Intel Arc B570 vs NVIDIA GeForce RTX 2080 SUPER Comparison

Head-to-Head Benchmarks

The benchmark data presents a clear split between these two cards. The NVIDIA GeForce RTX 2080 SUPER wins 9 of the 10 recorded tests, while the Intel Arc B570 takes a single, decisive victory in the newest DX12 workload.

The most striking result is in 3DMark Steel Nomad DX12. The Intel Arc B570 scores 2649 against the RTX 2080 SUPER's 1882, a 29% advantage. This is the only test where Intel leads, but it is a significant one, as Steel Nomad represents modern DirectX 12 gaming workloads. This suggests the Arc B570's architecture handles contemporary rendering paths more efficiently than the older Turing design.

Outside of that single test, the RTX 2080 SUPER dominates. In PassMark G3D, the NVIDIA card scores 19490 versus 14195, a 37.3% lead. The gap widens further in legacy DirectX tests: PassMark DX10 shows a 115.4% advantage (140 vs 65), and PassMark DX9 shows a 38.4% lead (227 vs 164). The RTX 2080 SUPER also wins PassMark DX11 by 39.8% (165 vs 118) and edges out the Arc B570 in DX12 by a narrower 4.2% (75 vs 72).

Compute workloads tell a similar story. In Geekbench OpenCL, the RTX 2080 SUPER scores 99226 against 83514, an 18.8% margin. Geekbench Vulkan shows a 14.9% lead (111284 vs 96844). PassMark GPU Compute favors NVIDIA by 13.9% (8290 vs 7281). Even the 2D test, PassMark G2D, goes to the RTX 2080 SUPER with a 39.2% advantage (920 vs 661).

The average benchmark scores reflect this overall trend. The RTX 2080 SUPER carries an average score of 24170, placing it at the 69th percentile of all GPUs. Its nearest rivals include the GTX 780 Ti (24236, 0.3% lower), the GTX 1630 (24277, 0.4% lower), and the RX 6800S (24063, 0.4% higher). The Arc B570's average score sits at 20556, good for the 65th percentile, with the RTX 3070 Mobile (20534, 0.1% lower) and Arc A750 (20582, 0.1% higher) as its closest competitors. The 24170 vs 20556 gap translates to roughly a 17.6% overall advantage for the NVIDIA card in average score.

FAQ

Q: Which card is faster in modern DirectX 12 games?

A: The Intel Arc B570 wins 3DMark Steel Nomad DX12 by 29% (2649 vs 1882), indicating a clear advantage in this current-generation DX12 workload. However, in PassMark DX12 the RTX 2080 SUPER still leads, albeit by a smaller 4.2% margin.

Q: How do the two cards compare in legacy DirectX performance?

A: The RTX 2080 SUPER is substantially faster in older APIs. It leads by 115.4% in DX10, 39.8% in DX11, and 38.4% in DX9. This makes it the better choice for older game libraries and applications that rely on legacy rendering paths.

Q: Which card has better compute performance?

A: The RTX 2080 SUPER wins all recorded compute tests. It leads by 18.8% in Geekbench OpenCL, 14.9% in Geekbench Vulkan, and 13.9% in PassMark GPU Compute. The margin is consistent across both OpenCL and Vulkan compute workloads.

Q: What is the overall performance percentile of each card?

A: The RTX 2080 SUPER sits at the 69th percentile of all GPUs with an average benchmark score of 24170. The Arc B570 ranks at the 65th percentile with an average score of 20556. The NVIDIA card occupies a higher overall position in the database rankings.

Q: Which card has more VRAM?

A: The Intel Arc B570 has 10 GB of GDDR6 memory, while the RTX 2080 SUPER has 8 GB. However, the RTX 2080 SUPER has a wider 256-bit memory bus and higher bandwidth at 495.9 GB/s, compared to the Arc B570's 160-bit bus and 380.0 GB/s.

Q: Which card is more power efficient?

A: The Arc B570 has a 150 W TDP and a suggested 450 W PSU, while the RTX 2080 SUPER has a 250 W TDP and a suggested 600 W PSU. The Intel card draws less power and requires a less substantial power supply, despite delivering competitive performance in the Steel Nomad test.

Architecture Differences

The two cards come from completely different architectural generations and design philosophies. The RTX 2080 SUPER uses the TU104 chip built on Turing architecture, manufactured by TSMC on a 12 nm process. It packs 13,600 million transistors into a 545 mm² die, resulting in a transistor density of 25.0M per mm². The Arc B570 uses the BMG-G21 chip on Intel's Xe2-HPG architecture, also built by TSMC but on a 5 nm node. It contains 19,600 million transistors in a much smaller 272 mm² die, achieving a density of 72.1M per mm². The smaller, denser process node is a major generational advantage for Intel.

Shader configuration differs significantly. The RTX 2080 SUPER has 3072 shading units, 192 TMUs, and 64 ROPs. The Arc B570 has fewer shading units at 2304, fewer TMUs at 144, but more ROPs at 80. Despite fewer shaders, the Arc B570 achieves slightly higher FP32 throughput at 11.52 TFLOPS versus 11.15 TFLOPS for the NVIDIA card, thanks to its higher clock speeds. The Arc B570 also leads in pixel rate at 200.0 GPixel/s versus 116.2 GPixel/s, and texture rate at 360.0 GTexel/s versus 348.5 GTexel/s.

Ray tracing and AI hardware tell a different story. The RTX 2080 SUPER includes 48 RT cores and 384 tensor cores, reflecting NVIDIA's early investment in dedicated ray tracing and tensor processing. The Arc B570 has 18 RT cores and no listed tensor cores. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature coverage is comparable on paper, but the underlying hardware implementations differ substantially.

Memory configurations also diverge. The RTX 2080 SUPER uses 8 GB of GDDR6 on a 256-bit bus with 495.9 GB/s bandwidth. The Arc B570 offers 10 GB of GDDR6 on a 160-bit bus with 380.0 GB/s bandwidth. The NVIDIA card has superior memory bandwidth, while the Intel card has more total capacity. Clock behavior differs too: the RTX 2080 SUPER runs at a 1650 MHz base and 1815 MHz boost, while the Arc B570 runs at a flat 2500 MHz for both base and boost, indicating a fixed-clock design.

The bus interface also differs. The RTX 2080 SUPER uses PCIe 3.0 x16, while the Arc B570 uses PCIe 4.0 x8. In practical terms, the newer PCIe 4.0 standard offers more bandwidth per lane, which partially compensates for the reduced lane count. Display outputs also differ: the NVIDIA card offers 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C, while the Intel card offers 1x HDMI 2.1a and 3x DisplayPort 2.1, providing a more modern display interface set.

The Verdict

The data supports a straightforward conclusion. The RTX 2080 SUPER is the faster card across the majority of recorded benchmarks, winning 9 of 10 tests and holding a 17.6% average score advantage (24170 vs 20556). It is particularly strong in legacy DirectX workloads, compute tasks, and 2D performance, where its margins range from 13.9% to 115.4%. The Arc B570's single victory in 3DMark Steel Nomad DX12, while impressive at 29%, does not offset the NVIDIA card's broad dominance elsewhere.

However, the Arc B570 is not without merit. Its 29% lead in Steel Nomad suggests better optimization for modern DX12 rendering pipelines, and its 10 GB VRAM capacity exceeds the RTX 2080 SUPER's 8 GB. The Intel card also carries a lower 150 W TDP and requires only a 450 W PSU, compared to 250 W and 600 W for the NVIDIA card. The Arc B570 is also an active production card with a listed launch MSRP of 219 USD, while the RTX 2080 SUPER is end-of-life with a launch MSRP of 699 USD.

For users prioritizing raw performance across a wide range of workloads, particularly older games and compute applications, the RTX 2080 SUPER is the clear choice from the data. For users focused on current-generation DX12 titles, lower power draw, and more VRAM capacity, the Arc B570 presents a compelling case. The RTX 2080 SUPER also places higher in overall percentile ranking at 69 versus 65, reinforcing its position as the stronger all-round performer.

Specification Differences

| Specification | NVIDIA GeForce RTX 2080 SUPER | Intel Arc B570 |

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

| Process Node | 12 nm | 5 nm |

| Transistors | 13,600 million | 19,600 million |

| Die Size | 545 mm² | 272 mm² |

| Transistor Density | 25.0M / mm² | 72.1M / mm² |

| Base Clock | 1650 MHz | 2500 MHz |

| Boost Clock | 1815 MHz | 2500 MHz |

| Memory Size | 8 GB | 10 GB |

| Memory Bus | 256 bit | 160 bit |

| Memory Bandwidth | 495.9 GB/s | 380.0 GB/s |

| Shading Units | 3072 | 2304 |

| TMUs | 192 | 144 |

| ROPs | 64 | 80 |

| RT Cores | 48 | 18 |

| Tensor Cores | 384 | None listed |

| FP32 | 11.15 TFLOPS | 11.52 TFLOPS |

| FP16 | 22.30 TFLOPS (2:1) | 23.04 TFLOPS (2:1) |

| Pixel Rate | 116.2 GPixel/s | 200.0 GPixel/s |

| Texture Rate | 348.5 GTexel/s | 360.0 GTexel/s |

| TDP | 250 W | 150 W |

| Power Connectors | 1x 6-pin + 1x 8-pin | 1x 8-pin |

| Suggested PSU | 600 W | 450 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C | 1x HDMI 2.1a, 3x DisplayPort 2.1 |

| Production Status | End-of-life | Active |

| Release Date | 2019-07-22 | 2025-01-15 |

Where Each One Wins

The RTX 2080 SUPER wins in the majority of scenarios. Its strongest categories are legacy DirectX performance, where DX10, DX11, and DX9 margins range from 38.4% to 115.4%. It also wins compute workloads across OpenCL, Vulkan, and GPU compute tests, with margins between 13.9% and 18.8%. PassMark G3D and G2D results add to its lead, with 37.3% and 39.2% advantages respectively. Even in PassMark DX12, the NVIDIA card maintains a 4.2% edge. Users running older game libraries, productivity apps with OpenCL compute, or general 3D rendering workloads will find the RTX 2080 SUPER consistently faster.

The Arc B570 wins specifically in 3DMark Steel Nomad DX12, where its 29% lead indicates a real strength in modern DirectX 12 rendering. This makes it the better pick for current-generation games that follow the latest rendering techniques. Its 10 GB VRAM capacity also gives it more headroom for texture-heavy workloads at higher resolutions, even though its bandwidth is lower at 380.0 GB/s versus 495.9 GB/s. The Arc B570 additionally offers lower power consumption at 150 W TDP and a reduced 450 W PSU requirement, making it the more efficient option for compact or power-conscious builds. Its active production status and newer release date, along with modern DisplayPort 2.1 and HDMI 2.1a outputs, make it the more forward-looking choice for new system builds.