Intel Arc A370M vs NVIDIA GeForce RTX 3070 Ti Comparison

The NVIDIA GeForce RTX 3070 Ti and Intel Arc A370M occupy entirely different performance tiers, and the data reflects a decisive victory for the desktop NVIDIA card. Across the two shared benchmark tests, the RTX 3070 Ti wins both, with an average benchmark score of 29,945 compared to the Arc A370M's 29,175. This translates to a 2.6% overall average score advantage, but the margin in raw compute workloads is far larger. The A370M, a 35 W mobile part, is not a competitor to the 290 W RTX 3070 Ti; instead, the data positions it as an entry-level mobile solution, with its nearest rivals including the AMD Radeon RX 470 and RX Vega M GH. The verdict is straightforward: the RTX 3070 Ti is for desktop gamers and creators demanding high-end performance, while the Arc A370M is for thin-and-light laptops needing modest 1080p-class capabilities.

The Verdict

The benchmark data is unambiguous: the NVIDIA GeForce RTX 3070 Ti is the superior product for any task requiring significant graphics processing power. In the Geekbench OpenCL test, the RTX 3070 Ti scores 119,718 against the Arc A370M's 29,676, a 303.4% advantage. In the Geekbench Vulkan test, the gap widens further: 139,541 versus 28,673, a 386.7% lead. These are not marginal differences; they represent a completely different performance class. The RTX 3070 Ti sits at the 75th percentile of all GPUs, while the Arc A370M is at the 74th percentile, yet this percentile similarity is misleading given the massive absolute score differences in individual tests.

Who should pick which? The RTX 3070 Ti is the clear choice for a desktop build targeting high-refresh-rate 1440p or entry-level 4K gaming, as well as GPU-accelerated rendering or compute workloads. Its 8 GB of GDDR6X memory on a 256-bit bus provides 608.3 GB/s of bandwidth, which is essential for large textures and data sets. The Arc A370M, conversely, is a mobile-only part (listed as IGP slot width) with 4 GB of GDDR6 on a 64-bit bus, yielding 112.0 GB/s. Its 35 W TDP makes it suitable for ultraportable laptops where battery life and thermals take priority over raw performance. The data shows no scenario where the A370M wins a benchmark; its only advantage is its drastically lower power envelope and physical size. For a user prioritizing mobility over frame rates, the A370M is the only option here; for anyone else, the RTX 3070 Ti is the definitive answer.

Where Each One Wins

The data provides only two head-to-head benchmark comparisons, both of which the RTX 3070 Ti wins. Therefore, the use-case split is driven by the GPUs' inherent characteristics rather than benchmark victories. The RTX 3070 Ti wins in all measured compute and graphics API tests. Its FP32 performance of 21.75 TFLOPS dwarfs the A370M's 4.198 TFLOPS, making it the obvious choice for compute-heavy applications like 3D rendering, video encoding, and scientific simulations. Its FP16 performance is also 21.75 TFLOPS (1:1 ratio), whereas the A370M offers 8.397 TFLOPS (2:1 ratio), meaning the NVIDIA card can handle half-precision workloads at full speed while the Intel card halves its throughput.

The Arc A370M's "win" is in power efficiency and form factor. At 35 W, it consumes a fraction of the RTX 3070 Ti's 290 W, making it viable for laptops without discrete power connectors (it lists none) and without a suggested PSU rating. The RTX 3070 Ti requires a 600 W PSU and a 1x 12-pin power connector. The A370M's IGP slot width means it is soldered to the motherboard, enabling ultra-thin designs. The RTX 3070 Ti is a dual-slot card measuring 267 mm in length. The data supports this split: the RTX 3070 Ti is a performance-first desktop component, while the A370M is an efficiency-first mobile component. Neither product encroaches on the other's territory.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes, explaining their divergent performance and power profiles. The RTX 3070 Ti uses the GA104 chip on NVIDIA's Ampere architecture, fabricated on Samsung's 8 nm process. It contains 17,400 million transistors on a 392 mm² die, yielding a transistor density of 44.4M per mm². In contrast, the Arc A370M uses the DG2-128 chip on Intel's Xe-HPG architecture, fabricated on TSMC's 6 nm process. It packs 7,200 million transistors on a 157 mm² die, achieving a higher density of 45.9M per mm². The smaller, denser Intel chip is a direct consequence of the more advanced 6 nm node.

The execution resources differ dramatically. The RTX 3070 Ti features 6,144 shading units, 192 TMUs, and 96 ROPs, along with 48 dedicated ray-tracing cores and 192 tensor cores. The A370M has 1,024 shading units, 64 TMUs, and 32 ROPs, with only 8 ray-tracing cores and no tensor cores listed. This 6:1 ratio in shading units and ray-tracing cores directly explains the massive compute performance gap. The NVIDIA card's pixel rate of 169.9 GPixel/s and texture rate of 339.8 GTexel/s are similarly 2.6x and 2.6x higher than the A370M's 65.60 GPixel/s and 131.2 GTexel/s, respectively.

Memory architecture is another major differentiator. The RTX 3070 Ti uses 8 GB of GDDR6X at 19 Gbps effective on a 256-bit bus, producing 608.3 GB/s bandwidth. The A370M uses 4 GB of GDDR6 at 14 Gbps effective on a 64-bit bus, producing 112.0 GB/s. The NVIDIA card has 5.4x the memory bandwidth, which is critical for high-resolution textures and data-intensive workloads. Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API-level features are identical, but the underlying hardware capabilities are vastly different.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL test?

A: The NVIDIA GeForce RTX 3070 Ti scores 119,718, which is 303.4% higher than the Intel Arc A370M's score of 29,676.

Q: How does the RTX 3070 Ti compare to the A370M in Vulkan performance?

A: The RTX 3070 Ti scores 139,541 in Geekbench Vulkan, a 386.7% advantage over the A370M's 28,673.

Q: What are the memory specifications of each GPU?

A: The RTX 3070 Ti has 8 GB of GDDR6X on a 256-bit bus with 608.3 GB/s bandwidth. The A370M has 4 GB of GDDR6 on a 64-bit bus with 112.0 GB/s bandwidth.

Q: What is the power consumption difference?

A: The RTX 3070 Ti has a TDP of 290 W, while the A370M has a TDP of 35 W. The NVIDIA card requires a 600 W PSU and a 1x 12-pin power connector; the Intel card lists no power connectors and no PSU requirement.

Q: Which GPU has more shading units?

A: The RTX 3070 Ti has 6,144 shading units, compared to the A370M's 1,024 shading units. The NVIDIA card also has 192 TMUs and 96 ROPs versus 64 TMUs and 32 ROPs.

Q: Are both GPUs end-of-life products?

A: Yes, both the NVIDIA GeForce RTX 3070 Ti and the Intel Arc A370M are listed as end-of-life in production status.

Head-to-Head Benchmarks

The shared benchmark suite between the two cards consists of exactly two tests, and the RTX 3070 Ti dominates both. The first is Geekbench OpenCL, a general-purpose compute benchmark. Here, the RTX 3070 Ti scores 119,718, while the A370M scores 29,676. The delta is 303.4%, meaning the NVIDIA card is roughly four times faster. This test stresses raw FP32 and memory throughput, where the RTX 3070 Ti's 21.75 TFLOPS and 608.3 GB/s bandwidth obliterate the A370M's 4.198 TFLOPS and 112.0 GB/s.

The second test is Geekbench Vulkan, which measures graphics API performance. The RTX 3070 Ti scores 139,541, and the A370M scores 28,673, a delta of 386.7%. This is the largest margin in either test, suggesting the NVIDIA card's advantage grows in a low-level graphics API that can fully utilize its 48 ray-tracing cores and 192 tensor cores. The A370M's 8 ray-tracing cores and lack of tensor cores limit its Vulkan throughput.

In terms of overall average benchmark score, the RTX 3070 Ti averages 29,945 across all its tested benchmarks, which is 2.6% higher than the A370M's 29,175 average. However, this aggregate number is skewed by the RTX 3070 Ti's other benchmarks (like 3DMark Steel Nomad at 3,478 and Passmark G3D at 23,356) that the A370M does not share. The head-to-head data shows a clear pattern: the RTX 3070 Ti wins both tests with deltas exceeding 300%. The A370M's nearest rival, the AMD Radeon RX 6800M, has an average score of 28,874, which is 1% lower, but that comparison is irrelevant here since the RTX 3070 Ti is 2.6% higher than the A370M's average.

Specification Differences

The following specifications differ between the two GPUs, highlighting their distinct positioning:

| Specification | NVIDIA GeForce RTX 3070 Ti | Intel Arc A370M |

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

| Chip | GA104 | DG2-128 |

| Architecture | Ampere | Xe-HPG |

| Generation | GeForce 30 | Alchemist (Arc 3 Mobile) |

| Process Node | 8 nm (Samsung) | 6 nm (TSMC) |

| Transistors | 17,400 million | 7,200 million |

| Die Size | 392 mm² | 157 mm² |

| Transistor Density | 44.4M / mm² | 45.9M / mm² |

| Base Clock | 1575 MHz | 1550 MHz |

| Boost Clock | 1770 MHz | 2050 MHz |

| Memory Clock | 1188 MHz (19 Gbps effective) | 1750 MHz (14 Gbps effective) |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR6X | GDDR6 |

| Memory Bus Width | 256 bit | 64 bit |

| Memory Bandwidth | 608.3 GB/s | 112.0 GB/s |

| Shading Units | 6144 | 1024 |

| TMUs | 192 | 64 |

| ROPs | 96 | 32 |

| Ray Tracing Cores | 48 | 8 |

| Tensor Cores | 192 | null |

| Pixel Rate | 169.9 GPixel/s | 65.60 GPixel/s |

| Texture Rate | 339.8 GTexel/s | 131.2 GTexel/s |

| FP32 Performance | 21.75 TFLOPS | 4.198 TFLOPS |

| FP16 Performance | 21.75 TFLOPS (1:1) | 8.397 TFLOPS (2:1) |

| TDP | 290 W | 35 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 12-pin | null |

| Suggested PSU | 600 W | null |

| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 1x HDMI 2.13x DisplayPort 1.4a | Portable Device Dependent |

| Dimensions | 267 mm length, 112 mm height | null |

| Release Date | 2021-05-30 | 2022-03-29 |

| Predecessor | GeForce 20 | null |

| Successor | GeForce 40 | null |

| Launch MSRP | 599 USD | null |