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

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark results between the Intel Arc Graphics 128EU Mobile and the NVIDIA GeForce RTX 5070 SUPER. The Intel part has no benchmark entries in the database, while the RTX 5070 SUPER has a single recorded score. This absence of overlapping tests means a direct comparison of measured performance cannot be established from the database.

What can be analyzed is the RTX 5070 SUPER's standing relative to its nearest rivals. Its single benchmark result, a 3DMark Steel Nomad DX12 score of 2690, places it just ahead of the NVIDIA Quadro K1100M, which scored 2664, a delta of 1%. The GeForce GT 1030 follows at 2662, also a 1.1% gap. The Intel Arc Pro B50 sits at 2660, a 1.1% difference, and the NVIDIA GeForce GT 440 trails at 2645, a 1.7% margin. These are extremely tight margins, indicating that in this particular test, the RTX 5070 SUPER does not demonstrate a commanding lead over its closest competitors; it leads by single percentage points.

The RTX 5070 SUPER's percentile standing among all GPUs in the database is 18, which means it ranks below the majority of recorded graphics processors. The Intel Arc Graphics 128EU Mobile, by contrast, has a percentile of 50, placing it exactly at the median of all GPUs in the database. This disparity in percentile is notable: the Intel integrated part sits at the midpoint of all recorded GPUs, while the RTX 5070 SUPER, despite its high-end positioning in terms of specifications, ranks in the lower fifth of the database. The Intel part's percentile is derived from its position relative to all GPUs, not from any recorded benchmarks, as its average benchmark score is 0. The RTX 5070 SUPER's average benchmark score is 2690, matching its single Steel Nomad result.

The lack of head-to-head data means no statement can be made about which part wins in any specific workload. The only quantitative comparison available is the RTX 5070 SUPER's narrow lead over its four nearest rivals, all within 1.7%. The Intel part's 50th percentile suggests it is statistically average within the database's full GPU population, but without benchmark scores, its actual performance relative to the RTX 5070 SUPER cannot be quantified.

Architecture Differences

The two processors belong to entirely different categories. The Intel Arc Graphics 128EU Mobile is an integrated graphics processor (IGP) built on the Meteor Lake chip, using the Xe-LPG architecture and a 10 nm process node from Intel's own foundry. The NVIDIA GeForce RTX 5070 SUPER is a discrete, dual-slot add-in board from the GeForce 50-series, built on the GB205 chip with the Blackwell 2.0 architecture, manufactured by TSMC on a 5 nm node.

Transistor counts and die sizes differ drastically. The RTX 5070 SUPER packs 31,100 million transistors into a 263 mm² die, yielding a transistor density of 118.3 million per square millimeter. The Intel part has no recorded transistor count, die size, or density figures in the database. The process node advantage belongs to NVIDIA, as 5 nm is a smaller feature size than 10 nm, but the Intel part is an integrated solution where the GPU shares the package with other components.

Execution resources show a significant imbalance. The Intel Arc Graphics 128EU Mobile has 1024 shading units, 64 texture mapping units, and 32 raster output pipelines. The RTX 5070 SUPER has 6400 shading units, 200 TMUs, and 80 ROPs. NVIDIA's part also includes 50 ray tracing cores and 200 tensor cores, while the Intel part lists neither, indicating no dedicated RT or tensor hardware in the recorded data.

Clock speeds differ substantially. Intel's IGP runs at a base clock of 300 MHz and boosts to 2250 MHz. NVIDIA's discrete GPU has a base clock of 2325 MHz and a boost of 2512 MHz. The memory subsystems are fundamentally different: the Intel part uses system-shared memory with a system-dependent bandwidth, while the RTX 5070 SUPER has 18 GB of dedicated GDDR7 memory on a 192-bit bus, delivering 672.0 GB/s of bandwidth. The Intel part's memory clock is listed as "System Shared" with no dedicated speed.

Compute throughput figures highlight the scale gap. The Intel part delivers 4.608 TFLOPS of FP32 performance and 9.216 TFLOPS of FP16 with a 2:1 ratio. The RTX 5070 SUPER delivers 32.15 TFLOPS of FP32 and 32.15 TFLOPS of FP16 at a 1:1 ratio. Pixel and texture rates follow the same pattern: Intel achieves 72.00 GPixel/s and 144.0 GTexel/s, while NVIDIA achieves 201.0 GPixel/s and 502.4 GTexel/s.

Power consumption is another stark divider. The Intel IGP has a TDP of 28 W and uses a Ring Bus interface with no power connectors. The RTX 5070 SUPER has a TDP of 275 W, uses a PCIe 5.0 x16 interface, and requires a single 16-pin power connector. Physical dimensions reflect the discrete nature of the NVIDIA card: 245 mm long, 115 mm high, and 40 mm wide. The Intel part has no recorded dimensions.

API support differs in DirectX version. Both support OpenGL 4.6 and Vulkan 1.4. The Intel part supports DirectX 12 (12_1), while the RTX 5070 SUPER supports DirectX 12 Ultimate (12_2), a higher feature level. Display outputs also differ: Intel's outputs are listed as "Portable Device Dependent," reflecting its integrated nature, while NVIDIA provides 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Release timing is far apart. The Intel part launched on December 13, 2023, while the RTX 5070 SUPER's release date is recorded as December 31, 2025. The Intel part's predecessor is listed as HD Graphics-M, while the NVIDIA part has no predecessor recorded. Both are marked as Active in production status.

Where Each One Wins

The RTX 5070 SUPER wins on nearly every measurable specification in the database. In raw compute, it offers 32.15 TFLOPS FP32 versus 4.608 TFLOPS, a 6.98x advantage. Its 672.0 GB/s memory bandwidth dwarfs the system-dependent bandwidth of the Intel part, and its 18 GB dedicated GDDR7 capacity eliminates the contention that comes with shared system memory. The 200 tensor cores and 50 RT cores give it dedicated hardware for AI acceleration and ray tracing that the Intel part entirely lacks. Its 6400 shading units, 200 TMUs, and 80 ROPs provide a massive resource advantage for geometry and texture work.

The Intel Arc Graphics 128EU Mobile wins on power efficiency and integration. Its 28 W TDP is dramatically lower than the 275 W TDP of the RTX 5070 SUPER. It requires no power connectors, no PCIe slot, and no additional physical space beyond the host device, as its display outputs are portable-device dependent. For systems where power draw and physical footprint are primary constraints, the Intel part is the only viable option among the two.

The Intel part's 50th percentile ranking versus the RTX 5070 SUPER's 18th percentile presents an interesting contradiction: by database standing, the Intel IGP is better positioned among all GPUs, even though it has no recorded benchmark scores. This likely reflects the database's inclusion of many low-end mobile and embedded parts, against which the Intel IGP is median, while the RTX 5070 SUPER's single Steel Nomad score places it low due to the test's demands or the limited data available.

For gaming workloads that require high sustained throughput, the RTX 5070 SUPER's specifications indicate superiority. For ultraportable laptops and low-power devices where the GPU is integrated into the main processor and shares system memory, the Intel part is the intended solution. The data does not support any claim that the Intel part outperforms the RTX 5070 SUPER in any recorded benchmark, because no Intel benchmarks exist in the database.

FAQ

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

A: No. The database lists an average benchmark score of 0 for the Intel part, and its benchmarks array is empty. Its 50th percentile standing is derived from its position relative to all GPUs in the database, not from any individual test results.

Q: What is the RTX 5070 SUPER's best recorded benchmark result?

A: Its only recorded result is a 3DMark Steel Nomad DX12 score of 2690, which also serves as its average benchmark score. This places it 1% ahead of the NVIDIA Quadro K1100M, which scored 2664.

Q: How much faster is the RTX 5070 SUPER than the Intel Arc Graphics 128EU Mobile in FP32 compute?

A: The RTX 5070 SUPER delivers 32.15 TFLOPS of FP32 performance, while the Intel part delivers 4.608 TFLOPS. This is a 6.98x difference in favor of the NVIDIA part.

Q: Which part has more memory bandwidth?

A: The RTX 5070 SUPER has 672.0 GB/s of dedicated bandwidth from its 18 GB GDDR7 memory on a 192-bit bus. The Intel part uses system-shared memory with bandwidth listed as "System Dependent," meaning the database records no fixed figure.

Q: What is the power consumption difference?

A: The Intel Arc Graphics 128EU Mobile has a TDP of 28 W, while the RTX 5070 SUPER has a TDP of 275 W. The NVIDIA part also requires a 16-pin power connector, while the Intel IGP uses no power connectors.

Q: Do both parts support the same DirectX version?

A: No. The Intel part supports DirectX 12 (12_1), while the RTX 5070 SUPER supports DirectX 12 Ultimate (12_2), a higher feature level. Both support OpenGL 4.6 and Vulkan 1.4.

Specification Differences

| Specification | Intel Arc Graphics 128EU Mobile | NVIDIA GeForce RTX 5070 SUPER |

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

| Architecture | Xe-LPG | Blackwell 2.0 |

| Process Node | 10 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | Not recorded | 31,100 million |

| Die Size | Not recorded | 263 mm² |

| Transistor Density | Not recorded | 118.3M / mm² |

| Base Clock | 300 MHz | 2325 MHz |

| Boost Clock | 2250 MHz | 2512 MHz |

| Memory Size | System Shared | 18 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 192 bit |

| Memory Bandwidth | System Dependent | 672.0 GB/s |

| Memory Clock | System Shared | 1750 MHz 28 Gbps effective |

| Shading Units | 1024 | 6400 |

| TMUs | 64 | 200 |

| ROPs | 32 | 80 |

| RT Cores | Not recorded | 50 |

| Tensor Cores | Not recorded | 200 |

| Pixel Rate | 72.00 GPixel/s | 201.0 GPixel/s |

| Texture Rate | 144.0 GTexel/s | 502.4 GTexel/s |

| FP32 | 4.608 TFLOPS | 32.15 TFLOPS |

| FP16 | 9.216 TFLOPS (2:1) | 32.15 TFLOPS (1:1) |

| TDP | 28 W | 275 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 16-pin |

| Bus Interface | Ring Bus | PCIe 5.0 x16 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| DirectX | 12 (12_1) | 12 Ultimate (12_2) |

| Dimensions | Not recorded | 245 mm x 115 mm x 40 mm |

| Release Date | 2023-12-13 | 2025-12-31 |

| Predecessor | HD Graphics-M | Not recorded |

| Percentile | 50 | 18 |

The Verdict

The data supports a clear split based on use case. The NVIDIA GeForce RTX 5070 SUPER is the superior performer by every recorded specification: 6.98x more FP32 throughput, 7x more shading units, 2.5x more ROPs, dedicated ray tracing and tensor hardware, a dedicated 18 GB GDDR7 memory pool with 672.0 GB/s bandwidth, and a DirectX 12 Ultimate feature level. Its 275 W TDP and dual-slot physical footprint are the costs of that performance, and its 18th percentile ranking reflects its limited benchmark presence rather than its specification sheet.

The Intel Arc Graphics 128EU Mobile is the appropriate choice for systems where the 28 W TDP, integrated form factor, and absence of discrete power requirements are mandatory constraints. Its 50th percentile standing suggests it is a median performer among all database GPUs, but with no recorded benchmarks, its real-world performance cannot be substantiated. The RTX 5070 SUPER, despite its lower percentile, has a verified benchmark score that places it marginally ahead of several older discrete GPUs.

Users who need maximum compute throughput, dedicated VRAM, and modern API features should select the RTX 5070 SUPER. Users constrained to integrated graphics in portable devices should use the Intel part, as the RTX 5070 SUPER cannot be installed in such configurations. The recorded data offers no scenario where the Intel part outperforms the RTX 5070 SUPER, but it also offers no scenario where the RTX 5070 SUPER could replace an integrated solution.