AMD Radeon PRO W7700 vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The recorded data places the AMD Radeon PRO W7700 and the Intel Arc B390 in completely different performance tiers. The AMD part holds an average benchmark score of 118,976, while the Intel part sits at 1,482. That is a gap of roughly 80 times, and the percentile rankings confirm the separation: the Radeon PRO W7700 lands in the 95th percentile of all GPUs in the database, whereas the Arc B390 sits in the 9th percentile.

The benchmark results available for each card do not overlap in test type. The AMD Radeon PRO W7700 was tested under Geekbench OpenCL and Geekbench Vulkan, scoring 108,245 and 129,706 respectively. The Intel Arc B390 was tested under 3DMark Steel Nomad DX12, scoring 1,482. Because the database has no shared head-to-head benchmark between the two, direct score comparisons must rely on the aggregate average and the nearest rival data.

Looking at the nearest rivals for the AMD Radeon PRO W7700, its average score of 118,976 places it 1.3% above the NVIDIA GB10 (117,393), 1.6% above the NVIDIA RTX 4000 SFF Ada Generation (117,088), 4.0% above the NVIDIA Tesla V100 SXM2 16 GB (114,395), and 4.4% above the NVIDIA RTX A5500 Mobile (113,944). Those deltas are narrow, indicating the Radeon PRO W7700 sits in a competitive cluster of workstation-class GPUs.

For the Intel Arc B390, the nearest rivals are all entry-level NVIDIA parts. Its average score of 1,482 is 1.3% above the NVIDIA GeForce GT 520MX (1,463), 1.5% above the NVIDIA GeForce 800M (1,460), 2.5% above the NVIDIA GeForce GT 625 OEM (1,446), and 2.7% above the NVIDIA GeForce GT 710 (1,443). The small deltas again show a tight grouping, but at a much lower performance level.

The two cards are not merely separated by score; they are separated by orders of magnitude. The Radeon PRO W7700 delivers roughly 80.3 times the average benchmark score of the Arc B390, using the recorded average values of 118,976 and 1,482. That ratio is the clearest single metric in the database for understanding the performance chasm.

In raw compute terms, the AMD part reaches 31.95 TFLOPS FP32 and 63.90 TFLOPS FP16 (2:1), while the Intel part reaches 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1). The AMD card is 4.16 times faster in FP32 and 4.16 times faster in FP16, matching the ratio exactly because both architectures list the same 2:1 FP16 acceleration.

Pixel and texture rates tell a similar story. The Radeon PRO W7700 outputs 249.6 GPixel/s and 499.2 GTexel/s. The Arc B390 outputs 60.00 GPixel/s and 120.0 GTexel/s. The AMD card is 4.16 times higher in both rates, again a consistent multiplier across the board.

Where Each One Wins

The AMD Radeon PRO W7700 wins every measurable performance category in the database. It has higher FP32, higher FP16, higher pixel rate, higher texture rate, and dramatically higher average benchmark scores. Its 95th percentile ranking versus the Arc B390's 9th percentile reinforces that this is a workstation-class part intended for heavy compute and professional rendering workloads.

The Intel Arc B390 wins on efficiency and form factor. Its TDP is 80 W against the AMD card's 190 W. It uses no power connectors, while the AMD card requires one 8-pin connector. The Intel part is an integrated graphics processor (IGP) with no slot width, making it suitable for portable devices, whereas the AMD card is a dual-slot discrete card measuring 241 mm in length and 111 mm in height. The Arc B390 has no suggested PSU requirement listed, while the AMD card suggests a 450 W power supply.

The Arc B390 also wins on process node. It is built on a 3 nm process at Intel's foundry, while the Radeon PRO W7700 uses a 5 nm process at TSMC. That manufacturing advantage does not translate into performance here, but it does contribute to the lower power draw and integrated form factor.

The Radeon PRO W7700 has a release date of November 2023, while the Arc B390 is newer with a January 2026 release date. The AMD card's production status is not listed, while the Intel part is marked as active production.

Architecture Differences

The AMD Radeon PRO W7700 uses the Navi 32 chip on the RDNA 3.0 architecture, with the codename "Wheat Nas" and the generation designation "Radeon Pro Navi (Navi III Series)". The Intel Arc B390 uses the Panther Lake chip on the Xe3-LPG architecture, with the generation designation "Arc Graphics-M (Panther Lake)". The codename field for the Intel part is null.

The process nodes differ: the AMD card uses TSMC's 5 nm process, the Intel card uses Intel's 3 nm process. The AMD card has 28,100 million transistors on a 346 mm² die, yielding a transistor density of 81.2 million per mm². The Intel card's transistor count, die size, and density are all listed as unknown or null.

The AMD card has 3,072 shading units, 192 texture mapping units, 96 render output units, and 48 ray tracing cores. The Intel card has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. In every count, the AMD card has exactly double the Intel part, except for ROPs where it has four times as many.

Memory architecture differs fundamentally. The Radeon PRO W7700 has 16 GB of GDDR6 memory on a 256-bit bus, with a bandwidth of 576.0 GB/s and a memory clock of 2250 MHz (18 Gbps effective). The Arc B390 uses system shared memory, with a system-dependent bandwidth and no dedicated memory clock. The bus width is listed as system shared, meaning the Intel part relies on the host system's memory rather than dedicated VRAM.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither lists tensor cores. The AMD card uses a PCIe 4.0 x16 interface, while the Intel card is listed as IGP for its bus interface.

Specification Differences

The table below highlights only the fields where the two cards differ.

| Specification | AMD Radeon PRO W7700 | Intel Arc B390 |

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

| Chip | Navi 32 | Panther Lake |

| Architecture | RDNA 3.0 | Xe3-LPG |

| Generation | Radeon Pro Navi (Navi III Series) | Arc Graphics-M (Panther Lake) |

| Process Node | 5 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 28,100 million | unknown |

| Die Size | 346 mm² | unknown |

| Transistor Density | 81.2M / mm² | null |

| Base Clock | 1900 MHz | 300 MHz |

| Boost Clock | 2600 MHz | 2500 MHz |

| Memory Clock | 2250 MHz (18 Gbps effective) | System Shared |

| Memory Size | 16 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 256 bit | System Shared |

| Memory Bandwidth | 576.0 GB/s | System Dependent |

| Shading Units | 3072 | 1536 |

| TMUs | 192 | 48 |

| ROPs | 96 | 24 |

| RT Cores | 48 | 12 |

| Pixel Rate | 249.6 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 499.2 GTexel/s | 120.0 GTexel/s |

| FP32 | 31.95 TFLOPS | 7.680 TFLOPS |

| FP16 | 63.90 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 190 W | 80 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | null |

| Bus Interface | PCIe 4.0 x16 | IGP |

| Display Outputs | 4x DisplayPort 2.1 | Portable Device Dependent |

| Dimensions | 241 mm (9.5 inches) length, 111 mm (4.4 inches) height | null |

| Production Status | null | Active |

| Release Date | 2023-11-12 | 2026-01-26 |

| Launch MSRP | 999 USD | null |

The base clock difference is notable: 1900 MHz for the AMD card versus 300 MHz for the Intel card. Boost clocks are closer, at 2600 MHz and 2500 MHz respectively, but the AMD card still holds the advantage. The AMD card's launch MSRP is 999 USD, while the Intel part has no listed MSRP.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon PRO W7700 has an average benchmark score of 118,976, while the Intel Arc B390 has an average score of 1,482. The AMD card sits in the 95th percentile of all GPUs, while the Intel card sits in the 9th percentile.

Q: How do the FP32 compute figures compare?

A: The AMD Radeon PRO W7700 delivers 31.95 TFLOPS FP32, which is 4.16 times the Intel Arc B390's 7.680 TFLOPS FP32. The FP16 figures follow the same ratio: 63.90 TFLOPS versus 15.36 TFLOPS, both at a 2:1 rate.

Q: What are the memory configurations?

A: The AMD Radeon PRO W7700 uses 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. The Intel Arc B390 uses system shared memory, meaning its memory size, type, and bus width are all system dependent.

Q: What is the TDP of each card?

A: The AMD Radeon PRO W7700 has a TDP of 190 W and requires one 8-pin power connector with a suggested PSU of 450 W. The Intel Arc B390 has a TDP of 80 W, uses no power connectors, and has no suggested PSU listed.

Q: Which card has more ray tracing cores?

A: The AMD Radeon PRO W7700 has 48 ray tracing cores, while the Intel Arc B390 has 12. The AMD card also has 3,072 shading units versus 1,536, and 192 TMUs versus 48.

Q: What is the form factor difference?

A: The AMD Radeon PRO W7700 is a dual-slot discrete card with a PCIe 4.0 x16 interface, measuring 241 mm in length and 111 mm in height. The Intel Arc B390 is an integrated graphics processor (IGP) with no slot width, no power connectors, and a bus interface listed as IGP.

The Verdict

The data points to two entirely different product categories. The AMD Radeon PRO W7700 is a discrete workstation card for compute-heavy tasks. Its 95th percentile ranking, 118,976 average score, and 31.95 TFLOPS FP32 place it among serious professional hardware. The Intel Arc B390 is an integrated GPU for portable devices, with a 9th percentile ranking and 1,482 average score.

Anyone needing dedicated GPU performance, high bandwidth memory, or substantial compute throughput should choose the AMD Radeon PRO W7700. It has 16 GB of dedicated GDDR6, 576.0 GB/s of bandwidth, and a 4.16 times advantage in every compute rate the database records. The 999 USD launch MSRP reflects that positioning.

Anyone prioritizing low power consumption, an integrated form factor, or a newer manufacturing process should choose the Intel Arc B390. Its 80 W TDP, lack of power connectors, and 3 nm process at Intel's foundry make it suitable for systems where discrete GPUs are not an option. The Arc B390 is listed as active production, while the Radeon PRO W7700 has no production status listed.

The benchmarks do not overlap in test type, so no direct head-to-head test exists in the database. The aggregate scores and the percentile ranks are the only comparable metrics, and both overwhelmingly favor the AMD card. The Intel part matches the performance level of entry-level NVIDIA GPUs like the GeForce GT 710, while the AMD part matches workstation parts like the RTX 4000 SFF Ada Generation. The choice is not between two equals; it is between a workstation GPU and an integrated graphics solution.