Intel Graphics 4 Xe-Cores (Panther Lake)

Intel Graphics 4 Xe-Cores (Panther Lake)
Intel Graphics 4 Xe-Cores (Panther Lake) graphics card review

Intel Graphics 4 Xe-Cores (Panther Lake): 1080p for Less-Demanding Games, AAA Titles Only on Low Settings

Intel Graphics 4 Xe-Cores is the integrated Xe3 graphics solution for Panther Lake with four Xe-cores, while the lower-end version has two, and the Arc B370 and B390 have ten and twelve, respectively. It scores around 2800 points in the 3DMark Time Spy Graphics test. That is enough for Counter-Strike 2 at 1080p, but Cyberpunk 2077 already requires switching to low settings.

Performance is sufficient for esports games, but in modern AAA titles, four Xe-cores quickly run up against the 30 FPS mark.

Four Xe-cores are used in Core Ultra Series 3 processors in the Ultra 5, Ultra 7, and Ultra 9 classes. Therefore, the Core Ultra 9 designation alone does not indicate more powerful integrated graphics: the Core Ultra 5 325 and Core Ultra 9 386H may use the same GPU configuration.

One GPU, but up to a 48% Difference Between Laptops

In 3DMark Time Spy Graphics, the tested laptops score between 2117 and 3136 points. The median is approximately 2900 points.

Device Processor RAM 3DMark Time Spy Graphics
ASUS ExpertBook P5605CAA-XS76 Core Ultra 7 356H 32 GB 2117
MSI Prestige 13 AI+ A3MG Core Ultra 9 386H 32 GB 2391
Dell XPS 16 Core Ultra 5 325 16 GB 2800
Lenovo ThinkPad X1 Carbon Gen 14 Core Ultra 5 325 32 GB 2905
Samsung Galaxy Book6 Pro Core Ultra 7 356H 32 GB 3003
Dell Pro 7 13 2-in-1 Core Ultra 7 366H 64 GB 3136

The difference between the slowest and fastest results reaches 48%.

The Core Ultra 5 325 in the Lenovo ThinkPad X1 Carbon Gen 14 scores 2905 points, while the MSI Prestige 13 with the Core Ultra 9 386H scores 2391. Power limits, cooling, and memory configuration all affect the result.

Therefore, when choosing a laptop for gaming, it is not enough to look only at the processor designation-two laptops with the same iGPU can differ noticeably in performance.

Intel Graphics 4 Xe-Cores Gaming Tests

Game Low Medium High Ultra
Dota 2 Reborn 124 FPS 84 FPS 82 FPS 78 FPS
Counter-Strike 2 79 FPS 59 FPS 33 FPS 21 FPS
GTA V 167 FPS 157 FPS 51 FPS 21 FPS
Cyberpunk 2077 37 FPS 28 FPS 24 FPS 20 FPS
Baldur's Gate 3 31 FPS 25 FPS 21 FPS 21 FPS

Dota 2 runs at 82 FPS on high settings and 78 FPS on Ultra.

Counter-Strike 2 at 1080p Low runs at around 79 FPS, while Medium delivers 59 FPS. To move noticeably above 60 FPS, settings have to be lowered to Low.

In GTA V, you can expect roughly 51 FPS at 1080p High without a discrete graphics card.

Cyberpunk 2077 delivers around 37 FPS at 1080p Low and 28 FPS at Medium. For a more stable frame rate, you will need to use XeSS or FSR, or reduce the render resolution.

Baldur's Gate 3 stays near 30 FPS only on low settings.

Black Myth: Wukong runs at around 18 FPS on Low. Even reducing the resolution and using upscaling does not guarantee a stable 30 FPS.

Four Xe-Cores vs. Two

The first tested Panther Lake system with Intel Graphics 2 Xe-Cores scored 1362 points in Time Spy Graphics. The average result for the four-Xe-core version is 2838 points.

GPU Xe-cores Time Spy Graphics
Intel Graphics 2 Xe-Cores 2 1362
Intel Graphics 4 Xe-Cores 4 2838

The difference exceeds 100%, but it is still too early to consider this exact twofold scaling. Far fewer results are available for the two-Xe-core version, while Intel Graphics 4 Xe-Cores has already been tested in numerous laptops.

Even taking the smaller sample for the lower-end version into account, four Xe-cores are noticeably faster than two. Two Xe-cores are intended primarily for everyday tasks and less-demanding games, while four already allow Counter-Strike 2, GTA V, and some modern titles to run properly at 1080p.

Arc B370 and B390 Are Much Faster

The Arc B370 has 10 Xe-cores, while the Arc B390 has 12, compared with four in Intel Graphics 4 Xe-Cores.

Therefore, the Core Ultra 9 386H with Intel Graphics 4 Xe-Cores should not be confused with the Core Ultra X9 388H and its Arc B390. The difference in the processor names is small, but the number of Xe-cores differs threefold.

If you need high gaming performance without a discrete graphics card, the Arc B370-and especially the B390-are in a higher class.

Is It Worth Buying a Laptop with Intel Graphics 4 Xe-Cores?

For work, multimedia, and occasional gaming, a discrete graphics card is not essential with this iGPU.

It is not worth paying extra to move from the Core Ultra 5 to the Core Ultra 9 solely for integrated graphics. In the table, the Core Ultra 5 325 scores higher than the Core Ultra 9 386H, so the higher-end CPU does not guarantee higher iGPU performance.

If the laptop is being purchased primarily for gaming, it is better to look for a Panther Lake model with the Arc B370 or Arc B390.

Conclusion

Intel Graphics 4 Xe-Cores can handle not only work and video playback but also 1080p gaming. It is capable of running esports and older games, while modern AAA titles require low settings and upscaling.

Results vary by almost one and a half times between different laptops, so the processor model alone says little about integrated graphics performance.

Intel Graphics 4 Xe-Cores is suitable for an all-purpose laptop used for occasional gaming. For demanding games, it is better to choose Panther Lake with the Arc B370 or B390.

GPU Comparison

Compare Graphics 4 Xe-Cores (Panther Lake) with other GPUs

Please select GPU from the dropdown list.

Basic

Label Name
Intel
Platform
Integrated
Launch Date
January 2026
Former Codename
Panther Lake
GPU Lithography
Intel 3
Model Name
Intel Graphics
Generation
Xe3 (Panther Lake)
Base Clock
300 MHz
Boost Clock
2300-2500 MHz
RT Cores
4
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
32
Foundry
Intel
Process Size
Intel 3
Architecture
Xe3
Xe-cores
4

Memory Specifications

Memory Size
System Shared
Memory Type
DDR5 / LPDDR5X (System Shared)
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
System Shared
Memory Clock
System Dependent
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
System Dependent

Display and Media

AV1 Encode/Decode
Yes
DisplayPort Extensions
DisplayPort 2.1 UHBR20
H.264 Hardware Encode/Decode
Yes
H.265 HEVC Hardware Encode/Decode
Yes
H.266 VVC Hardware Encode/Decode
Decode Only
HDMI Version
HDMI 2.1 FRL
Intel Quick Sync Video
Yes
Max Resolution DP
7680 x 4320 @ 60Hz
Max Resolution eDP
3840 x 2400 @ 120Hz
Number of Displays Supported
4
Outputs
eDP 1.5, DisplayPort 2.1 UHBR20, HDMI 2.1 FRL

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
36.8-40.0 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
73.6-80.0 GTexel/s
FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
2.56 TFLOPS

AI Features

AI Software Frameworks Supported by GPU
OpenVINO, WindowsML, DirectML, ONNX RT, WebGPU, WebNN
GPU Peak TOPS (Int8)
37-40 TOPS
Intel Deep Learning Boost on GPU
Yes

Miscellaneous

Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
512
L2 Cache
4 MB
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.4
OpenCL Version
3.0
OpenGL
4.6
CUDA
No
DirectX
DirectX 12 Ultimate
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
16

Benchmarks

Cyberpunk 2077 1080p
Score
28 fps
GTA 5 1080p
Score
51 fps
FP32 (float)
Score
2.56 TFLOPS
3DMark Steel Nomad
Score
585
3DMark Time Spy
Score
2824
Vulkan
Score
26276
OpenCL
Score
22285

Compared to Other GPU

Cyberpunk 2077 1080p / fps
75 +167.9%
60 +114.3%
GTA 5 1080p / fps
186 +264.7%
172 +237.3%
151 +196.1%
108 +111.8%
FP32 (float) / TFLOPS
2.757 +7.7%
2.519 -1.6%
2.481 -3.1%
3DMark Time Spy
4952 +75.4%
3817 +35.2%
1205 -57.3%
3DMark Steel Nomad
647 +10.6%
555 -5.1%
537 -8.2%
Vulkan
69708 +165.3%
45859 +74.5%
12472 -52.5%
7844 -70.1%