Intel Arc B370 vs NVIDIA RTX 5000 Mobile Ada Generation Comparison

Head-to-Head Benchmarks

The only recorded benchmark comparison between these two mobile graphics solutions is the 3DMark Steel Nomad DX12 test. In that workload, the NVIDIA RTX 5000 Mobile Ada Generation scores 3596, while the Intel Arc B370 scores 1184. The delta is -67.1% for Intel, meaning NVIDIA delivers roughly three times the performance in this particular test.

This is a decisive margin, not a close contest. The RTX 5000 Mobile lands at the 21st percentile among all GPUs in the database, while the Arc B370 sits at the 5th percentile. That percentile gap puts the two parts in completely different performance tiers. The NVIDIA part is not merely faster; it occupies a league where 79% of recorded GPUs score lower, while the Intel part is near the bottom of the distribution.

Looking at the nearest rivals for each card reinforces the separation. The Arc B370's closest competitors are the ATI Mobility Radeon HD 5570 (avg score 1186, delta -0.2%), the ATI Radeon HD 5770 (avg score 1190, delta -0.5%), the AMD Radeon HD 7650M (avg score 1192, delta -0.7%), and the AMD FirePro M2000 (avg score 1168, delta +1.4%). The Arc B370 is effectively trading blows with graphics hardware from roughly a decade earlier. Its best relative result is a 1.4% advantage over the FirePro M2000, and its worst is a 0.7% deficit against the Radeon HD 7650M. This is not a part that outclasses its immediate peers; it lands squarely in the middle of a very old performance cluster.

The RTX 5000 Mobile's nearest rivals tell a different story. The NVIDIA GeForce GT 545 scores 3594 (delta +0.1%), the GeForce GT 735M scores 3616 (delta -0.6%), the GeForce GTX 1050 scores 3629 (delta -0.9%), and the AMD Radeon HD 6770 scores 3649 (delta -1.5%). The RTX 5000 Mobile is slightly behind the GTX 1050 and the HD 6770, but the differences are within a couple of percentage points. The NVIDIA part is competitive with a mid-range desktop GPU from the Pascal era, which is a far more recent and capable reference point than anything near the Arc B370.

In the single head-to-head measurement, the RTX 5000 Mobile wins outright. The data shows no benchmark where the Intel part comes out ahead. The margin is large enough that no amount of driver tuning or workload selection would plausibly close it in this specific test. The 3DMark Steel Nomad DX12 result is a modern, DirectX 12 workload that stresses both rasterization and ray tracing, and the NVIDIA part simply has far more hardware resources to throw at it.

The Verdict

The benchmark data points to a clear split: the NVIDIA RTX 5000 Mobile Ada Generation is the substantially faster GPU for 3D rendering workloads, while the Intel Arc B370 is a low-power integrated solution that cannot compete in raw performance.

For anyone whose primary concern is frame rates in DirectX 12 games or 3D applications, the RTX 5000 Mobile is the obvious choice. It produces a 3DMark Steel Nomad score of 3596, which places it at the 21st percentile globally. That is roughly three times the Arc B370's score of 1184, and the delta of -67.1% confirms that the Intel part is not in the same performance class.

However, the RTX 5000 Mobile carries a 120 W TDP and uses a discrete 16 GB GDDR6 memory subsystem with a 256-bit bus and 576.0 GB/s of bandwidth. The Arc B370, by contrast, has a 25 W TDP and uses system shared memory with system dependent bandwidth. The Intel part is designed for efficiency and integration, not for heavy 3D loads. Its 3 nm process node and integrated form factor make it suitable for thin-and-light portable devices where power draw is the limiting factor.

The data does not support any scenario where the Arc B370 outperforms the RTX 5000 Mobile in the recorded benchmark. There are zero wins for the Intel part and one win for the NVIDIA part. The verdict is therefore straightforward: choose the RTX 5000 Mobile for performance, choose the Arc B370 only if the system must operate within a much lower power envelope and does not require discrete-class graphics throughput.

Where Each One Wins

The RTX 5000 Mobile wins in every measured category that involves 3D rendering throughput. Its shading units total 9728 versus 1280 for the Arc B370. Its texture mapping units number 304 versus 40. Its raster operation units total 112 versus 20. Its ray tracing cores number 76 versus 10, and its tensor cores total 304 versus none listed for the Intel part. These are not incremental advantages; they are order-of-magnitude differences in parallel compute resources.

The pixel rate for the RTX 5000 Mobile is 236.9 GPixel/s, compared to 48.00 GPixel/s for the Arc B370. The texture rate is 643.0 GTexel/s versus 96.00 GTexel/s. Floating point performance is 41.15 TFLOPS for FP32 versus 6.144 TFLOPS, and 41.15 TFLOPS for FP16 versus 12.29 TFLOPS. Every throughput metric favors NVIDIA by a large margin.

The Arc B370's only advantages are in power consumption and integration. Its 25 W TDP is one-fifth of the RTX 5000 Mobile's 120 W TDP. It is an IGP with no power connectors, while the RTX 5000 Mobile is also listed as IGP with no power connectors, but the NVIDIA part clearly draws far more power. The Intel part uses a 3 nm process from Intel, while the NVIDIA part uses a 5 nm process from TSMC. The smaller process node gives Intel a density advantage, but that does not translate into performance in the recorded data.

For gaming or GPU-accelerated compute at high settings, the RTX 5000 Mobile is the only viable option. For basic display output, video playback, or light productivity work in a low-power portable device, the Arc B370 can suffice, but it will not deliver playable frame rates in demanding modern titles.

FAQ

Q: Which GPU is faster in the 3DMark Steel Nomad DX12 benchmark?

A: The NVIDIA RTX 5000 Mobile Ada Generation, with a score of 3596 versus 1184 for the Intel Arc B370. The Intel part trails by -67.1%.

Q: How does each GPU rank among all GPUs in the database?

A: The RTX 5000 Mobile sits at the 21st percentile, while the Arc B370 sits at the 5th percentile.

Q: What are the closest rivals to the Arc B370?

A: The ATI Mobility Radeon HD 5570 (avg 1186, delta -0.2%), ATI Radeon HD 5770 (avg 1190, delta -0.5%), AMD Radeon HD 7650M (avg 1192, delta -0.7%), and AMD FirePro M2000 (avg 1168, delta +1.4%).

Q: What are the closest rivals to the RTX 5000 Mobile?

A: The NVIDIA GeForce GT 545 (avg 3594, delta +0.1%), GeForce GT 735M (avg 3616, delta -0.6%), GeForce GTX 1050 (avg 3629, delta -0.9%), and AMD Radeon HD 6770 (avg 3649, delta -1.5%).

Q: How much memory does each GPU have?

A: The RTX 5000 Mobile has 16 GB of GDDR6 memory on a 256-bit bus with 576.0 GB/s bandwidth. The Arc B370 uses system shared memory with system dependent bandwidth.

Q: What is the power draw of each GPU?

A: The RTX 5000 Mobile has a 120 W TDP, while the Arc B370 has a 25 W TDP.

Architecture Differences

The two GPUs come from entirely different architectural lineages. The Intel Arc B370 uses the Xe3-LPG architecture on a 3 nm process from Intel's own foundry. Its chip is named Panther Lake, and it belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA RTX 5000 Mobile uses the Ada Lovelace architecture on a 5 nm process from TSMC. Its chip is the AD103, and it belongs to the Ada-MW generation.

The transistor counts differ enormously. The RTX 5000 Mobile integrates 45,900 million transistors on a 379 mm² die, for a density of 121.1M / mm². The Arc B370's transistor count and die size are listed as unknown in the database, so no direct comparison is possible. However, the process node difference (3 nm versus 5 nm) suggests Intel is using a more advanced manufacturing process, even though the NVIDIA chip has far more transistors.

Ray tracing hardware is present in both, but with very different scale. The Arc B370 has 10 ray tracing cores, while the RTX 5000 Mobile has 76. Tensor cores are listed only for the NVIDIA part, with 304 units; the Intel part has no tensor core count recorded. This affects AI-accelerated workloads and DLSS-style features, though the benchmark data does not directly measure those.

The API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display outputs are portable device dependent for both, meaning the exact connections vary by laptop implementation.

Specification Differences

The most striking specification difference is memory. The RTX 5000 Mobile uses 16 GB of GDDR6 with a 256-bit bus and 576.0 GB/s bandwidth. The Arc B370 uses system shared memory, meaning it borrows from the system RAM and has no dedicated VRAM. Its memory bus width and type are both listed as system shared, and bandwidth is system dependent. This has major implications for texture-heavy workloads and high-resolution rendering.

Clock speeds also differ. The Arc B370 has a base clock of 300 MHz and a boost clock of 2400 MHz. The RTX 5000 Mobile has a base clock of 1425 MHz and a boost clock of 2115 MHz. The Intel part has a higher boost clock, but its lower base clock and far fewer execution units mean it cannot translate that into higher throughput.

The compute unit counts are vastly different. The Arc B370 has 1280 shading units, 40 TMUs, and 20 ROPs. The RTX 5000 Mobile has 9728 shading units, 304 TMUs, and 112 ROPs. The NVIDIA part has roughly 7.6 times the shading units, 7.6 times the TMUs, and 5.6 times the ROPs.

Power consumption is a major differentiator. The Arc B370 has a 25 W TDP, while the RTX 5000 Mobile has a 120 W TDP. Both are listed as IGP with no power connectors, but the NVIDIA part draws nearly five times the power. The bus interface also differs: the Arc B370 uses IGP, while the RTX 5000 Mobile uses PCIe 4.0 x16.

The release dates are separated by nearly three years. The RTX 5000 Mobile launched on 2023-03-20, while the Arc B370 launched on 2026-01-26. The NVIDIA part has a predecessor (Ampere-MW) and a successor (Blackwell-MW), while the Intel part has neither listed.

The FP16 performance ratio also differs. The Arc B370 delivers 12.29 TFLOPS FP16 using a 2:1 ratio relative to FP32, while the RTX 5000 Mobile delivers 41.15 TFLOPS FP16 at a 1:1 ratio. The NVIDIA part does not halve its throughput for FP16, which matters for workloads that use reduced precision.