Intel Arc B370 vs NVIDIA GeForce RTX 5060 Ti 8 GB Comparison
Intel Arc B370
GeForce RTX 5060 Ti 8 GB
PERFORMANCE BENCHMARKS
Analysis: Intel Arc B370 vs NVIDIA GeForce RTX 5060 Ti 8 GB
Where Each One Wins
The benchmark data splits cleanly along performance tiers. The NVIDIA GeForce RTX 5060 Ti 8 GB dominates the single available head-to-head test, the 3DMark Steel Nomad DX12 run, scoring 4019 against the Intel Arc B370's 1184. That is a 70.5% deficit for the Intel part, and it is the only direct comparison recorded in the database. The Arc B370 wins nowhere in this matchup; the wins column shows zero for Intel and one for NVIDIA.
Context matters here. The Arc B370 sits in the 5th percentile of all GPUs tracked by the database, while the RTX 5060 Ti lands in the 29th percentile. The nearest rivals for the Intel part are older discrete and mobile parts such as the ATI Mobility Radeon HD 5570 (avg score 1186, 0.2% ahead), the ATI Radeon HD 5770 (1190, 0.5% ahead), and the AMD Radeon HD 7650M (1192, 0.7% ahead). The Arc B370 also edges the AMD FirePro M2000 by 1.4%. For the NVIDIA card, the nearest rivals include the AMD FirePro W5130M (4904, 0.1% ahead), the NVIDIA GeForce GTS 450 (4893, 0.2% behind), and the AMD Radeon R7 M265 (4929, 0.6% ahead). These proximity bands show that the Intel chip competes with decade-old parts, while the NVIDIA chip sits near much stronger legacy hardware.
The use-case split is therefore stark. The RTX 5060 Ti 8 GB is the only option here for any workload that stresses the GPU in a 3DMark Steel Nomad-style DX12 scenario. The Arc B370, with its IGP slot width and system-shared memory, appears oriented toward portable or low-power environments where the 3D load is minimal. The data does not support any scenario where the Intel part wins a recorded benchmark, so any buyer or integrator looking at this pairing must treat the NVIDIA card as the sole performance choice.
Architecture Differences
The two parts come from entirely different design philosophies. The Intel Arc B370 uses the Xe3-LPG architecture on the Panther Lake chip, built on a 3 nm process at Intel's own foundry. The NVIDIA GeForce RTX 5060 Ti 8 GB uses Blackwell 2.0 on the GB206 chip, fabricated on a 5 nm process at TSMC. Transistor counts differ sharply: the NVIDIA chip packs 21,900 million transistors on a 181 mm² die, giving 121.0M transistors per mm². The Intel part's transistor count and die size are listed as unknown in the database.
The execution resources tell the same story. The Arc B370 has 1280 shading units, 40 texture mapping units, 20 ROPs, and 10 ray tracing cores. The RTX 5060 Ti has 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. The NVIDIA part also has a dedicated tensor core array; the Intel part lists none. Clock behavior differs as well. The Arc B370 runs a 300 MHz base and 2400 MHz boost, while the RTX 5060 Ti runs a 2407 MHz base and 2572 MHz boost.
Memory architecture separates the two fundamentally. The Arc B370 uses system-shared memory with a system-dependent bandwidth, meaning there is no dedicated VRAM of its own. The RTX 5060 Ti has 8 GB of GDDR7 on a 128-bit bus, delivering 448.0 GB/s. The memory clock is listed as 1750 MHz with 28 Gbps effective. That dedicated bandwidth is a primary reason the NVIDIA part sustains far higher fill rates: 123.5 GPixel/s and 370.4 GTexel/s versus 48.00 GPixel/s and 96.00 GTexel/s for Intel.
Power and physical design also diverge. The Arc B370 is rated at 25 W TDP, uses an IGP slot width, has no power connectors, and exposes display outputs that are portable-device dependent. The RTX 5060 Ti is a dual-slot card rated at 180 W, requires a single 8-pin power connector, suggests a 450 W PSU, and offers 1x HDMI 2.1b plus 3x DisplayPort 2.1b. The NVIDIA card measures 241 mm by 111 mm by 40 mm. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature parity exists despite the internal differences.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The NVIDIA GeForce RTX 5060 Ti 8 GB has an average benchmark score of 4901, while the Intel Arc B370 averages 1184. The NVIDIA card also sits in the 29th percentile of all GPUs, compared to the Intel part's 5th percentile.
Q: How much faster is the RTX 5060 Ti in the 3DMark Steel Nomad DX12 test?
A: The RTX 5060 Ti scores 4019, and the Arc B370 scores 1184. The delta is 70.5% in favor of NVIDIA.
Q: What memory configuration does each card use?
A: The RTX 5060 Ti uses 8 GB of GDDR7 on a 128-bit bus with 448.0 GB/s bandwidth. The Arc B370 uses system-shared memory with system-dependent bandwidth.
Q: Do both cards support the same graphics APIs?
A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
Q: What is the power draw difference?
A: The Arc B370 is rated at 25 W TDP and requires no power connectors. The RTX 5060 Ti is rated at 180 W TDP and uses a single 8-pin connector with a suggested 450 W PSU.
Q: Which card has more ray tracing cores?
A: The RTX 5060 Ti has 36 RT cores. The Arc B370 has 10 RT cores.
Specification Differences
The two GPUs differ in nearly every measurable specification. The NVIDIA card uses the Blackwell 2.0 architecture on a 5 nm TSMC process with 21,900 million transistors on a 181 mm² die. The Intel part uses Xe3-LPG on a 3 nm Intel process with unknown transistor count and die size. Base clocks are 2407 MHz for NVIDIA versus 300 MHz for Intel; boost clocks are 2572 MHz versus 2400 MHz. Memory is 8 GB GDDR7 on a 128-bit bus with 448.0 GB/s bandwidth for NVIDIA, while Intel uses system-shared memory with system-dependent bandwidth.
Compute resources: NVIDIA has 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. Intel has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores, with no tensor cores listed. Fill rates: NVIDIA achieves 123.5 GPixel/s and 370.4 GTexel/s; Intel achieves 48.00 GPixel/s and 96.00 GTexel/s. Floating point: NVIDIA delivers 23.70 TFLOPS FP32 and 23.70 TFLOPS FP16 (1:1); Intel delivers 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1).
Power and physical specs: NVIDIA is 180 W, dual-slot, with a 1x 8-pin connector and 450 W suggested PSU; Intel is 25 W, IGP slot width, no power connectors. The NVIDIA card is 241 mm long, 111 mm high, and 40 mm wide; the Intel part has no listed dimensions. Bus interface: NVIDIA uses PCIe 5.0 x8; Intel uses IGP. Display outputs: NVIDIA offers 1x HDMI 2.1b and 3x DisplayPort 2.1b; Intel's outputs are portable-device dependent. Release dates differ: NVIDIA launched 2025-04-15, Intel 2026-01-26. The NVIDIA card lists a launch MSRP of 379 USD.
Head-to-Head Benchmarks
The only common benchmark in the database is 3dmark_3dmark_steel_nomad_dx12. The RTX 5060 Ti scores 4019, and the Arc B370 scores 1184, resulting in a delta of 70.5% for NVIDIA. That single result defines the entire comparison. The NVIDIA card's nearest rivals average around 4900, so the 4019 score is below its own peer group. The Intel part's 1184 score sits within 1% of several older ATI and AMD parts, confirming its position far down the performance ladder.
The Intel Arc B370's additional benchmark list is empty aside from the Steel Nomad result. The NVIDIA card also has PassMark entries: DirectX 9 at 228, DirectX 10 at 142, DirectX 11 at 220, DirectX 12 at 82, G2D at 1169, G3D at 21981, and GPU compute at 11365. These additional scores do not have Intel counterparts, so they cannot be compared directly. The only defensible cross-card statement is the Steel Nomad delta.
Pixel and texture rates reinforce the gap. The RTX 5060 Ti's 123.5 GPixel/s is roughly 2.6 times the Intel part's 48.00 GPixel/s. Texture rate is 370.4 GTexel/s versus 96.00 GTexel/s, a ratio of about 3.9. FP32 throughput is 23.70 TFLOPS against 6.144 TFLOPS, roughly 3.9 times. These ratios align with the 70.5% benchmark deficit, indicating that the benchmark result is consistent with the raw specification differences rather than an outlier.
The Verdict
The recorded data leaves little room for ambiguity. The NVIDIA GeForce RTX 5060 Ti 8 GB is the only part in this pairing that delivers competitive 3D performance, with a 3DMark Steel Nomad score of 4019 versus 1184 for the Intel Arc B370. The NVIDIA card also holds a 29th percentile rank, while the Intel part sits at the 5th percentile. Any workload that relies on the 3DMark Steel Nomad DX12 metric will favor NVIDIA by a wide margin.
The Intel Arc B370 does have a role, but it is not a performance role. Its 25 W TDP, IGP form factor, system-shared memory, and lack of power connectors position it as an integrated solution for portable devices. The 3 nm Panther Lake process and Xe3-LPG architecture indicate a modern, power-lean design, but the benchmark data shows it performing alongside ATI Mobility Radeon HD 5570-class hardware. For a device that needs basic graphics with minimal power draw, the Arc B370 fits. For any task that demands the throughput demonstrated by the RTX 5060 Ti, the NVIDIA card is the only choice supported by the measurements.
The RTX 5060 Ti's 8 GB GDDR7 memory, 448.0 GB/s bandwidth, 4608 shading units, and 36 RT cores give it a structural advantage that no Intel specification can offset. The launch MSRP of 379 USD for the NVIDIA card also indicates a retail add-in board, whereas the Intel part's IGP bus interface ties it to a specific platform. Buyers choosing between these two should base the decision on whether they need a discrete, high-throughput GPU or an integrated, low-power solution. The data favors the former for performance and the latter for power efficiency.