Intel Arc Pro B65 vs NVIDIA GeForce RTX 5090 D V2 Comparison

Intel’s Arc Pro B65 and NVIDIA’s GeForce RTX 5090 D V2 occupy very different positions in the database. The Arc Pro B65 is a professional graphics card built around the Xe2-HPG architecture, while the RTX 5090 D V2 is a high-end GeForce 50-series part using Blackwell 2.0. Their benchmark records, however, tell a more nuanced story than their specifications might suggest.

Where Each One Wins

The recorded benchmark data provides only one head-to-head measurement for the RTX 5090 D V2: a 3DMark Steel Nomad DX12 score of 16504. The Intel Arc Pro B65 has no benchmark entries in the database, meaning its average benchmark score is zero and its percentile versus all GPUs sits at 50. The RTX 5090 D V2, by comparison, achieves a percentile of 59 and an average benchmark score of 16504. Based strictly on this data, the RTX 5090 D V2 wins the only measurable performance comparison. The Arc Pro B65 cannot be declared a winner in any test because there are no recorded scores for it.

That said, the database positions the Arc Pro B65 as a 50th-percentile GPU, which implies it sits near the middle of the performance distribution across all recorded graphics cards. The RTX 5090 D V2, at the 59th percentile, sits somewhat higher. The gap between the two in percentile terms is nine points, which is modest but consistent with the RTX 5090 D V2’s higher average score. In practical terms, the Arc Pro B65 appears aimed at professional workloads requiring large memory capacity and specific API support, while the RTX 5090 D V2 is a compute-heavy card with a much higher shading-unit count.

For use-case splits, the data indicates the RTX 5090 D V2 is the stronger choice for any workload represented by the Steel Nomad DX12 test. The Arc Pro B65, with its 32 GB memory and 256-bit bus, might be intended for memory-bound professional tasks, but the database does not contain benchmark evidence to confirm that. The only definitive win belongs to the RTX 5090 D V2.

Architecture Differences

Both cards use a 5 nm process from TSMC, but their silicon is otherwise unrelated. The Arc Pro B65 is built on the BMG-G21 chip, part of Intel’s Battlemage (Pro Series) generation, and uses the Xe2-HPG architecture. The RTX 5090 D V2 uses the GB202 chip, belongs to the GeForce 50 generation, and is based on Blackwell 2.0. Transistor counts differ substantially: the Intel chip packs 19,600 million transistors on a 272 mm² die, while the NVIDIA chip contains 92,200 million transistors on a 750 mm² die. That translates to a transistor density of 72.1M per mm² for Intel and 122.9M per mm² for NVIDIA.

The RTX 5090 D V2 has 21,760 shading units, 680 texture mapping units, 176 raster output units, 170 ray tracing cores, and 680 tensor cores. The Arc Pro B65 has 2,560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores, with no tensor core count listed. Clock speeds differ as well: the Intel card runs at a base and boost of 2400 MHz, while the NVIDIA card has a 2017 MHz base and a 2407 MHz boost. Memory clocks are 2375 MHz (19 Gbps effective) for the Arc Pro B65 and 1750 MHz (28 Gbps effective) for the RTX 5090 D V2.

The architectures also differ in compute throughput. The Arc Pro B65 delivers 12.29 TFLOPS of FP32 and 24.58 TFLOPS of FP16 via a 2:1 ratio. The RTX 5090 D V2 delivers 104.8 TFLOPS of FP32 and 104.8 TFLOPS of FP16 with a 1:1 ratio. Pixel and texture rates follow the same pattern: 192.0 GPixel/s and 384.0 GTexel/s for Intel, versus 423.6 GPixel/s and 1,636.8 GTexel/s for NVIDIA. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between the Arc Pro B65 and the RTX 5090 D V2. The only relevant data point is the RTX 5090 D V2’s Steel Nomad DX12 score of 16504. That score places it near several rivals: the NVIDIA T400 scores 16508, the AMD Radeon PRO W7500 scores 16415, the NVIDIA RTX PRO 6000 Blackwell scores 16408, and the AMD Radeon RX 5700 XT scores 16361. The delta percentages show the RTX 5090 D V2 is essentially tied with the T400 (0 percent difference), 0.5 percent ahead of the Radeon PRO W7500, 0.6 percent ahead of the RTX PRO 6000 Blackwell, and 0.9 percent ahead of the Radeon RX 5700 XT.

These deltas are extremely small, indicating that the RTX 5090 D V2’s measured performance in this particular test is nearly identical to those four rivals. The Arc Pro B65 has no comparable score, so no direct delta can be calculated. What the data does show is that the RTX 5090 D V2, despite its massive shading unit count and high TFLOPS rating, does not dominate the Steel Nomad DX12 test by a wide margin. Its score is within 1 percent of four other cards, including a low-end professional card (T400) and an older gaming card (RX 5700 XT). That suggests the test may be limited by factors other than raw compute, or that the RTX 5090 D V2’s driver optimization for this workload is not fully realized.

For the Arc Pro B65, the absence of benchmark data means any comparison is speculative. The database lists its FP32 throughput at 12.29 TFLOPS, which is roughly 8.5 times lower than the RTX 5090 D V2’s 104.8 TFLOPS, but no measured score exists to confirm how that translates into real performance. The only honest conclusion from the head-to-head section is that the RTX 5090 D V2 has a recorded score and the Arc Pro B65 does not.

Specification Differences

Several specification fields differ between the two cards. Memory size is 32 GB for the Arc Pro B65 and 24 GB for the RTX 5090 D V2. Memory type is GDDR6 for Intel and GDDR7 for NVIDIA. Bus width is 256 bit for Intel and 384 bit for NVIDIA. Memory bandwidth is 608.0 GB/s for Intel and 1.34 TB/s for NVIDIA. The RTX 5090 D V2 has substantially more bandwidth, despite having less total memory.

Shading units are 2,560 versus 21,760, TMUs are 160 versus 680, ROPs are 80 versus 176, ray tracing cores are 20 versus 170, and tensor cores are absent from the Intel listing versus 680 for NVIDIA. Pixel rate is 192.0 GPixel/s versus 423.6 GPixel/s, texture rate is 384.0 GTexel/s versus 1,636.8 GTexel/s, FP32 is 12.29 TFLOPS versus 104.8 TFLOPS, and FP16 is 24.58 TFLOPS versus 104.8 TFLOPS. Thermal design power is 200 W for Intel and 575 W for NVIDIA. Power connectors are 1x 8-pin for Intel and 1x 16-pin for NVIDIA. Suggested power supply is 550 W for Intel and 950 W for NVIDIA.

Display outputs differ as well: the Arc Pro B65 has 4x DisplayPort 2.1, while the RTX 5090 D V2 has 1x HDMI 2.1b and 3x DisplayPort 2.1b. The RTX 5090 D V2 has listed physical dimensions of 304 mm in length, 137 mm in height, and 48 mm in width, while the Intel card has no dimensions recorded. Both are dual-slot cards and both use PCIe 5.0 x16 interfaces. The RTX 5090 D V2 has a launch MSRP of 2,299 USD; the Arc Pro B65 has no launch MSRP listed.

Release dates also differ: the Arc Pro B65 was released on 2026-03-31, while the RTX 5090 D V2 was released on 2025-08-14. The RTX 5090 D V2 lists its predecessor as GeForce 40 and successor as GeForce 60; the Arc Pro B65 lists no predecessor or successor. Both are marked as Active in production status.

FAQ

Q: Which card has more memory?

A: The Intel Arc Pro B65 has 32 GB of GDDR6 memory, while the NVIDIA GeForce RTX 5090 D V2 has 24 GB of GDDR7 memory.

Q: What is the benchmark score for the RTX 5090 D V2?

A: The RTX 5090 D V2 records a 3DMark Steel Nomad DX12 score of 16504, with an average benchmark score of 16504 and a percentile rank of 59.

Q: Does the Intel Arc Pro B65 have any recorded benchmark scores?

A: No, the database lists zero benchmark entries for the Arc Pro B65, an average benchmark score of 0, and a percentile rank of 50.

Q: How do the two cards compare in FP32 compute?

A: The RTX 5090 D V2 delivers 104.8 TFLOPS of FP32, while the Arc Pro B65 delivers 12.29 TFLOPS, a difference of roughly 8.5 times in favor of the NVIDIA card.

Q: What are the power requirements for each card?

A: The Arc Pro B65 has a TDP of 200 W and a suggested power supply of 550 W. The RTX 5090 D V2 has a TDP of 575 W and a suggested power supply of 950 W.

Q: Which card supports more display outputs?

A: The Arc Pro B65 has 4x DisplayPort 2.1 outputs. The RTX 5090 D V2 has 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs, for a total of four outputs as well, but with a different mix of connector types.

Q: What is the transistor count difference?

A: The Arc Pro B65 contains 19,600 million transistors on a 272 mm² die. The RTX 5090 D V2 contains 92,200 million transistors on a 750 mm² die.

Q: Are both cards built on the same process node?

A: Yes, both use a 5 nm process from TSMC, but they use different chips and architectures: Xe2-HPG for Intel and Blackwell 2.0 for NVIDIA.

Q: What is the memory bandwidth of each card?

A: The Arc Pro B65 has a bandwidth of 608.0 GB/s, while the RTX 5090 D V2 has a bandwidth of 1.34 TB/s.