Intel Arc Graphics 1 Xe Mobile vs NVIDIA GeForce RTX 4070 Comparison

Head-to-Head Benchmarks

The database contains no shared benchmark entries for the Intel Arc Graphics 1 Xe Mobile and the NVIDIA GeForce RTX 4070. The Intel part has an empty benchmark list and an average benchmark score of zero, which places it at the 50th percentile among all tracked GPUs. The NVIDIA card, by contrast, carries a full set of ten recorded tests with an average benchmark score of 37,648, placing it at the 81st percentile.

Direct comparison therefore relies entirely on the NVIDIA side of the ledger. In 3DMark Steel Nomad DX12, the RTX 4070 records 3,854 points. Its Geekbench OpenCL result reaches 154,858, while the Vulkan score climbs higher still at 174,152. PassMark tests show a G3D score of 26,927, with GPU compute at 14,720. Legacy DirectX tests land at 320 for DX9, 244 for DX11, 139 for DX10, and 103 for DX12. The 2D score sits at 1,164.

The Intel Arc Graphics 1 Xe Mobile has no comparable numbers in the database. Its only statistical marker is the 50th percentile ranking, which suggests a mid-pack position among all GPUs, but with zero recorded benchmark scores the percentile cannot be tied to any specific workload outcome. The RTX 4070, at 81 percent, sits well above it in the overall distribution.

The nearest rivals for the RTX 4070 provide additional context. The NVIDIA Tesla P4 averages 37,628, a 0.1 percent difference. The AMD Radeon RX Vega 56 averages 37,507, a 0.4 percent gap. The NVIDIA GeForce RTX 4080 Mobile averages 38,135, which is 1.3 percent higher, while the AMD Radeon PRO W6400 averages 37,157, 1.3 percent lower. These deltas are all small, indicating that the RTX 4070 sits inside a tight performance cluster.

No such rival data exists for the Intel part. The wins tally shows zero for both sides in head-to-head benchmarks, which reflects the absence of shared tests rather than a measured tie. The data cannot show a single workload where the Intel GPU outperforms the RTX 4070, because no workload was recorded for the Intel part.

The Verdict

The recorded data points to a clear separation. The NVIDIA GeForce RTX 4070 delivers measurable results across every benchmark category in the database, from 3DMark Steel Nomad at 3,854 to PassMark G3D at 26,927 and Geekbench Vulkan at 174,152. Its 81st percentile ranking and average score of 37,648 place it among the top quarter of all tracked GPUs.

The Intel Arc Graphics 1 Xe Mobile shows no benchmark results at all. Its 50th percentile ranking without any supporting scores means the database has no evidence of its real-world performance in any of the ten test categories. A percentile with zero average score is a placeholder, not a measurement.

From the data alone, the RTX 4070 is the only part with demonstrated performance. The Intel GPU is a 3 nm integrated part with a 25 W TDP, designed for portable devices, while the RTX 4070 is a 200 W dual-slot discrete card with a 16-pin power connector and a suggested 550 W power supply. These are different product classes with different design goals, and the benchmark data reflects that only on the NVIDIA side.

Users who need documented frame rates, compute scores, and DirectX or Vulkan results will find them exclusively with the RTX 4070. The Intel part has no recorded wins, no recorded scores, and no rival comparisons. The database cannot support a case for the Intel GPU in any measurable workload.

FAQ

Q: Which GPU has a higher benchmark average score?

A: The NVIDIA GeForce RTX 4070 has an average benchmark score of 37,648. The Intel Arc Graphics 1 Xe Mobile has an average benchmark score of 0.

Q: How does the RTX 4070 compare to its nearest rivals?

A: The RTX 4070 averages 37,648. It sits 0.1 percent above the NVIDIA Tesla P4 (37,628), 0.4 percent above the AMD Radeon RX Vega 56 (37,507), 1.3 percent below the NVIDIA GeForce RTX 4080 Mobile (38,135), and 1.3 percent above the AMD Radeon PRO W6400 (37,157).

Q: What is the highest recorded benchmark score for the RTX 4070?

A: The highest score is 174,152 in Geekbench Vulkan. The next highest is 154,858 in Geekbench OpenCL, followed by 26,927 in PassMark G3D.

Q: What DirectX benchmark scores does the RTX 4070 have?

A: PassMark DirectX scores are 320 for DX9, 244 for DX11, 139 for DX10, and 103 for DX12. The 3DMark Steel Nomad DX12 test records 3,854.

Q: Does the Intel Arc Graphics 1 Xe Mobile have any benchmark entries?

A: No. The database lists an empty benchmark array, an average score of 0, and no nearest rivals for the Intel part.

Q: What percentile ranking does each GPU hold?

A: The Intel Arc Graphics 1 Xe Mobile ranks at the 50th percentile among all GPUs. The NVIDIA GeForce RTX 4070 ranks at the 81st percentile.

Specification Differences

The two GPUs differ across nearly every recorded specification field. The Intel Arc Graphics 1 Xe Mobile uses a 3 nm process from Intel, while the RTX 4070 uses a 5 nm process from TSMC. Transistor counts differ sharply: the Intel part is listed as unknown, while the NVIDIA chip carries 35,800 million transistors on a 294 mm² die, giving a transistor density of 121.8M per mm².

Clock speeds show a 300 MHz base and 2300 MHz boost for the Intel GPU. The RTX 4070 runs a 1920 MHz base and 2475 MHz boost, with memory clock at 1313 MHz or 21 Gbps effective. Memory configurations are fundamentally different. The Intel part uses system shared memory with system dependent bandwidth. The RTX 4070 has 12 GB of GDDR6X on a 192-bit bus with 504.2 GB/s bandwidth.

Compute resources diverge heavily. The Intel GPU has 128 shading units, 8 texture mapping units, 4 raster output units, and 1 ray tracing core. The RTX 4070 has 5,888 shading units, 184 TMUs, 64 ROPs, 46 RT cores, and 184 tensor cores. Pixel rate for the Intel part is 9.200 GPixel/s with a texture rate of 18.40 GTexel/s. The RTX 4070 reaches 158.4 GPixel/s and 455.4 GTexel/s. FP32 throughput is 588.8 GFLOPS for Intel versus 29.15 TFLOPS for NVIDIA. FP16 rates are 1,177.6 GFLOPS (2:1) for Intel and 29.15 TFLOPS (1:1) for NVIDIA.

Power and physical dimensions also differ. The Intel GPU draws 25 W, is an IGP with no power connectors, and uses an IGP bus interface. The RTX 4070 draws 200 W, is dual-slot, requires one 16-pin connector, and suggests a 550 W power supply. The NVIDIA card measures 240 mm in length, 110 mm in height, and 40 mm in width. The Intel part has no listed dimensions. Display outputs for Intel are portable device dependent, while the RTX 4070 offers one HDMI 2.1 and three DisplayPort 1.4a outputs.

Production status and release dates differ as well. The Intel GPU is active with a release date of April 15, 2026, and no launch MSRP. The RTX 4070 is end-of-life, released April 11, 2023, with a launch MSRP of 599 USD. The Intel predecessor is HD Graphics-M; the NVIDIA predecessor is GeForce 30, with successor GeForce 50.

Architecture Differences

The Intel Arc Graphics 1 Xe Mobile is built on the Xe3-LPG architecture using the Wildcat Lake chip. It belongs to the Arc Graphics-M (Wildcat Lake) generation. The RTX 4070 uses the Ada Lovelace architecture on the AD104 chip within the GeForce 40 series.

The Intel GPU integrates 1 ray tracing core, which supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 4070 carries 46 RT cores and 184 tensor cores, also supporting DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. API coverage is identical, but the hardware underneath differs by orders of magnitude.

Memory architecture separates the two sharply. The Intel part shares system memory with no dedicated VRAM, no memory bus width, and bandwidth that depends on the host system. The RTX 4070 has dedicated 12 GB GDDR6X with a fixed 192-bit bus and a fixed 504.2 GB/s bandwidth. This makes the NVIDIA card independent of system memory performance.

The Intel GPU is an integrated part with no slot width, no power connectors, and a 25 W TDP. It is designed to sit inside a portable device. The RTX 4070 is a discrete dual-slot card with a 16-pin power connector, 200 W TDP, and a 550 W suggested power supply. The NVIDIA part is a standalone expansion card with physical dimensions, while the Intel part has none listed.

The tensor core count differs significantly. Intel lists no tensor cores, while NVIDIA has 184. The FP16 ratio also differs: Intel runs at 2:1, meaning half the rate of FP32, while NVIDIA runs at 1:1, matching FP32 throughput. This gives the RTX 4070 a compute advantage in mixed-precision workloads.

Where Each One Wins

The NVIDIA GeForce RTX 4070 wins every category where data exists. In rasterization, its 158.4 GPixel/s pixel rate and 455.4 GTexel/s texture rate far exceed the Intel figures of 9.200 GPixel/s and 18.40 GTexel/s. In compute, the RTX 4070 delivers 29.15 TFLOPS FP32 versus 588.8 GFLOPS for Intel, a 49.5 times difference. FP16 shows a similar gap at 29.15 TFLOPS versus 1,177.6 GFLOPS.

For ray tracing, the RTX 4070 has 46 RT cores against a single RT core on the Intel part. For tensor operations, NVIDIA has 184 tensor cores while Intel has none listed. Memory bandwidth favors NVIDIA at 504.2 GB/s versus system dependent for Intel. The RTX 4070 also wins on benchmark evidence with all ten recorded scores, including a 26,927 PassMark G3D result and a 174,152 Geekbench Vulkan score.

The Intel Arc Graphics 1 Xe Mobile has no recorded wins. Its advantages, where they exist, are structural rather than performance-based. It uses a 3 nm process versus 5 nm for NVIDIA, which indicates a newer manufacturing node. It draws 25 W versus 200 W, making it suitable for systems without discrete power delivery. It is an IGP with no power connectors, no slot width, and no suggested PSU, meaning it fits in portable devices where the RTX 4070 cannot operate.

The RTX 4070, by contrast, is a dual-slot, 240 mm card requiring a 16-pin connector and a 550 W power supply. It is end-of-life with a successor in the GeForce 50 series, while the Intel part is active with no successor. The data shows the NVIDIA card as the only one with measurable performance. The Intel GPU remains an unmeasured integrated option whose 50th percentile ranking lacks any supporting benchmark evidence.