Intel Arc Graphics 128EU Mobile vs NVIDIA GeForce RTX 5070 Mobile Comparison

Head-to-Head Benchmarks

The recorded data presents a stark contrast between the Intel Arc Graphics 128EU Mobile and the NVIDIA GeForce RTX 5070 Mobile. The database contains no benchmark entries for the Intel part, leaving its performance profile entirely unmeasured. The NVIDIA part, by contrast, carries a full suite of nine benchmark scores across Geekbench and Passmark tests, providing a clear picture of its standing.

The NVIDIA GeForce RTX 5070 Mobile delivers an average benchmark score of 29,928 across its recorded tests. This places it in the 75th percentile of all GPUs in the database, a solid position that indicates strong overall performance. Its nearest rivals confirm this placement. The RTX 5070 Mobile sits within 0.1% of the NVIDIA GeForce RTX 3070 Ti, which scores 29,945, meaning the two are effectively tied in aggregate performance. It runs 0.5% ahead of the NVIDIA GeForce RTX 2080 Ti, which scores 29,783, and trails the AMD Radeon RX 6800 by 0.6%, that card scoring 30,095. The largest gap among its nearest rivals is against the AMD Radeon RX 6700, where the RTX 5070 Mobile is 1.7% behind a score of 30,433. These deltas are all small, indicating the RTX 5070 Mobile competes in a tight cluster of high-end desktop-class parts.

Looking at individual workloads, the RTX 5070 Mobile shows notable variation. In Geekbench OpenCL, it scores 122,238, while in Geekbench Vulkan it reaches 116,960. The Vulkan result trails the OpenCL score by approximately 4.3%, a modest gap that suggests the driver and architecture handle both APIs similarly. Passmark results tell a different story. The DirectX 9 score of 214 and the DirectX 10 score of 129 show the part handles legacy APIs, while DirectX 11 reaches 192 and DirectX 12 drops to 93. The DirectX 12 score is notably lower than the DirectX 11 score, a 51.6% reduction, which is an unusual pattern for a modern GPU and may reflect specific driver or test characteristics rather than raw capability.

The Passmark G3D score of 20,355 and the GPU compute score of 8,279 round out the picture. The G3D score, which represents general 3D graphics performance, is substantially higher than the compute score, indicating the RTX 5070 Mobile is optimized for rasterization and graphics workloads over general-purpose compute. The G2D score of 896 is comparatively modest, reflecting that 2D performance is not a primary strength of this part.

The Intel Arc Graphics 128EU Mobile has no recorded benchmarks and no nearest rivals in the database. Its average benchmark score is listed as zero, and its percentile ranking sits at 50, which is the median position for all GPUs in the database. This percentile is not derived from actual performance measurements but rather reflects a default or unranked status. Without benchmark data, no direct head-to-head comparison of scores is possible. The wins count is zero for the Intel part and zero for the NVIDIA part, confirming that no measured comparison exists in the database.

FAQ

Q: How does the NVIDIA GeForce RTX 5070 Mobile compare to its nearest rivals in average benchmark score?

A: The RTX 5070 Mobile scores 29,928 on average. It is 0.1% behind the NVIDIA GeForce RTX 3070 Ti, which scores 29,945, and 0.5% ahead of the NVIDIA GeForce RTX 2080 Ti, which scores 29,783. It trails the AMD Radeon RX 6800 by 0.6% (score 30,095) and the AMD Radeon RX 6700 by 1.7% (score 30,433).

Q: What is the percentile ranking of each GPU in the database?

A: The NVIDIA GeForce RTX 5070 Mobile ranks in the 75th percentile of all GPUs. The Intel Arc Graphics 128EU Mobile ranks in the 50th percentile, though this is not tied to any measured benchmark performance since it has no recorded scores.

Q: How do the Geekbench scores for the RTX 5070 Mobile compare?

A: The Geekbench OpenCL score is 122,238, while the Geekbench Vulkan score is 116,960. The Vulkan result is about 4.3% lower than the OpenCL result, indicating a slight performance difference between the two APIs.

Q: What do the Passmark DirectX scores indicate about the RTX 5070 Mobile?

A: The DirectX 9 score is 214, DirectX 10 is 129, DirectX 11 is 192, and DirectX 12 is 93. The DirectX 12 score is roughly half of the DirectX 11 score, a notable drop that appears in the recorded data.

Q: Does the Intel Arc Graphics 128EU Mobile have any benchmark entries?

A: No. The database lists no benchmarks for the Intel part, and its average benchmark score is zero. Its nearest rivals list is empty, so no performance comparisons can be drawn from measured data.

Q: What is the average benchmark score for the RTX 5070 Mobile?

A: The average benchmark score is 29,928, derived from its nine recorded test results. This places it in the 75th percentile and close to the scores of several desktop GPUs from previous generations.

The Verdict

The data supports a clear separation between these two mobile GPUs. The NVIDIA GeForce RTX 5070 Mobile is a measured performer with a 75th percentile ranking and an average score of 29,928. Its nearest rivals are all established desktop GPUs, and the deltas between them are minimal, ranging from 1.7% behind the AMD Radeon RX 6700 to 0.5% ahead of the NVIDIA GeForce RTX 2080 Ti. This indicates the RTX 5070 Mobile delivers desktop-class performance in a mobile form factor.

The Intel Arc Graphics 128EU Mobile has no measured performance data. Its 50th percentile ranking appears to be a placeholder rather than a result of testing. The absence of benchmarks and nearest rivals means the database cannot support any performance claims for this part.

For users selecting between the two based solely on recorded data, the choice is straightforward. The RTX 5070 Mobile has demonstrated performance across multiple APIs and workloads. The Intel part has no recorded evidence of performance. The RTX 5070 Mobile also brings a larger feature set, including dedicated ray tracing cores and tensor cores, which the Intel part lacks entirely. The RTX 5070 Mobile offers 8 GB of GDDR7 memory with 384.0 GB/s of bandwidth, while the Intel part relies on system shared memory with system dependent bandwidth. These are substantial differences in both measured results and architectural capability.

The RTX 5070 Mobile is the only part in this comparison with data supporting its performance. The Intel Arc Graphics 128EU Mobile may serve specific integrated graphics roles, but the database contains no evidence of its performance level. The verdict, based strictly on recorded measurements, favors the NVIDIA part overwhelmingly.

Specification Differences

The two GPUs differ across nearly every recorded specification. The NVIDIA GeForce RTX 5070 Mobile uses the GB206 chip built on a 5 nm process at TSMC, while the Intel Arc Graphics 128EU Mobile uses the Meteor Lake chip on a 10 nm process at Intel. The NVIDIA part integrates 21,900 million transistors on a 181 mm² die, giving a transistor density of 121.0M per mm². The Intel part has no recorded transistor count, die size, or density.

Clock speeds differ significantly. The RTX 5070 Mobile has a base clock of 907 MHz and a boost clock of 1425 MHz. The Intel part runs at a 300 MHz base and boosts to 2250 MHz. Despite the higher boost clock on the Intel part, its execution resources are far smaller.

The RTX 5070 Mobile has 4,608 shading units, 144 texture mapping units, and 48 raster output pipelines. It also includes 36 ray tracing cores and 144 tensor cores. The Intel Arc Graphics 128EU Mobile has 1,024 shading units, 64 TMUs, and 32 ROPs, with no ray tracing or tensor cores recorded. The NVIDIA part delivers 13.13 TFLOPS of FP32 performance and 13.13 TFLOPS of FP16 performance in a 1:1 ratio. The Intel part delivers 4.608 TFLOPS FP32 and 9.216 TFLOPS FP16 in a 2:1 ratio. The NVIDIA part produces 205.2 GTexel/s of texture rate and 68.40 GPixel/s of pixel rate. The Intel part produces 144.0 GTexel/s and 72.00 GPixel/s, respectively.

Memory configurations are entirely different. The RTX 5070 Mobile uses 8 GB of GDDR7 on a 128-bit bus with 384.0 GB/s of bandwidth and a memory clock of 1500 MHz, 24 Gbps effective. The Intel part uses system shared memory with a system shared type and bus width, and its bandwidth is system dependent.

Power consumption differs as well. The RTX 5070 Mobile has a TDP of 50 W and no power connectors. The Intel part has a TDP of 28 W. Both are integrated graphics packages, though the RTX 5070 Mobile connects via PCIe 5.0 x16, while the Intel part uses a Ring Bus interface.

The API support also differs. The RTX 5070 Mobile supports DirectX 12 Ultimate (12_2), while the Intel part supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The NVIDIA part was released on 2025-04-14, while the Intel part was released on 2023-12-13. The NVIDIA part's predecessor is the GeForce 40 Mobile series, and the Intel part's predecessor is HD Graphics-M.

Architecture Differences

The architectural gap between these two GPUs is substantial. The NVIDIA GeForce RTX 5070 Mobile uses the Blackwell 2.0 architecture, built on TSMC's 5 nm process. The Intel Arc Graphics 128EU Mobile uses the Xe-LPG architecture, built on Intel's 10 nm process. These are fundamentally different design philosophies targeting different segments.

The NVIDIA part is a discrete-class GPU with a full complement of specialized hardware. Its 36 ray tracing cores and 144 tensor cores enable hardware-accelerated ray tracing and AI workloads, features that are absent from the Intel part's recorded specifications. The RTX 5070 Mobile's 4,608 shading units provide over four times the shader count of the Intel part's 1,024 units. This translates directly to the FP32 throughput gap: 13.13 TFLOPS versus 4.608 TFLOPS, a 2.85x difference.

The Blackwell 2.0 architecture also handles FP16 at a 1:1 ratio with FP32, meaning there is no throughput penalty for mixed-precision workloads. The Xe-LPG architecture uses a 2:1 ratio, where FP16 throughput is double FP32, which is a different design choice that can benefit certain compute tasks but does not match the balanced approach of the NVIDIA part.

Memory architecture reinforces the performance divide. The RTX 5070 Mobile's dedicated 8 GB GDDR7 pool with 384.0 GB/s of bandwidth is a discrete memory subsystem designed for sustained high-throughput workloads. The Intel part's system shared memory means its bandwidth is dependent on the host system's memory configuration, which introduces variability and potential contention with CPU workloads.

The power envelopes reflect their positioning. The RTX 5070 Mobile draws 50 W, nearly double the Intel part's 28 W. This higher power budget supports the larger shader array, dedicated RT and tensor cores, and dedicated memory interface. The Intel part's lower power draw is consistent with an integrated graphics solution designed for efficiency over peak performance.

The bus interfaces also highlight the difference. The RTX 5070 Mobile uses PCIe 5.0 x16, a high-bandwidth external interface suited for a discrete-class GPU. The Intel part uses a Ring Bus, an internal fabric connection typical of integrated graphics. This affects how each part communicates with the rest of the system, with PCIe 5.0 x16 providing substantially more bandwidth for data transfer between the GPU and CPU.

The DirectX feature levels differ as well. The RTX 5070 Mobile supports DirectX 12 Ultimate (12_2), which includes the full set of modern DirectX 12 features such as hardware ray tracing and variable rate shading. The Intel part supports DirectX 12 (12_1), a lower feature level that lacks some of these capabilities. Both support OpenGL 4.6 and Vulkan 1.4, so cross-API compatibility is similar, but the underlying hardware capabilities differ significantly.