Intel Arc A770M vs NVIDIA GeForce RTX 5090 D V2 Comparison

Intel Arc A770M versus NVIDIA GeForce RTX 5090 D V2 is not a contest in any measurable sense; the database records a single shared head-to-head benchmark, and the NVIDIA part wins it by a decisive margin. The RTX 5090 D V2 scores 16,504 in 3DMark Steel Nomad DX12, while the Arc A770M manages 2,278, a difference of 86.2% in favor of NVIDIA. That delta is so large that it defines the entire comparison; every other observation in this analysis is secondary to that result.

Head-to-Head Benchmarks

The only benchmark where both cards have recorded scores is 3DMark Steel Nomad DX12. The NVIDIA GeForce RTX 5090 D V2 scores 16,504, and the Intel Arc A770M scores 2,278. The delta is 86.2%, meaning the NVIDIA card outperforms the Intel part by more than seven times in this workload. No other common test exists in the dataset, so the head-to-head record stands at one win for NVIDIA and zero for Intel.

The average benchmark score for each card tells a similar story. The Arc A770M holds an average of 18,383 across its ten recorded tests, which places it in the 62nd percentile of all GPUs. The RTX 5090 D V2, based on its single recorded Steel Nomad score, has an average of 16,504 and sits in the 59th percentile. On average score alone, the Intel part appears ahead by about 1,879 points, but that is misleading: the Arc A770M's average is built from a wide range of legacy DirectX and compute tests, while the RTX 5090 D V2's average is solely the modern DX12 Steel Nomad result. When both cards run the same modern DX12 test, the NVIDIA card is 86.2% ahead.

The nearest rivals in the database reinforce how different these two products are. The Arc A770M's closest competitors are the AMD Radeon RX 460 (average 18,373, 0.1% behind), the AMD FirePro D500 (18,533, 0.8% ahead), the AMD Radeon Pro 5700 (18,189, 1.1% behind), and the NVIDIA GeForce RTX 3060 Mobile (18,159, 1.2% behind). The RTX 5090 D V2 sits next to the NVIDIA T400 (16,508, 0.0% delta), the AMD Radeon PRO W7500 (16,415, 0.5% behind), the NVIDIA RTX PRO 6000 Blackwell (16,408, 0.6% behind), and the AMD Radeon RX 5700 XT (16,361, 0.9% behind). The Intel card competes with mid-range mobile and older workstation parts; the NVIDIA card's neighbors are prosumer and workstation accelerators, despite its lower percentile ranking.

The Verdict

The data is unambiguous. The NVIDIA GeForce RTX 5090 D V2 is the stronger GPU by every measure that matters for modern rendering. Its 86.2% lead in the shared DX12 benchmark dwarfs any other consideration. The Intel Arc A770M is an end-of-life mobile part with a 62nd percentile standing; the RTX 5090 D V2 is an active desktop flagship with a 59th percentile standing, but that percentile is based on a single test that is far more demanding than the legacy workloads in the Arc's average.

Who should pick which? A user running modern DX12 workloads, ray tracing, or high-resolution rendering should choose the RTX 5090 D V2 without hesitation. The 16,504 Steel Nomad score versus 2,278 is not a marginal advantage; it is a generational chasm. The Arc A770M, by contrast, only makes sense for someone constrained to its form factor (it is an integrated-class mobile part) or its power envelope (120 W versus 575 W), and even then the performance gap is enormous. The database shows no scenario where the Arc A770M wins a shared test, so the verdict is simple: the RTX 5090 D V2 wins outright.

FAQ

Q: Which GPU wins the only benchmark they share?

A: The NVIDIA GeForce RTX 5090 D V2 wins 3DMark Steel Nomad DX12 with a score of 16,504 against the Intel Arc A770M's 2,278, a delta of 86.2% in NVIDIA's favor.

Q: How do their average benchmark scores compare?

A: The Intel Arc A770M has an average benchmark score of 18,383 across ten tests. The NVIDIA GeForce RTX 5090 D V2 has an average of 16,504 from a single test. The Intel card's average is higher, but the NVIDIA card wins the only test both have taken.

Q: What are the closest rivals to each card in the database?

A: The Arc A770M's nearest rival is the AMD Radeon RX 460 (18,373 average, 0.1% delta). The RTX 5090 D V2's nearest rival is the NVIDIA T400 (16,508 average, 0.0% delta).

Q: Which card has the higher percentile ranking among all GPUs?

A: The Intel Arc A770M ranks in the 62nd percentile, while the NVIDIA GeForce RTX 5090 D V2 ranks in the 59th percentile.

Q: Is the RTX 5090 D V2 still in production?

A: Yes, its production status is active. The Intel Arc A770M is listed as end-of-life.

Q: Does the RTX 5090 D V2 have more memory?

A: Yes. The RTX 5090 D V2 has 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. The Arc A770M has 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth.

Specification Differences

The two GPUs differ in nearly every specification. The NVIDIA GeForce RTX 5090 D V2 uses the GB202 chip on a 5 nm process, while the Intel Arc A770M uses the DG2-512 chip on a 6 nm process. The NVIDIA card has 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9M per mm². The Intel card has 21,700 million transistors on a 406 mm² die, for a density of 53.4M per mm².

Clock speeds also diverge sharply. The Arc A770M runs at a 1650 MHz base and 2050 MHz boost. The RTX 5090 D V2 runs at a 2017 MHz base and 2407 MHz boost. Memory clocks differ as well: the Intel part uses 2000 MHz with 16 Gbps effective, while the NVIDIA part uses 1750 MHz with 28 Gbps effective.

Compute resources are not comparable in scale. The Arc A770M has 4,096 shading units, 256 TMUs, 128 ROPs, and 32 ray tracing cores. The RTX 5090 D V2 has 21,760 shading units, 680 TMUs, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. The throughput figures follow: the Intel card delivers 262.4 GPixel/s, 524.8 GTexel/s, 16.79 TFLOPS FP32, and 33.59 TFLOPS FP16 (2:1). The NVIDIA card delivers 423.6 GPixel/s, 1,636.8 GTexel/s, 104.8 TFLOPS FP32, and 104.8 TFLOPS FP16 (1:1).

Power and physical design differ completely. The Arc A770M is rated at 120 W, uses an IGP slot width, and has no listed power connector or suggested PSU. The RTX 5090 D V2 is rated at 575 W, uses a dual-slot design, requires a 1x 16-pin power connector, and suggests a 950 W power supply. The bus interface also differs: PCIe 4.0 x16 for Intel, PCIe 5.0 x16 for NVIDIA. Display outputs on the NVIDIA card are 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the Intel card lists portable device dependent outputs. The NVIDIA card has physical dimensions of 304 mm length, 137 mm height, and 48 mm width; the Intel card lists none. The NVIDIA card was released on 2025-08-14 with a 2,299 USD launch MSRP; the Intel card has no release date or MSRP in the database.

Architecture Differences

The architectural gap is generational. The Intel Arc A770M is built on Xe-HPG, specifically the Alchemist generation for Arc 7 Mobile. The NVIDIA GeForce RTX 5090 D V2 is Blackwell 2.0 in the GeForce 50 series. The Intel chip is DG2-512; the NVIDIA chip is GB202. Both are fabricated by TSMC, but on different nodes: 6 nm for Intel, 5 nm for NVIDIA.

Memory architecture is another major split. The Arc A770M uses 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The RTX 5090 D V2 uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. The NVIDIA card has more than double the memory bandwidth, which directly supports its higher fill rates and compute throughput.

Ray tracing and tensor hardware reflect the generational divide. The Arc A770M has 32 ray tracing cores and no tensor core count listed. The RTX 5090 D V2 has 170 ray tracing cores and 680 tensor cores. The FP16 ratio also differs: the Intel card runs FP16 at 2:1 relative to FP32, while the NVIDIA card runs it at 1:1. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is not a differentiator.

The production status differs: the Arc A770M is end-of-life, while the RTX 5090 D V2 is active. The NVIDIA part has a predecessor (GeForce 40) and a successor (GeForce 60); the Intel part lists neither.

Where Each One Wins

The NVIDIA GeForce RTX 5090 D V2 wins the only shared test, 3DMark Steel Nomad DX12, by 86.2%. That makes it the clear choice for any modern DX12 workload: high-fidelity gaming, ray tracing, or GPU compute that scales with tensor cores. Its 104.8 TFLOPS FP32 and 104.8 TFLOPS FP16, along with 1.34 TB/s memory bandwidth, put it in a different performance class. The 24 GB GDDR7 frame buffer supports large datasets and high-resolution textures. Its active production status and desktop form factor (dual-slot, 304 mm length) suit a workstation or high-end desktop build.

The Intel Arc A770M wins no shared benchmarks, but the database does show areas where it is not without merit. Its average benchmark score of 18,383 is higher than the RTX 5090 D V2's 16,504, driven by strong results in legacy tests: 178 in PassMark DirectX 9, 70 in DirectX 12, 69 in DirectX 11, 11,774 in PassMark G3D, 89,494 in Geekbench OpenCL, and 74,422 in Geekbench Vulkan. In raw compute terms, those Geekbench numbers are respectable for a 120 W mobile part. The 16 GB GDDR6 frame buffer and 512.0 GB/s bandwidth are adequate for 1080p and 1440p gaming in its era. The 120 W TDP and IGP slot width make it suitable for thin mobile systems where the 575 W, dual-slot NVIDIA card physically cannot fit.

The use-case split is therefore stark. For desktop users who can supply a 950 W PSU and a dual-slot PCIe 5.0 slot, the RTX 5090 D V2 is the only rational choice from the data. For mobile users who need a 120 W integrated-class GPU and can tolerate end-of-life status, the Arc A770M exists, but the performance gap in the shared DX12 test is so large that no workload analysis can recommend it over the NVIDIA card when both are available. The database records one winner, and it is NVIDIA by 86.2%.