Intel Arc B570 vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The recorded data presents an unusual comparison: the Intel Arc B570 has a complete set of benchmark scores, while the NVIDIA GeForce RTX 5090 SE has no recorded benchmarks in the database. This means the head-to-head comparison is one-sided, with the Arc B570 holding all recorded performance data.

The Arc B570 scores 2649 in 3DMark Steel Nomad DX12, 83514 in Geekbench OpenCL, and 96844 in Geekbench Vulkan. In Passmark tests, it records 65 in DirectX 10, 118 in DirectX 11, 72 in DirectX 12, and 164 in DirectX 9. The Passmark G2D score is 661, while the G3D score is 14195, and the GPU compute score is 7281.

Its average benchmark score is 20556, placing it in the 65th percentile among all GPUs in the database. The nearest rivals show a tight cluster: the NVIDIA GeForce RTX 3070 Mobile averages 20534 (0.1% behind the Arc B570), the Intel Arc A750 averages 20582 (0.1% ahead), the NVIDIA Quadro M4000M averages 20480 (0.4% behind), and the AMD Radeon R9 M390X averages 20662 (0.5% ahead). These margins are negligible, indicating the Arc B570 sits in a densely packed performance tier.

The RTX 5090 SE, by contrast, has zero recorded benchmarks and an average score of zero, placing it in the 50th percentile by default. With no test data, the database cannot establish any direct performance relationship between these two cards. The wins counter shows zero wins for either side.

FAQ

Q: What benchmark scores does the Intel Arc B570 have?

A: The Arc B570 has ten recorded scores: 2649 in 3DMark Steel Nomad DX12, 83514 in Geekbench OpenCL, 96844 in Geekbench Vulkan, 65 in Passmark DirectX 10, 118 in Passmark DirectX 11, 72 in Passmark DirectX 12, 164 in Passmark DirectX 9, 661 in Passmark G2D, 14195 in Passmark G3D, and 7281 in Passmark GPU compute.

Q: Does the NVIDIA GeForce RTX 5090 SE have any benchmark results?

A: No. The database lists an empty benchmarks array for the RTX 5090 SE, with an average benchmark score of zero and no nearest rivals recorded.

Q: How does the Arc B570 compare to its nearest rivals?

A: The Arc B570 averages 20556, which is 0.1% above the RTX 3070 Mobile (20534), 0.1% below the Arc A750 (20582), 0.4% above the Quadro M4000M (20480), and 0.5% below the Radeon R9 M390X (20662).

Q: What is the percentile ranking for each card?

A: The Arc B570 sits in the 65th percentile among all GPUs, while the RTX 5090 SE sits in the 50th percentile, though the latter reflects the absence of recorded performance data rather than actual measured performance.

Q: What memory configurations do the two cards use?

A: The Arc B570 uses 10 GB of GDDR6 on a 160-bit bus with 380.0 GB/s bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth.

Q: What are the power requirements listed for each card?

A: The Arc B570 has a TDP of 150 W with a suggested PSU of 450 W and a single 8-pin connector. The RTX 5090 SE has a TDP of 500 W with a suggested PSU of 900 W and a single 16-pin connector.

Architecture Differences

The two GPUs represent fundamentally different design scales. The Intel Arc B570 uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage generation within the Arc 5 lineup. It is manufactured by TSMC on a 5 nm process, containing 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1M per mm².

The NVIDIA GeForce RTX 5090 SE uses the GB202 chip built on the Blackwell 2.0 architecture, part of the GeForce 50 series. It is also manufactured by TSMC on a 5 nm process but contains 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9M per mm². The RTX 5090 SE packs 4.7 times the transistor count and 2.8 times the die area of the Arc B570.

Compute resources differ sharply. The Arc B570 has 2304 shading units, 144 texture mapping units, and 80 ROPs, with 18 ray tracing cores and no tensor cores listed. The RTX 5090 SE has 14080 shading units, 440 TMUs, and 160 ROPs, with 110 ray tracing cores and 440 tensor cores. The NVIDIA card delivers 66.94 TFLOPS of FP32 and FP16 performance at a 1:1 ratio, while the Intel card delivers 11.52 TFLOPS FP32 and 23.04 TFLOPS FP16 at a 2:1 ratio.

Clock behavior differs as well. The Arc B570 runs at a fixed 2500 MHz for both base and boost. The RTX 5090 SE has a 1740 MHz base clock and a 2377 MHz boost clock, indicating a wider frequency range under load. Memory clocks also differ: the Arc B570 uses 2375 MHz memory (19 Gbps effective), while the RTX 5090 SE uses 1750 MHz memory (28 Gbps effective).

Pixel and texture rates reflect the resource disparity. The Arc B570 achieves 200.0 GPixel/s and 360.0 GTexel/s. The RTX 5090 SE achieves 380.3 GPixel/s and 1,045.9 GTexel/s. The NVIDIA card more than doubles the pixel throughput and nearly triples the texture throughput.

The bus interface differs: the Arc B570 uses PCIe 4.0 x8, while the RTX 5090 SE uses PCIe 5.0 x16, providing four times the lane count on a newer standard. Display outputs also differ, with the Arc B570 offering 1x HDMI 2.1a and 3x DisplayPort 2.1, while the RTX 5090 SE offers 1x HDMI 2.1b and 3x DisplayPort 2.1b. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Physical dimensions show the Arc B570 at 272 mm length and 115 mm height, while the RTX 5090 SE measures 267 mm length, 111 mm height, and 40 mm width. Both are dual-slot cards. The Arc B570 was released on 2025-01-15, while the RTX 5090 SE has a release date of 2025-12-31. The Arc B570 lists Alchemist as its predecessor, while the RTX 5090 SE lists GeForce 40 as predecessor and GeForce 60 as successor.

The Verdict

The data supports a straightforward selection for users who require measured performance: the Intel Arc B570 has verified benchmark results across multiple tests, while the NVIDIA GeForce RTX 5090 SE has none recorded in the database. For any workload where a score must be cited, the Arc B570 is the only option with empirical evidence.

The RTX 5090 SE, however, presents overwhelming architectural advantages on paper. Its 14080 shading units versus 2304, its 66.94 TFLOPS FP32 versus 11.52 TFLOPS, its 24 GB GDDR7 memory versus 10 GB GDDR6, and its 1.34 TB/s bandwidth versus 380.0 GB/s all indicate a far larger compute and memory resource pool. The 110 ray tracing cores and 440 tensor cores versus 18 ray tracing cores and no tensor cores further separate the two in feature capability.

The average benchmark score of 20556 for the Arc B570 places it in the 65th percentile, a respectable position. The RTX 5090 SE's 50th percentile is a placeholder figure derived from zero scores, not a performance measurement. Users needing immediate, verifiable results should look to the Arc B570. Users whose workloads demand the massive compute and memory resources described in the specification data should recognize that the RTX 5090 SE, pending any benchmark results, is designed for a categorically different performance level.

The absence of head-to-head benchmark data means no direct performance comparison exists. The database records zero wins for either card. Selection must therefore rest on either the available measured scores (favoring the Arc B570) or the architectural specifications (favoring the RTX 5090 SE). The launch MSRP for the Arc B570 is 219 USD, while the RTX 5090 SE has a launch MSRP of 1,499 USD.

Specification Differences

| Field | Intel Arc B570 | NVIDIA GeForce RTX 5090 SE |

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

| Chip | BMG-G21 | GB202 |

| Architecture | Xe2-HPG | Blackwell 2.0 |

| Generation | Battlemage (Arc 5) | GeForce 50 |

| Transistors | 19,600 million | 92,200 million |

| Die Size | 272 mm² | 750 mm² |

| Transistor Density | 72.1M / mm² | 122.9M / mm² |

| Base Clock | 2500 MHz | 1740 MHz |

| Boost Clock | 2500 MHz | 2377 MHz |

| Memory Clock | 2375 MHz (19 Gbps effective) | 1750 MHz (28 Gbps effective) |

| Memory Size | 10 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus Width | 160 bit | 384 bit |

| Memory Bandwidth | 380.0 GB/s | 1.34 TB/s |

| Shading Units | 2304 | 14080 |

| TMUs | 144 | 440 |

| ROPs | 80 | 160 |

| RT Cores | 18 | 110 |

| Tensor Cores | None listed | 440 |

| Pixel Rate | 200.0 GPixel/s | 380.3 GPixel/s |

| Texture Rate | 360.0 GTexel/s | 1,045.9 GTexel/s |

| FP32 | 11.52 TFLOPS | 66.94 TFLOPS |

| FP16 | 23.04 TFLOPS (2:1) | 66.94 TFLOPS (1:1) |

| TDP | 150 W | 500 W |

| Power Connectors | 1x 8-pin | 1x 16-pin |

| Suggested PSU | 450 W | 900 W |

| Bus Interface | PCIe 4.0 x8 | PCIe 5.0 x16 |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | 272 mm x 115 mm | 267 mm x 111 mm x 40 mm |

| Release Date | 2025-01-15 | 2025-12-31 |

| Predecessor | Alchemist | GeForce 40 |

| Successor | None listed | GeForce 60 |

| Launch MSRP | 219 USD | 1,499 USD |

| Production Status | Active | Active |

Both cards share the same process node (5 nm), foundry (TSMC), slot width (dual-slot), DirectX version (12 Ultimate 12_2), OpenGL version (4.6), and Vulkan version (1.4). The Arc B570 lists no successor, while the RTX 5090 SE lists GeForce 60 as its successor. The Arc B570 has no series designation, while the RTX 5090 SE belongs to the GeForce 50-series. Neither card lists a game clock or codename in the database.