete GPU. The sensible next upgrade for a user in this platform would be to maximize what the laptop offers: adding more DDR5 memory if the motherboard supports it, or moving to an external GPU enclosure via the PCIe lanes if the laptop has a Thunderbolt or OCuLink port, though the FACT PACK does not confirm such connectivity. The 4 GB VRAM on the GPU is the most limiting factor for future-proofing; users who need more graphics memory would need to consider a different laptop entirely rather than upgrading components. The platform’s strength is its efficiency—50 watts total for CPU and GPU is low—which supports thinner chassis and longer battery life, but it also caps performance ceiling.

Who Should Build It — target users and industries (gamers at specific resolutions, content creators, developers, students, small business workstations) tied strictly to the measured performance

The data defines a clear user profile for this pairing: individuals who need a portable laptop for everyday computing and light-to-moderate graphics work without demanding extreme performance. Gamers at 1080p with moderate settings are the primary target, as the GPU’s 74th percentile ranking and 4 GB VRAM are sufficient for esports titles and older AAA games, but not for high-refresh or high-detail gaming. The CPU’s 70th percentile and PassMark multithread score of 13024 indicate it can handle office suites, web browsing, and productivity apps without strain, making it suitable for students and small business workstations where multitasking is common but heavy rendering is rare.

Content creators working with light photo editing or short 1080p video clips will find the A370M’s 1024 shading units and ray tracing support useful, but the 4.198 TFLOPS FP32 and 4 GB VRAM will force compromises in longer projects or higher resolutions. Software developers can benefit from the CPU’s 10 threads and 10 MB shared L3 cache for compilation tasks, though the PassMark extended instructions score of 8620 shows decent SIMD performance. The integrated Arc Xe-LPG graphics provide a backup for basic display output, but the discrete GPU is the workhorse. The system is not designed for AI model training or large-scale 3D rendering, given the GPU’s memory and compute limits. Small business workstations that run accounting software, document management, and light CRM tools will find the performance more than adequate, with the low TDP enabling fanless or near-silent operation in some designs. The key exclusion is high-end gamers and professional renderers, who would need more VRAM and higher FP32 throughput than this pairing provides.

Usage Scenarios — grounded in the scores: high-refresh gaming, streaming, video editing, 3D rendering, software development, student and office work. One short paragraph per scenario, citing the numbers that support the verdict

High-refresh gaming: The GPU’s average benchmark score of 29175 and 74th percentile ranking suggest it can drive 1080p displays at moderate refresh rates, but the 4 GB VRAM and 4.198 TFLOPS FP32 limit frame rates in demanding titles. Esports games like Counter-Strike or Valorant could approach high refresh rates, but AAA games will likely hover near 60 FPS at medium settings, making a 144Hz panel underutilized.

Streaming: The CPU’s 8 cores and 10 threads, combined with a PassMark multithread score of 13024, provide enough headroom for software encoding at 1080p, while the GPU’s ray tracing cores could offload some effects. The 15W CPU TDP and 35W GPU TDP mean thermals are manageable, but simultaneous gaming and encoding will stress the 10-thread limit, likely requiring a dedicated hardware encoder to avoid frame drops.

Video editing: The Cinebench R23 multicore score of 10855 and the GPU’s Vulkan score of 28673 indicate reasonable performance for 1080p timeline editing and color grading. The 4 GB VRAM is sufficient for effects stacks but will become a bottleneck with 4K footage or multiple layers, and the 112.0 GB/s memory bandwidth may slow scrubbing through high-bitrate clips.

3D rendering: The 8 ray tracing cores and 8.397 TFLOPS FP16 throughput support real-time previews in apps like Blender or Unreal Engine, but the 4.198 TFLOPS FP32 and 4 GB VRAM cap final-frame renders. The CPU’s R23 multicore score of 10855 means CPU-based rendering is possible for small scenes, but large projects will be slow, and the 10 MB L3 cache limits complex geometry handling.

Software development: The CPU’s PassMark integer math score of 41043 and single-thread score of 3057 show strong per-core performance for code compilation and script execution. The 10 threads handle parallel builds reasonably well, and the 89.6 GB/s memory bandwidth aids large data structures, making this a solid choice for web or mobile development.

Student and office work: The CPU’s 70th percentile ranking and PassMark data compression score of 141945 indicate snappy response for document editing, spreadsheet calculations, and web browsing. The integrated Arc Xe-LPG graphics provide a low-power fallback for display tasks, and the 15W CPU TDP ensures long battery life, making this ideal for all-day campus or office use without needing a dedicated GPU.

Gaming Performance — measured FPS by game and resolution from measuredFpsUltraByGame (or, if dataIsMeasured is false, frame expectations qualitatively from the benchmark scores and say the figures are estimates)

The FACT PACK contains no measured FPS rows for this exact CPU-GPU combination, and the `measuredFpsUltraByGame` field is empty. The `dataIsMeasured` flag is false, so all frame rate discussions must be treated as estimates derived from benchmark scores rather than empirical results. The GPU’s average benchmark score of 29175 and 74th percentile position, relative to rivals like the AMD Radeon RX 470 (0.6% lower) and AMD Radeon RX 6800M (1.0% lower), provide a reference point: the A370M should perform similarly to a desktop RX 470 in aggregate terms. For 1080p gaming at ultra settings, the 4 GB VRAM will be a limiting factor in titles that exceed that allocation, but based on the GPU’s compute and memory scores, users can expect playable frame rates in esports and older AAA games, with modern AAA titles requiring medium or high preset adjustments. At 1440p, the 4 GB VRAM and 112.0 GB/s bandwidth will cause significant performance drops, and the 64-bit memory bus further restricts high-resolution textures. The CPU’s single-thread score of 3057 and boost clock of 4.20 GHz should avoid bottlenecking the GPU in most scenarios, but the 8-core, 10-thread configuration may limit frame pacing in games that scale poorly across cores. These are estimates, not measured values, and actual performance will vary by game optimization and laptop cooling design.

Balance and Bottleneck — which component limits which workload, using percentiles and FPS scaling as evidence

The system’s combined percentile of 72, versus the CPU’s 70th and GPU’s 74th percentile, indicates a well-matched pairing where neither component is drastically out of line, but specific workloads reveal different bottlenecks. In CPU-bound tasks like physics simulation (PassMark physics score of 898) and prime number calculations (score of 53), the processor is the clear limiter, as these tasks show low scores that drag down the average. The Cinebench R23 singlecore score of 1532 is notably lower than the multicore score of 10855, suggesting that lightly threaded games or applications will not fully utilize the CPU’s potential, but the 4.20 GHz boost clock helps mitigate this. In GPU-bound workloads like gaming, the A370M’s 74th percentile is slightly higher than the CPU’s, meaning the GPU has a small edge in raw performance compared to the processor’s standing among its peers; however, the 4 GB VRAM and 64-bit bus create a hard ceiling that no amount of CPU power can overcome. For example, in a game that requires 6 GB of VRAM at 1080p ultra, the A370M will stutter or fail regardless of the CPU’s capability, making the GPU the bottleneck in high-texture scenarios. Conversely, in CPU-intensive simulations or compilation tasks, the GPU sits idle while the CPU’s 10 threads and 10 MB L3 cache work through the load, and the 15W TDP limits sustained boost clocks. The FPS scaling evidence, though estimated, suggests that at 1080p medium settings, the CPU can feed the GPU adequately, but at higher resolutions or settings, the GPU’s memory bandwidth (112.0 GB/s) and FP32 throughput (4.198 TFLOPS) will cause frame rates to drop faster than the CPU would predict. The balanced percentiles mean there is no single dominant bottleneck, but the GPU’s VRAM and the CPU’s thread count are the first limits encountered in gaming and productivity, respectively.

FAQ — 5-7 Q&A pairs answerable from FACT PACK data

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

A: The combined percentile is 72, meaning it outperforms 72% of all tested configurations.

Q: How does the Intel Arc A370M compare to its nearest rival in benchmark scores?

A: The A370M’s average benchmark score is 29175, while the AMD Radeon RX Vega M GH scores 29197, a 0.1% difference. The AMD Radeon RX 470 scores 28996, which is 0.6% lower than the A370M.

Q: What are the core and thread counts of the Intel Core Ultra 5 115U?

A: The CPU has 8 cores and 10 threads, with a base clock of 1500 MHz and a boost clock of 4.20 GHz.

Q: Does the Intel Arc A370M support hardware ray tracing?

A: Yes, it has 8 dedicated ray tracing cores, and it supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the memory configuration of the GPU?

A: The A370M has 4 GB of GDDR6 memory on a 64-bit bus, with a bandwidth of 112.0 GB/s and memory clocks at 1750 MHz (14 Gbps effective).

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

A: The CPU has a TDP of 15 watts, and the GPU has a TDP of 35 watts, totaling 50 watts for both components.

Q: Are there any measured FPS values for this specific combination?

A: No, the FACT PACK contains no measured FPS data for this exact CPU-GPU pairing, and the `dataIsMeasured` flag is false, so all frame rate figures are estimates based on benchmark scores.

CPU Analysis — cores, clocks, architecture, what the benchmark scores mean for real workloads

The Intel Core Ultra 5 115U is a Meteor Lake part built on Intel’s 7 nm process, featuring 8 cores and 10 threads, which implies a hybrid configuration with performance and efficiency cores, though the FACT PACK does not specify the ratio. Base clock is 1500 MHz with a boost clock of 4.20 GHz, and the cache hierarchy includes 112 KB L1 per core, 2 MB L2 per core, and 10 MB shared L3 cache. The CPU supports DDR5 memory with dual-channel configuration and 89.6 GB/s bandwidth, and it provides PCIe Gen 4 with 12 lanes. The integrated graphics are Arc Xe-LPG with 48 execution units, offering a secondary display output. The TDP is 15 watts, which is typical for ultra-low-power mobile processors, and the socket is Intel BGA 2049, confirming a soldered, non-upgradeable design.

Benchmark scores reveal a specific workload profile. Cinebench R23 multicore scores 10855 and singlecore scores 1532, showing good multicore scaling but modest single-thread performance relative to higher-end parts. PassMark results are more granular: integer math scores 41043 and floating point math scores 30538, indicating strong ALU performance for general computing. Data compression scores 141945, which is a high value and suggests efficient memory access for archive and file operations. Data encryption scores 8606, and extended instructions score 8620, both reasonable for security and SIMD workloads. However, physics scores 898 and find prime numbers scores 53, which are low, suggesting the CPU struggles with certain types of floating-point-heavy or latency-sensitive tasks. The average benchmark score is 16753, placing it at the 70th percentile, and the nearest rivals are all within 0.6% performance, such as the Intel Core i5-1235U (0.1% higher) and the AMD Ryzen 3 7335U (0.4% higher). For real workloads, this means the Ultra 5 115U is a competent mid-range processor: it handles office productivity, web development, and light content creation well, but it is not suited for heavy 3D rendering or large-scale data analysis. The 10 MB L3 cache helps with multitasking, but the 10-thread limit prevents it from seriously competing with higher-core-count chips in parallel workloads. Overall, the CPU provides a balanced platform for a laptop, with enough power for mainstream tasks and low enough TDP for portable designs, but it lacks the headroom for enthusiast-level computing.