Intel Arc Pro B390 vs NVIDIA GeForce RTX 5060 Ti 16 GB Comparison
Intel Arc Pro B390
GeForce RTX 5060 Ti 16 GB
PERFORMANCE BENCHMARKS
Analysis: Intel Arc Pro B390 vs NVIDIA GeForce RTX 5060 Ti 16 GB
Head-to-Head Benchmarks
The recorded data for the Intel Arc Pro B390 contains no benchmark scores, while the NVIDIA GeForce RTX 5060 Ti 16 GB has a full set of measurements. This means every direct comparison relies on the NVIDIA card’s results and the Intel part’s theoretical specifications.
The RTX 5060 Ti 16 GB posts a 3DMark Steel Nomad DX12 score of 4019. Its Passmark G3D score is 22618, and its Passmark GPU Compute score is 11224. The older DirectX APIs show smaller numbers: Passmark DirectX 10 scores 144, DirectX 11 scores 219, DirectX 9 scores 238, and DirectX 12 scores 89. The 2D portion, Passmark G2D, reaches 1206.
Since the Intel Arc Pro B390 has no benchmark entries in the database, its average benchmark score is 0, and it holds a percentile rank of 50 among all GPUs. The RTX 5060 Ti 16 GB, by contrast, has an average benchmark score of 4970 and sits at the 29th percentile. The Intel part’s theoretical peak FP32 throughput is 7.680 TFLOPS, while the NVIDIA card delivers 23.70 TFLOPS, a difference of roughly three times in raw floating-point compute. Texture rate tells a similar story: the Intel part reaches 120.0 GTexel/s, the NVIDIA card reaches 370.4 GTexel/s. Pixel rate is 60.00 GPixel/s for Intel versus 123.5 GPixel/s for NVIDIA.
The RTX 5060 Ti 16 GB’s nearest rivals in the database are all lower-tier parts. The NVIDIA Quadro 4000 averages 4979, which is 0.2% above the RTX card. The AMD Radeon R7 Graphics averages 4998, 0.6% above. The AMD Radeon R7 M360 averages 4931, which is 0.8% below. The AMD Radeon R7 M265 also averages 4929, again 0.8% below. These deltas are tiny, meaning the RTX 5060 Ti 16 GB sits in a very narrow performance band relative to those older or integrated parts, despite its much higher raw specifications.
In the absence of Intel benchmark data, the comparison is one-sided. The RTX 5060 Ti 16 GB has measurable wins in every recorded test, but the Intel Arc Pro B390 has no recorded wins at all because no tests exist for it in the database.
The Verdict
From the data alone, the NVIDIA GeForce RTX 5060 Ti 16 GB is the only part with benchmark evidence. It shows 23.70 TFLOPS FP32, 370.4 GTexel/s, and 123.5 GPixel/s, with a Passmark G3D score of 22618. The Intel Arc Pro B390 provides no measured scores, so any claim about its real-world performance is unsupported by the database.
The Intel part targets a different role entirely. It is an integrated graphics processor (IGP) with a 3 nm process, 80 W TDP, and system-shared memory. Its bus interface is IGP, and it uses no power connectors. The NVIDIA card is a dual-slot discrete GPU with 16 GB of GDDR7 on a 128-bit bus, 448.0 GB/s bandwidth, a 180 W TDP, and a single 8-pin power connector. These are fundamentally different product classes.
For a user who needs a discrete card with dedicated memory and proven benchmark results, the RTX 5060 Ti 16 GB is the clear choice. For a system that relies on integrated graphics, the Arc Pro B390 could be the only option, but the database contains no measurements to validate its performance. The RTX card’s percentile rank of 29 versus the Intel part’s rank of 50 is misleading without Intel scores; the rank likely reflects the absence of data rather than actual performance.
The RTX 5060 Ti 16 GB also has a launch MSRP of 429 USD, which is the only pricing data available. The Intel part has no launch MSRP listed.
Where Each One Wins
The RTX 5060 Ti 16 GB wins in every category where measurements exist. In compute-heavy workloads, its FP32 throughput of 23.70 TFLOPS and FP16 throughput of 23.70 TFLOPS (1:1) show balanced performance. The Intel Arc Pro B390 offers FP16 at 15.36 TFLOPS (2:1), which is higher than its FP32 rate but still below the NVIDIA card’s FP16 figure.
Memory bandwidth is another clear win. The RTX card has 448.0 GB/s from 16 GB of GDDR7 on a 128-bit bus. The Intel part has system-shared memory with bandwidth described as system dependent, so no fixed number exists. Discrete memory versus shared memory is a structural advantage for NVIDIA.
The RTX card also has more execution resources: 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. The Intel part has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores, with no tensor cores listed. These counts directly explain the texture and pixel rate differences.
The Intel Arc Pro B390 has one unique advantage: it is an IGP with a 3 nm process and 80 W TDP. It requires no power connectors and fits in a portable device dependent display configuration. For low-power or compact systems, this is a meaningful difference, but it is not a performance win in any recorded benchmark.
FAQ
Q: Does the Intel Arc Pro B390 have any benchmark scores in the database?
A: No. The Intel part has an empty benchmark list, an average benchmark score of 0, and no nearest rivals recorded.
Q: What is the RTX 5060 Ti 16 GB’s best benchmark result?
A: Its Passmark G3D score of 22618 is the highest single test result. The 3DMark Steel Nomad DX12 score is 4019, and Passmark GPU Compute is 11224.
Q: How do the two cards compare in FP32 performance?
A: The Intel Arc Pro B390 delivers 7.680 TFLOPS FP32, while the RTX 5060 Ti 16 GB delivers 23.70 TFLOPS, roughly three times higher.
Q: What memory configuration does each card use?
A: The Intel part uses system-shared memory with system dependent bandwidth. The RTX card uses 16 GB of GDDR7 on a 128-bit bus with 448.0 GB/s bandwidth.
Q: Which card has more ray tracing cores?
A: The RTX 5060 Ti 16 GB has 36 RT cores; the Intel Arc Pro B390 has 12 RT cores.
Q: Are there any rivals close to the RTX 5060 Ti 16 GB in average score?
A: Yes. The NVIDIA Quadro 4000 is 0.2% above, the AMD Radeon R7 Graphics is 0.6% above, and the AMD Radeon R7 M360 and R7 M265 are each 0.8% below.
Architecture Differences
The Intel Arc Pro B390 uses the Panther Lake chip with Xe3-LPG architecture, built on Intel’s 3 nm process. It belongs to the Arc Graphics-WM generation and is listed as a successor to HD Graphics-WM. It has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores. There are no tensor cores listed. Its FP16 rate is 15.36 TFLOPS with a 2:1 ratio, meaning FP16 runs at twice the FP32 rate. The part supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
The NVIDIA GeForce RTX 5060 Ti 16 GB uses the GB206 chip with Blackwell 2.0 architecture, built on a 5 nm process at TSMC. It has 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. Its FP16 rate is 23.70 TFLOPS with a 1:1 ratio, matching FP32. It also supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The transistor count is 21,900 million on a 181 mm² die, giving a density of 121.0M per mm².
The Intel part has no tensor cores, which means no dedicated AI acceleration hardware is listed. The NVIDIA card’s 144 tensor cores provide a structural advantage for workloads that use them, though no benchmark in the database directly tests tensor performance.
The Intel part’s memory is entirely system shared, with no dedicated VRAM. The RTX card has 16 GB of GDDR7. This is the largest architectural gap: one part depends on system memory bandwidth, the other has a fixed 448.0 GB/s.
Specification Differences
The two parts differ on every specification field except the API list. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
| Specification | Intel Arc Pro B390 | NVIDIA GeForce RTX 5060 Ti 16 GB |
| --- | --- | --- |
| Process node | 3 nm | 5 nm |
| Foundry | Intel | TSMC |
| Transistors | unknown | 21,900 million |
| Die size | unknown | 181 mm² |
| Base clock | 300 MHz | 2407 MHz |
| Boost clock | 2500 MHz | 2572 MHz |
| Memory size | System Shared | 16 GB |
| Memory type | System Shared | GDDR7 |
| Memory bus | System Shared | 128 bit |
| Memory bandwidth | System Dependent | 448.0 GB/s |
| Shading units | 1536 | 4608 |
| TMUs | 48 | 144 |
| ROPs | 24 | 48 |
| RT cores | 12 | 36 |
| Tensor cores | null | 144 |
| Pixel rate | 60.00 GPixel/s | 123.5 GPixel/s |
| Texture rate | 120.0 GTexel/s | 370.4 GTexel/s |
| FP32 | 7.680 TFLOPS | 23.70 TFLOPS |
| FP16 | 15.36 TFLOPS (2:1) | 23.70 TFLOPS (1:1) |
| TDP | 80 W | 180 W |
| Slot width | IGP | Dual-slot |
| Power connectors | None | 1x 8-pin |
| Suggested PSU | null | 450 W |
| Bus interface | IGP | PCIe 5.0 x8 |
| Display outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |
| Release date | 2026-01-26 | 2025-04-15 |
| Predecessor | HD Graphics-WM | GeForce 40 |
| Successor | null | GeForce 60 |
| Launch MSRP | null | 429 USD |
The clock speeds show a large gap: the Intel part idles at 300 MHz and boosts to 2500 MHz, while the NVIDIA card runs at 2407 MHz base and 2572 MHz boost. The Intel part’s low base clock reflects its integrated, low-power design. The RTX card’s higher clocks, combined with more execution units, produce the measured performance advantage.
The physical form factors are opposites. The Intel part is an IGP with no slot width, no power connectors, and portable device dependent display outputs. The RTX card is a dual-slot, 241 mm long, 111 mm tall, 40 mm wide board with a single 8-pin connector and a 450 W suggested PSU. The release dates also differ: the Intel part is dated 2026-01-26, while the NVIDIA card is dated 2025-04-15. The RTX card’s predecessor is GeForce 40, and its successor is GeForce 60. The Intel part’s predecessor is HD Graphics-WM, with no successor listed.