Intel Arc B770 vs NVIDIA GeForce RTX 5090 D Comparison

Where Each One Wins

The data presents a stark contrast between these two GPUs. The Intel Arc B770 holds the 50th percentile among all GPUs in the database, while the NVIDIA GeForce RTX 5090 D sits at the 92nd percentile. The Arc B770 has no recorded benchmark scores, no average score, and no nearest rivals in the database. The RTX 5090 D, by contrast, has ten recorded benchmark scores across multiple test suites, an average benchmark score of 77712, and a set of four nearest rivals that it outpaces or trails by narrow margins.

The RTX 5090 D wins every recorded benchmark category. It shows dominance in compute-oriented workloads with a Geekbench OpenCL score of 310674 and a Geekbench Vulkan score of 376915. Its PassMark G3D score of 44065 and PassMark GPU Compute score of 28396 further confirm strength across both graphics and general compute tasks. The Arc B770 has zero wins in the head-to-head comparison, which is the only outcome possible given the absence of any benchmark entries for it.

The use-case split is therefore one-sided in the recorded data. The RTX 5090 D handles DirectX 12 workloads well, as indicated by its 3DMark Steel Nomad DX12 score of 14326. It also covers legacy DirectX paths through PassMark DirectX 9, 10, 11, and 12 scores of 434, 231, 371, and 219 respectively. The PassMark G2D score of 1487 shows 2D throughput, while the compute scores cover OpenCL and Vulkan paths. For the Arc B770, no such distinctions can be made from the database because no test results exist.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc B770 uses the Xe2-HPG architecture with the BMG-G31 chip, belonging to the Battlemage generation in the Arc 7 family. Its predecessor is Alchemist. The NVIDIA GeForce RTX 5090 D uses the Blackwell 2.0 architecture with the GB202 chip, belonging to the GeForce 50 series and generation. Its predecessor is GeForce 40 and its successor is GeForce 60.

Both are built on a 5 nm process at TSMC, but the similarities end there. The Arc B770 has a die size of 368 mm² with transistor count listed as unknown. The RTX 5090 D has a die size of 750 mm² with 92,200 million transistors and a transistor density of 122.9M per mm². The Arc B770 has no transistor density recorded.

Memory architecture differs substantially. The Arc B770 uses 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The RTX 5090 D uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. Clock behavior also differs: the Arc B770 runs a base clock of 2100 MHz and a boost of 2400 MHz with memory at 2000 MHz (16 Gbps effective), while the RTX 5090 D runs a base of 2017 MHz and a boost of 2407 MHz with memory at 1750 MHz (28 Gbps effective).

Compute resources are heavily skewed toward the NVIDIA part. The Arc B770 has 4096 shading units, 256 TMUs, 128 ROPs, 32 ray tracing cores, and no tensor cores listed. The RTX 5090 D has 21760 shading units, 680 TMUs, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. Pixel rate for the Arc B770 is 307.2 GPixel/s versus 423.6 GPixel/s for the RTX 5090 D. Texture rate is 614.4 GTexel/s versus 1,636.8 GTexel/s. FP32 throughput is 19.66 TFLOPS versus 104.8 TFLOPS. FP16 is 39.32 TFLOPS (2:1) for Intel versus 104.8 TFLOPS (1:1) for NVIDIA.

Power and connectivity also diverge. The Arc B770 has a TDP of 225 W with a suggested PSU of 550 W and uses one 6-pin plus one 8-pin power connector. The RTX 5090 D has a TDP of 575 W with a suggested PSU of 950 W and uses a single 16-pin connector. Both are dual-slot cards. The Arc B770 uses PCIe 4.0 x16 while the RTX 5090 D uses PCIe 5.0 x16. Display outputs are similar: the Arc B770 has one HDMI 2.1a and three DisplayPort 2.1, while the RTX 5090 D has one HDMI 2.1b and three DisplayPort 2.1b. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

No head-to-head benchmark results exist in the database for these two cards, so a direct score-by-score comparison cannot be made. However, the RTX 5090 D has its own benchmark scores, and these can be examined against its nearest rivals to establish its performance position.

The RTX 5090 D has an average benchmark score of 77712. Its nearest rival, the AMD Radeon RX 6650M XT, has an average score of 76904, which places the RTX 5090 D 1.1% ahead. The AMD Radeon RX 6850M XT scores 78940, putting the RTX 5090 D 1.6% behind. The NVIDIA Tesla P100 PCIe 12 GB scores 79396, a 2.1% deficit for the RTX 5090 D. The NVIDIA Tesla P100 PCIe 16 GB scores 79605, a 2.4% deficit. The RTX 5090 D therefore sits in a tight cluster with these four rivals, within roughly two and a half percentage points in either direction.

The individual benchmark scores for the RTX 5090 D show a clear pattern. The Geekbench Vulkan score of 376915 exceeds the OpenCL score of 310674, indicating strong Vulkan performance relative to OpenCL on this card. The 3DMark Steel Nomad DX12 score of 14326 represents the only modern DirectX 12 gaming benchmark in the set. PassMark results show a G3D score of 44065 against a GPU Compute score of 28396, meaning graphics throughput outpaces compute throughput in that suite. Legacy DirectX scores are lower, with DirectX 9 at 434, DirectX 11 at 371, DirectX 10 at 231, and DirectX 12 at 219. The G2D score of 1487 is the highest PassMark subscore, though it measures 2D operations rather than 3D rendering.

The Arc B770 has no comparable data. Its average benchmark score is 0, its percentile is 50, and it has no nearest rivals. The database contains no evidence of its performance relative to the RTX 5090 D or any other GPU.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce RTX 5090 D has an average benchmark score of 77712. The Intel Arc B770 has an average benchmark score of 0, as no benchmark results are recorded for it.

Q: How does the RTX 5090 D compare to its nearest rivals?

A: The RTX 5090 D is 1.1% ahead of the AMD Radeon RX 6650M XT, 1.6% behind the AMD Radeon RX 6850M XT, 2.1% behind the NVIDIA Tesla P100 PCIe 12 GB, and 2.4% behind the NVIDIA Tesla P100 PCIe 16 GB.

Q: What memory configurations do the two GPUs use?

A: The Intel Arc B770 uses 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The NVIDIA GeForce RTX 5090 D uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth.

Q: What are the power requirements for each card?

A: The Arc B770 has a TDP of 225 W and a suggested PSU of 550 W. The RTX 5090 D has a TDP of 575 W and a suggested PSU of 950 W.

Q: Which GPU has more ray tracing cores?

A: The NVIDIA GeForce RTX 5090 D has 170 ray tracing cores. The Intel Arc B770 has 32 ray tracing cores.

Q: What is the FP32 throughput of each GPU?

A: The Intel Arc B770 delivers 19.66 TFLOPS of FP32 performance. The NVIDIA GeForce RTX 5090 D delivers 104.8 TFLOPS of FP32 performance.

Specification Differences

The two GPUs differ across nearly every recorded specification. The chip designations are different: BMG-G31 for Intel versus GB202 for NVIDIA. The architectures differ, Xe2-HPG versus Blackwell 2.0, and the generations differ, Battlemage (Arc 7) versus GeForce 50. The production status for the Arc B770 is not listed, while the RTX 5090 D is marked Active.

Die size is 368 mm² for the Arc B770 and 750 mm² for the RTX 5090 D. Transistor count is unknown for the Intel part and 92,200 million for the NVIDIA part. Transistor density is not recorded for Intel and 122.9M per mm² for NVIDIA.

Clock speeds differ in both base and boost. The Arc B770 runs at 2100 MHz base and 2400 MHz boost. The RTX 5090 D runs at 2017 MHz base and 2407 MHz boost. Memory clocks are 2000 MHz with 16 Gbps effective for Intel versus 1750 MHz with 28 Gbps effective for NVIDIA.

Memory size, type, bus width, and bandwidth all differ: 16 GB GDDR6 on 256-bit at 512.0 GB/s versus 32 GB GDDR7 on 512-bit at 1.79 TB/s. Shading units, TMUs, and ROPs differ heavily: 4096, 256, and 128 for Intel versus 21760, 680, and 176 for NVIDIA. Ray tracing cores are 32 versus 170. Tensor cores are not listed for Intel and 680 for NVIDIA.

Pixel rate is 307.2 GPixel/s versus 423.6 GPixel/s. Texture rate is 614.4 GTexel/s versus 1,636.8 GTexel/s. FP32 is 19.66 TFLOPS versus 104.8 TFLOPS. FP16 is 39.32 TFLOPS (2:1) versus 104.8 TFLOPS (1:1). TDP is 225 W versus 575 W. Power connectors are 1x 6-pin plus 1x 8-pin versus 1x 16-pin. Suggested PSU is 550 W versus 950 W. Bus interface is PCIe 4.0 x16 versus PCIe 5.0 x16.

Display outputs differ slightly: HDMI 2.1a with DisplayPort 2.1 for Intel versus HDMI 2.1b with DisplayPort 2.1b for NVIDIA. The RTX 5090 D has recorded dimensions of 304 mm by 137 mm by 48 mm, while the Arc B770 has none. Release dates differ, with the Arc B770 listed for 2025-12-31 and the RTX 5090 D for 2025-01-29. The RTX 5090 D has a launch MSRP of 2,299 USD; the Arc B770 has no launch MSRP recorded. The RTX 5090 D lists GeForce 60 as its successor, while the Arc B770 lists no successor.

The Verdict

The recorded data supports only one conclusion for measured performance: the NVIDIA GeForce RTX 5090 D is the only one of the two with any benchmark results, and those results place it at the 92nd percentile among all GPUs. Its average benchmark score of 77712 puts it in a competitive cluster with its nearest rivals, ranging from 1.1% ahead of the AMD Radeon RX 6650M XT to 2.4% behind the NVIDIA Tesla P100 PCIe 16 GB. Its individual scores show strong Vulkan and OpenCL compute performance, solid DirectX 12 capability, and substantial GPU compute throughput.

The Intel Arc B770 cannot be evaluated on measured performance because the database contains no benchmark entries for it. Its specification sheet shows a smaller chip, 368 mm² versus 750 mm², fewer shading units, 4096 versus 21760, less memory, 16 GB versus 32 GB, and lower bandwidth, 512.0 GB/s versus 1.79 TB/s. Its FP32 throughput of 19.66 TFLOPS is roughly one fifth of the RTX 5090 D's 104.8 TFLOPS. Its TDP of 225 W is less than half of the RTX 5090 D's 575 W, and its suggested PSU of 550 W is well below the 950 W required for the NVIDIA card.

For users choosing strictly from the data, the RTX 5090 D is the only option with verified performance records. It delivers measured results across multiple benchmark suites, holds a high percentile rank, and offers 32 GB of GDDR7 memory with 1.79 TB/s bandwidth. The Arc B770 offers lower power draw and a smaller physical footprint in unspecified dimensions, but no performance evidence exists to support any claim of competitive capability. The verdict follows the data: the RTX 5090 D is the measured performer, while the Arc B770 remains an unverified specification sheet.