AMD Radeon 890M vs Intel Arc Graphics 4 Xe Mobile Comparison

Where Each One Wins

The recorded benchmark data presents an asymmetric picture. The AMD Radeon 890M has a full suite of ten benchmark results across DirectX 10, 11, 12, and 9, plus OpenCL, Vulkan, and compute workloads. The Intel Arc Graphics 4 Xe Mobile, by contrast, has no recorded benchmark scores in the database at this time. Its percentile rank of 50 against all GPUs is listed, but the average benchmark score is zero, and there are no nearest rivals provided. This means the AMD part wins every measurable category by default, not because of direct comparison, but because the Intel part lacks any submitted results.

The AMD Radeon 890M shows its strength in compute-oriented workloads. The Geekbench OpenCL score of 37,254 and the Vulkan score of 40,808 are substantial numbers for an integrated graphics processor. The Passmark GPU Compute score of 4,157 further indicates that this part handles general-purpose compute tasks with reasonable efficiency. For legacy DirectX workloads, the Passmark DirectX 9 score of 97 is the highest among the DirectX tests, while DirectX 11 scores 73, DirectX 12 scores 37, and DirectX 10 scores 33. The 3DMark Steel Nomad DX12 test, a modern gaming workload, records a score of 590.

The Intel Arc Graphics 4 Xe Mobile, based on the Panther Lake chip and the Xe3-LPG architecture, has a percentile rank of 50, which sits above the AMD part's percentile rank of 45. However, without a single benchmark score in the database, there is no way to verify what that percentile represents. The data shows a product that is active in production status but has not yet contributed any measured results. The AMD part has an average benchmark score of 9,210, placing it in the 45th percentile of all GPUs, and its nearest rivals include the AMD Radeon Vega 8 at 9,221 average score with a delta of -0.1 percent, the NVIDIA GeForce GTX 960 at 9,273 with a delta of -0.7 percent, the NVIDIA GeForce GTX 465 at 9,294 with a delta of -0.9 percent, and the NVIDIA GeForce GTX 850M at 9,302 with a delta of -1 percent. These deltas are all negative, meaning the 890M scores slightly below each rival, but the differences are all within one percent.

Architecture Differences

The two integrated GPUs come from different manufacturers and use entirely different underlying technologies. The AMD Radeon 890M is built on the Strix Point chip with the RDNA 3.5 architecture, part of the Navi III IGP generation for Strix Point Mobile. It uses a 4 nm process node from TSMC, containing 34,000 million transistors on a die size of 233 mm squared, yielding a transistor density of 145.9 million per mm squared. The Intel Arc Graphics 4 Xe Mobile uses the Panther Lake chip with the Xe3-LPG architecture, part of the Arc Graphics-M generation for Panther Lake. It uses a 3 nm process node from Intel, but the transistor count and die size are listed as unknown.

The compute resources differ sharply. The AMD part has 1,024 shading units, 64 texture mapping units, 32 raster output pipelines, and 16 ray tracing cores. The Intel part has 512 shading units, 32 TMUs, 16 ROPs, and 4 ray tracing cores. This gives the AMD part exactly double the shading units, double the TMUs, double the ROPs, and quadruple the ray tracing cores. The clock speeds also differ: the AMD part runs at a base of 400 MHz and a boost of 2,900 MHz, while the Intel part runs at a base of 300 MHz and a boost of 2,300 MHz. The AMD boost clock is 600 MHz higher than the Intel boost clock.

Both parts use system shared memory with system dependent bandwidth, meaning they draw on the host system's RAM rather than dedicated video memory. Both are integrated graphics processors with no power connectors and portable device dependent display outputs. The AMD part uses a PCIe 4.0 x8 bus interface, while the Intel part uses an IGP bus interface. The thermal design power differs: the AMD part is rated at 15 W, while the Intel part is rated at 25 W. The Intel part has a higher TDP by 10 W, which could indicate more thermal headroom, but without benchmark scores, the impact of that headroom cannot be measured.

The floating point throughput reflects the hardware differences. The AMD part delivers 5.939 TFLOPS for FP32 and the same 5.939 TFLOPS for FP16 with a 1:1 ratio. The Intel part delivers 2.355 TFLOPS for FP32 and 4.710 TFLOPS for FP16 with a 2:1 ratio. The AMD part's FP32 throughput is more than double the Intel part's, at 5.939 TFLOPS versus 2.355 TFLOPS. The pixel rate is 92.80 GPixel/s for AMD and 36.80 GPixel/s for Intel, and the texture rate is 185.6 GTexel/s for AMD and 73.60 GTexel/s for Intel. Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical.

Head-to-Head Benchmarks

There are no head-to-head benchmark records in the database for these two parts. The wins count for the AMD Radeon 890M is zero, and the wins count for the Intel Arc Graphics 4 Xe Mobile is also zero. This is because the Intel part has an empty benchmark array. The AMD part has ten individual scores, but none of them can be compared directly to the Intel part since no Intel scores exist.

The AMD part's individual results show a clear hierarchy across workloads. The Geekbench Vulkan score of 40,808 is the highest recorded result, followed closely by the Geekbench OpenCL score of 37,254. The Passmark G3D score of 8,076 is the next highest, followed by the Passmark GPU Compute score of 4,157. The Passmark G2D score of 979 is lower, and the DirectX legacy scores are smaller still. The 3DMark Steel Nomad DX12 score of 590 sits in the middle range. The Passmark DirectX 9 score of 97 is the highest of the four DirectX tests, which is notable because many modern parts struggle with legacy DirectX 9 workloads.

The average benchmark score for the AMD part is 9,210, which places it in the 45th percentile of all GPUs. The nearest rival data shows that the AMD Radeon Vega 8 averages 9,221, a delta of -0.1 percent, meaning the 890M is essentially tied with the Vega 8. The NVIDIA GeForce GTX 960 averages 9,273, a delta of -0.7 percent. The NVIDIA GeForce GTX 465 averages 9,294, a delta of -0.9 percent. The NVIDIA GeForce GTX 850M averages 9,302, a delta of -1 percent. All four rivals score within one percent of the 890M, indicating that the 890M sits in a tight performance cluster. The Intel part has no average benchmark score to compare, and its percentile rank of 50 is not backed by any measured data.

FAQ

Q: Which GPU has the higher boost clock speed?

A: The AMD Radeon 890M has a boost clock of 2,900 MHz, which is 600 MHz higher than the Intel Arc Graphics 4 Xe Mobile's boost clock of 2,300 MHz.

Q: How do the shading unit counts compare between the two parts?

A: The AMD Radeon 890M has 1,024 shading units, exactly double the 512 shading units of the Intel Arc Graphics 4 Xe Mobile.

Q: What is the FP32 throughput difference?

A: The AMD Radeon 890M delivers 5.939 TFLOPS for FP32, while the Intel Arc Graphics 4 Xe Mobile delivers 2.355 TFLOPS, making the AMD part more than double the Intel part's FP32 throughput.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both the AMD Radeon 890M and the Intel Arc Graphics 4 Xe Mobile support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: Which GPU has a higher TDP rating?

A: The Intel Arc Graphics 4 Xe Mobile has a TDP of 25 W, which is 10 W higher than the AMD Radeon 890M's TDP of 15 W.

Q: What benchmark scores exist for the Intel Arc Graphics 4 Xe Mobile?

A: The database contains no benchmark scores for the Intel Arc Graphics 4 Xe Mobile. Its average benchmark score is listed as zero, and its benchmark array is empty.

The Verdict

The data shows a clear situation: the AMD Radeon 890M has extensive measured results, while the Intel Arc Graphics 4 Xe Mobile has none. For anyone selecting between these two parts based on the database, the AMD part offers verified performance across ten different workloads, including modern DirectX 12, Vulkan, OpenCL, and compute tests. The Intel part offers only a percentile rank of 50 with no supporting scores, which cannot be used for any practical comparison.

The AMD part's nearest rivals, all scoring within one percent of its average, indicate that its performance level is well understood. The AMD Radeon Vega 8 and the NVIDIA GeForce GTX 960, GTX 465, and GTX 850M all sit within a narrow band around the 890M's average score of 9,210. This suggests the 890M delivers a consistent, mid-range experience for integrated graphics. The Intel part's percentile rank of 50, if taken at face value, would place it in the middle of the GPU distribution, but without benchmark data, that rank is unverifiable.

From a specification standpoint, the AMD part has double the shading units, TMUs, and ROPs, plus four times the ray tracing cores, and a higher boost clock. It also uses a 4 nm process from TSMC with a known transistor count of 34,000 million. The Intel part uses a 3 nm process from Intel with unknown transistor counts and die size. The AMD part's FP32 throughput of 5.939 TFLOPS is more than double the Intel part's 2.355 TFLOPS. The pixel rate and texture rate of the AMD part are also substantially higher. The only specification where the Intel part leads is TDP, at 25 W versus 15 W, and FP16 throughput, at 4.710 TFLOPS versus 5.939 TFLOPS, though the Intel FP16 number is still lower in absolute terms.

The verdict is straightforward from the recorded data. The AMD Radeon 890M is the only part with measurable performance, and its results place it in the 45th percentile of all GPUs with an average score of 9,210. The Intel Arc Graphics 4 Xe Mobile cannot be evaluated for performance because no benchmark scores exist. Any user relying on the database for a performance comparison must choose the AMD part, as it is the only one with verified results. The Intel part's higher TDP and 3 nm process node suggest different design priorities, but without scores, those priorities do not translate into measurable advantages.

Specification Differences

| Specification | AMD Radeon 890M | Intel Arc Graphics 4 Xe Mobile |

| --- | --- | --- |

| Manufacturer | AMD | Intel |

| Chip | Strix Point | Panther Lake |

| Architecture | RDNA 3.5 | Xe3-LPG |

| Generation | Navi III IGP (Strix Point Mobile) | Arc Graphics-M (Panther Lake) |

| Process Node | 4 nm (TSMC) | 3 nm (Intel) |

| Transistors | 34,000 million | Unknown |

| Die Size | 233 mm² | Unknown |

| Base Clock | 400 MHz | 300 MHz |

| Boost Clock | 2,900 MHz | 2,300 MHz |

| Shading Units | 1,024 | 512 |

| TMUs | 64 | 32 |

| ROPs | 32 | 16 |

| Ray Tracing Cores | 16 | 4 |

| Pixel Rate | 92.80 GPixel/s | 36.80 GPixel/s |

| Texture Rate | 185.6 GTexel/s | 73.60 GTexel/s |

| FP32 | 5.939 TFLOPS | 2.355 TFLOPS |

| FP16 | 5.939 TFLOPS (1:1) | 4.710 TFLOPS (2:1) |

| TDP | 15 W | 25 W |

| Bus Interface | PCIe 4.0 x8 | IGP |

| Release Date | 2024-07-14 | 2026-01-26 |

| Average Benchmark Score | 9,210 | 0 |

| Percentile vs All GPUs | 45 | 50 |