Intel Arc B370 vs NVIDIA GeForce RTX 5080 SUPER Comparison

FAQ

Q: How do the Intel Arc B370 and NVIDIA GeForce RTX 5080 SUPER compare in the 3DMark Steel Nomad DX12 benchmark?

A: The recorded data shows the NVIDIA GeForce RTX 5080 SUPER scores 3075, while the Intel Arc B370 scores 1184. The NVIDIA card leads by 61.5 percent in this test.

Q: What are the respective percentile rankings for these two GPUs?

A: The Intel Arc B370 sits at the 5th percentile among all GPUs in the database, while the NVIDIA GeForce RTX 5080 SUPER sits at the 19th percentile.

Q: Which GPU uses a larger process node?

A: The Intel Arc B370 uses a 3 nm process node, while the NVIDIA GeForce RTX 5080 SUPER uses a 5 nm process node fabricated by TSMC.

Q: What is the memory configuration difference between the two cards?

A: The Intel Arc B370 uses system shared memory with system dependent bandwidth. The NVIDIA GeForce RTX 5080 SUPER has 24 GB of GDDR7 memory on a 256 bit bus, delivering 1.02 TB/s of bandwidth.

Q: How do the power requirements differ?

A: The Intel Arc B370 has a TDP of 25 W and uses no power connectors. The NVIDIA GeForce RTX 5080 SUPER has a TDP of 415 W and requires one 16-pin power connector.

Q: Do both GPUs support the same API feature levels?

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

Architecture Differences

The Intel Arc B370 and NVIDIA GeForce RTX 5080 SUPER represent fundamentally different design approaches. The Intel part uses the Panther Lake chip with Xe3-LPG architecture and belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA part uses the GB203 chip with Blackwell 2.0 architecture and belongs to the GeForce 50 series.

Manufacturing processes differ significantly. Intel fabricates the B370 on a 3 nm node at its own foundry. NVIDIA builds the RTX 5080 SUPER on a 5 nm node at TSMC. The NVIDIA chip uses 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6M per mm². The Intel chip's transistor count and die size are not recorded in the database.

The execution resource counts diverge sharply. The Arc B370 has 1280 shading units, 40 texture mapping units, 20 ROPs, and 10 ray tracing cores. The RTX 5080 SUPER has 10752 shading units, 336 TMUs, 112 ROPs, and 84 ray tracing cores. NVIDIA also includes 336 tensor cores, while no tensor core count is recorded for the Intel part.

Clock behavior differs by design intent. The Arc B370 runs at a 300 MHz base clock and boosts to 2400 MHz. The RTX 5080 SUPER has a much higher base of 2295 MHz and boosts to 2617 MHz. Memory clocks also reflect different strategies: the Intel GPU uses system shared memory, while the NVIDIA card operates its GDDR7 memory at 2000 MHz with 32 Gbps effective speed.

The compute throughput figures illustrate the scaling gap. The Arc B370 delivers 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 with a 2:1 ratio. The RTX 5080 SUPER delivers 56.28 TFLOPS for both FP32 and FP16 at a 1:1 ratio. Pixel and texture rates follow the same pattern: the Intel part reaches 48.00 GPixel/s and 96.00 GTexel/s, while the NVIDIA card reaches 293.1 GPixel/s and 879.3 GTexel/s.

Form factor and integration also separate the two. The Arc B370 is an IGP with no slot width, no power connectors, and a portable device dependent display output. The RTX 5080 SUPER is a dual-slot card measuring 304 mm by 137 mm by 40 mm, with a PCIe 5.0 x16 interface and outputs of one HDMI 2.1b and three DisplayPort 2.1b ports.

Where Each One Wins

The benchmark data records only one head-to-head test, and the NVIDIA GeForce RTX 5080 SUPER wins it. The wins tally shows 0 wins for the Intel Arc B370 and 1 win for the NVIDIA card.

The RTX 5080 SUPER dominates the 3DMark Steel Nomad DX12 test by a wide margin. Its score of 3075 versus 1184 represents a 61.5 percent lead. This outcome aligns with the massive differences in shading units, memory bandwidth, and compute throughput. The NVIDIA card's 1.02 TB/s memory bandwidth alone exceeds what the system shared memory configuration of the Intel part can provide in most scenarios.

The Intel Arc B370 holds advantages in power efficiency and integration. Its 25 W TDP allows operation without any power connector, making it suitable for compact portable devices. The NVIDIA card requires 415 W and a 16-pin connector. The B370 also uses a smaller 3 nm process node, which suggests a denser manufacturing approach despite the unknown transistor count.

For workload classification, the RTX 5080 SUPER is the clear choice for high-resolution gaming and GPU-intensive compute tasks. Its 24 GB GDDR7 frame buffer and tensor core array provide resources for demanding rendering and AI workloads. The Arc B370, as an integrated GPU with system shared memory, targets lighter graphics duties where low power draw and minimal physical footprint take priority over absolute performance.

Specification Differences

The two GPUs differ across nearly every recorded specification.

Process and chip: The Arc B370 uses a 3 nm Intel process with the Panther Lake chip. The RTX 5080 SUPER uses a 5 nm TSMC process with the GB203 chip.

Transistors and die: The Intel part has unknown transistor count and die size. The NVIDIA part has 45,600 million transistors on a 378 mm² die with 120.6M per mm² density.

Core clocks: Intel lists 300 MHz base and 2400 MHz boost. NVIDIA lists 2295 MHz base and 2617 MHz boost.

Memory: The Intel GPU uses system shared memory with system dependent bandwidth. The NVIDIA card uses 24 GB GDDR7 on a 256 bit bus with 1.02 TB/s bandwidth.

Execution units: Intel has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. NVIDIA has 10752 shading units, 336 TMUs, 112 ROPs, and 84 RT cores.

Tensor cores: No count recorded for Intel. NVIDIA has 336 tensor cores.

Pixel and texture rates: Intel reaches 48.00 GPixel/s and 96.00 GTexel/s. NVIDIA reaches 293.1 GPixel/s and 879.3 GTexel/s.

Compute throughput: Intel delivers 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1). NVIDIA delivers 56.28 TFLOPS for both FP32 and FP16 (1:1).

Power and cooling: Intel has a 25 W TDP, is IGP class, and uses no power connectors. NVIDIA has a 415 W TDP, is dual-slot, and uses one 16-pin connector.

Interface and outputs: Intel uses an IGP bus interface with portable device dependent outputs. NVIDIA uses PCIe 5.0 x16 with one HDMI 2.1b and three DisplayPort 2.1b outputs.

Dimensions: Intel has no recorded dimensions. NVIDIA measures 304 mm by 137 mm by 40 mm.

Release date: Intel released on 2026-01-26. NVIDIA released on 2025-12-31.

Launch MSRP: NVIDIA launched at 999 USD. Intel has no recorded launch MSRP.

Benchmark score: Intel scores 1184. NVIDIA scores 3075.

Head-to-Head Benchmarks

The database contains one head-to-head benchmark between these two GPUs: 3DMark Steel Nomad DX12. The NVIDIA GeForce RTX 5080 SUPER scores 3075, and the Intel Arc B370 scores 1184. The delta is recorded as negative 61.5 percent from the perspective of the Intel part, meaning the NVIDIA card outperforms it by that margin.

This result places the two GPUs in entirely different performance brackets. The Intel Arc B370's nearest rivals in the database include the ATI Mobility Radeon HD 5570 at 1186, the ATI Radeon HD 5770 at 1190, the AMD Radeon HD 7650M at 1192, and the AMD FirePro M2000 at 1168. The deltas for these rivals range from negative 0.7 percent to positive 1.4 percent, indicating that all four sit within a narrow band around the Intel part's score. The Arc B370 effectively trades blows with older discrete and mobile GPUs from over a decade ago.

The NVIDIA GeForce RTX 5080 SUPER's nearest rivals tell a similar story at a higher level. The NVIDIA Quadro P1000 scores 3163, which is 2.8 percent above the RTX 5080 SUPER. The Intel Arc Pro B60 scores 3182, 3.4 percent above. On the lower side, the NVIDIA GeForce 820A scores 2983, 3.1 percent below, and the NVIDIA GeForce GTX 860M scores 2967, 3.6 percent below. The RTX 5080 SUPER sits in a cluster where the surrounding GPUs are within roughly 3.5 percent, but that cluster operates at roughly 2.5 times the absolute score of the Arc B370's cluster.

The magnitude of the gap becomes clear when comparing the percentile standings. The Arc B370 ranks at the 5th percentile of all GPUs, meaning the vast majority of recorded GPUs score higher. The RTX 5080 SUPER ranks at the 19th percentile, a stronger position but still not near the top of the database. Neither GPU is a leader in the global rankings, yet the separation between them spans multiple tiers of performance.

The only recorded benchmark result, while limited in scope, is consistent with the hardware specifications. The NVIDIA card's 56.28 TFLOPS FP32 throughput is roughly 9.2 times the Intel part's 6.144 TFLOPS. Its 1.02 TB/s memory bandwidth is a discrete dedicated pool versus the Intel part's system dependent shared memory. Its 10752 shading units dwarf the 1280 in the Intel chip. These structural advantages translate directly into the Steel Nomad result.

The data does not show any benchmark where the Intel Arc B370 wins. The wins tally confirms this: 0 for Intel, 1 for NVIDIA. For any workload captured by the 3DMark Steel Nomad DX12 test, the RTX 5080 SUPER delivers the higher score by a decisive margin. The Intel part remains competitive only within its own performance neighborhood, where it trades positions with GPUs scoring between 1168 and 1192.