Intel Arc B370 vs NVIDIA GeForce RTX 5080 Comparison

Two very different graphics products appear in the same database comparison: the Intel Arc B370, an integrated GPU from Intel's Arc Graphics-M (Panther Lake) generation, and the NVIDIA GeForce RTX 5080, a discrete card from the GeForce 50-series. The recorded data shows only one shared benchmark, 3DMark Steel Nomad DX12, and in that test the NVIDIA part scores 8637 against 1184 for the Intel part. The Arc B370 sits at the 5th percentile of all GPUs, while the RTX 5080 sits at the 87th percentile. Their average benchmark scores, 1184 and 56083, frame the scale of the comparison.

Head-to-Head Benchmarks

3DMark Steel Nomad DX12 is the sole common benchmark. The RTX 5080 wins with 8637, and the Arc B370 records 1184. The delta is -86.3%, so the Intel part trails by 86.3% of the NVIDIA result. There are no other head-to-head tests in the database for this pair. The win count is 0 for Intel and 1 for NVIDIA.

The RTX 5080's average score of 56083 places it near AMD Radeon RX 9070 GRE (57367, -2.2), AMD Radeon 8060S (55757, 0.6), AMD Radeon RX 6750 GRE 12 GB (55698, 0.7), and AMD Radeon Pro W5700X (54828, 2.3). The delta values show the RTX 5080 sits 0.6% ahead of the AMD Radeon 8060S, 0.7% ahead of the RX 6750 GRE 12 GB, 2.3% ahead of the Pro W5700X, and 2.2% behind the RX 9070 GRE.

The Arc B370's average score of 1184 places it near ATI Mobility Radeon HD 5570 (1186, -0.2), ATI Radeon HD 5770 (1190, -0.5), AMD Radeon HD 7650M (1192, -0.7), and AMD FirePro M2000 (1168, 1.4). That means the Intel part is 0.2% behind ATI Mobility Radeon HD 5570, 0.5% behind ATI Radeon HD 5770, 0.7% behind AMD Radeon HD 7650M, and 1.4% ahead of AMD FirePro M2000. These nearest-rival positions show that the RTX 5080 competes in a much higher performance band.

FAQ

Q: Which GPU wins the only recorded head-to-head benchmark?

A: The NVIDIA GeForce RTX 5080 wins 3DMark Steel Nomad DX12 with a score of 8637. The Intel Arc B370 scores 1184, producing a -86.3% delta for the Intel part.

Q: What memory configurations do the two GPUs use?

A: The Arc B370 uses system-shared memory with a system-shared type, bus width, and system-dependent bandwidth. The RTX 5080 uses 16 GB of GDDR7 on a 256-bit bus with 960.0 GB/s bandwidth and a memory clock of 1875 MHz 30 Gbps effective.

Q: How do their power and physical requirements differ?

A: The Arc B370 has a 25 W TDP, an IGP slot width, and no power connectors. The RTX 5080 has a 360 W TDP, a dual-slot width, one 16-pin power connector, and a suggested PSU of 750 W.

Q: Do they support the same graphics APIs?

A: Yes. Both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: How do the compute resources compare?

A: The Arc B370 has 1280 shading units, 40 texture mapping units, 20 ROPs, and 10 ray tracing cores. The RTX 5080 has 10752 shading units, 336 TMUs, 112 ROPs, 84 ray tracing cores, and 336 tensor cores. The Arc B370 has no tensor core count in the database.

Q: Where does each part rank among all GPUs?

A: The Arc B370 is at the 5th percentile with an average benchmark score of 1184. The RTX 5080 is at the 87th percentile with an average benchmark score of 56083.

Architecture Differences

The two parts come from different manufacturing and design lineages. The Arc B370 uses the Panther Lake chip with Xe3-LPG architecture on Intel's 3 nm process at Intel foundry. The RTX 5080 uses the GB203 chip with Blackwell 2.0 architecture on TSMC's 5 nm process. The Arc B370 is part of the Arc Graphics-M (Panther Lake) generation; the RTX 5080 belongs to the GeForce 50 generation and the GeForce 50-series. The RTX 5080 carries 45,600 million transistors on a 378 mm² die with 120.6M / mm² density. The Arc B370's transistor count and die size are unknown.

The compute blocks differ in scale. The Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The RTX 5080 has 10752 shading units, 336 TMUs, 112 ROPs, 84 RT cores, and 336 tensor cores. The FP32 throughput is 6.144 TFLOPS for the Arc B370 and 56.28 TFLOPS for the RTX 5080. The FP16 throughput is 12.29 TFLOPS (2:1) for the Intel part and 56.28 TFLOPS (1:1) for the NVIDIA part. Pixel fill rates are 48.00 GPixel/s and 293.1 GPixel/s; texture fill rates are 96.00 GTexel/s and 879.3 GTexel/s.

Memory architecture is another separator. The Arc B370 relies on system-shared memory with system-dependent bandwidth. The RTX 5080 has a dedicated 16 GB GDDR7 frame buffer on a 256-bit bus with 960.0 GB/s. The RTX 5080 also has a memory clock of 1875 MHz 30 Gbps effective, while the Arc B370's memory clock is listed as System Shared.

Physical integration differs as well. The Arc B370 is an IGP with no power connector and a 25 W TDP. The RTX 5080 is a dual-slot card with a 360 W TDP, one 16-pin power connector, a suggested PSU of 750 W, and a PCIe 5.0 x16 interface. The Arc B370's display outputs are portable-device-dependent; the RTX 5080 lists 1x HDMI 2.1b, 3x DisplayPort 2.1b.

Specification Differences

The following table lists the fields where the database records differ.

| Field | Intel Arc B370 | NVIDIA GeForce RTX 5080 |

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

| Series | not listed | GeForce 50-series |

| Manufacturer | Intel | NVIDIA |

| Chip | Panther Lake | GB203 |

| Architecture | Xe3-LPG | Blackwell 2.0 |

| Generation | Arc Graphics-M (Panther Lake) | GeForce 50 |

| Process node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | unknown | 45,600 million |

| Die size | unknown | 378 mm² |

| Transistor density | not listed | 120.6M / mm² |

| Base clock | 300 MHz | 2295 MHz |

| Boost clock | 2400 MHz | 2617 MHz |

| Memory clock | System Shared | 1875 MHz 30 Gbps effective |

| Memory size | System Shared | 16 GB |

| Memory type | System Shared | GDDR7 |

| Memory bus width | System Shared | 256 bit |

| Memory bandwidth | System Dependent | 960.0 GB/s |

| Shading units | 1280 | 10752 |

| TMUs | 40 | 336 |

| ROPs | 20 | 112 |

| RT cores | 10 | 84 |

| Tensor cores | not listed | 336 |

| Pixel rate | 48.00 GPixel/s | 293.1 GPixel/s |

| Texture rate | 96.00 GTexel/s | 879.3 GTexel/s |

| FP32 | 6.144 TFLOPS | 56.28 TFLOPS |

| FP16 | 12.29 TFLOPS (2:1) | 56.28 TFLOPS (1:1) |

| TDP | 25 W | 360 W |

| Slot width | IGP | Dual-slot |

| Power connectors | None | 1x 16-pin |

| Suggested PSU | not listed | 750 W |

| Bus interface | IGP | PCIe 5.0 x16 |

| Display outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | not listed | 304 mm 12 inches, 137 mm 5.4 inches, 40 mm 1.6 inches |

| Release date | 2026-01-26T17:00:00.000Z | 2025-01-29T17:00:00.000Z |

| Predecessor | not listed | GeForce 40 |

| Successor | not listed | GeForce 60 |

| Launch MSRP | not listed | 999 USD |

Where Each One Wins

The benchmark record is lopsided. The RTX 5080 holds the only win in the shared 3DMark Steel Nomad DX12 test, and the Arc B370 has zero wins. That makes the NVIDIA part the winner for the workload captured by that benchmark. The Arc B370's role is defined by its integrated nature: IGP slot width, 25 W TDP, no power connectors, system-shared memory, and portable-device-dependent display outputs. The RTX 5080's role is defined by its discrete design: dual-slot, 360 W TDP, 1x 16-pin connector, 750 W suggested PSU, 16 GB GDDR7, and PCIe 5.0 x16 interface.

The nearest-rival data reinforces the split. The Arc B370 sits with ATI Mobility Radeon HD 5570 (1186, -0.2), ATI Radeon HD 5770 (1190, -0.5), AMD Radeon HD 7650M (1192, -0.7), and AMD FirePro M2000 (1168, 1.4). The RTX 5080 sits with AMD Radeon 8060S (55757, 0.6), AMD Radeon RX 6750 GRE 12 GB (55698, 0.7), AMD Radeon Pro W5700X (54828, 2.3), and AMD Radeon RX 9070 GRE (57367, -2.2). The RTX 5080's average benchmark score is 56083, while the Arc B370's average is 1184.

The Verdict

The recorded data leads to a clear split. For a system that can supply 360 W over a 16-pin connector, fit a dual-slot card, and provide a 750 W suggested PSU, the RTX 5080 delivers the 8637 Steel Nomad score, a 56083 average benchmark score, and the 87th percentile ranking. For a system that needs an integrated GPU with no power connector, an IGP slot width, and system-shared memory, the Arc B370 is the only one of the two that fits; its recorded performance is 1184 in Steel Nomad, a 1184 average, and the 5th percentile ranking.

The RTX 5080 wins the only head-to-head benchmark. The Arc B370 wins none. The architecture and specification differences explain why: the NVIDIA part uses a larger chip, dedicated 16 GB GDDR7, 10752 shading units, 84 RT cores, and 336 tensor cores, while the Intel part is a 25 W integrated GPU with 1280 shading units and 10 RT cores. The database offers no contradiction to that result.