Intel Arc B370 vs NVIDIA N1X 48SM Comparison

Intel
GPU

Intel Arc B370

CORE STATE Panther Lake
VRAM System Shared
CLOCK SPEED 2400 MHz
TDP 25 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026
VS
NVIDIA
GEFORCE

N1X 48SM

CORE STATE GB20B
VRAM 128 GB
CLOCK SPEED 2346 MHz
TDP unknown
BUS WIDTH 256 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,184
N/A

Analysis: Intel Arc B370 vs NVIDIA N1X 48SM

Intel Arc B370 and NVIDIA N1X 48SM occupy different positions in the database, with the Arc B370 returning a recorded 3DMark Steel Nomad DX12 score of 1184, placing it in the 5th percentile of all GPUs, while the N1X 48SM has no benchmark entries and sits at the 50th percentile. The Arc B370’s nearest rivals include the ATI Mobility Radeon HD 5570 (average score 1186, delta -0.2%), ATI Radeon HD 5770 (average score 1190, delta -0.5%), AMD Radeon HD 7650M (average score 1192, delta -0.7%), and AMD FirePro M2000 (average score 1168, delta +1.4%). The N1X 48SM has no nearest rivals listed, so direct comparisons must rely on architectural and specification data.

Where Each One Wins

The Intel Arc B370 wins on benchmark availability and software compatibility. It has a single recorded benchmark, 3dmark_3dmark_steel_nomad_dx12, with a score of 1184. This places it in the 5th percentile of all GPUs, meaning it outperforms a small fraction of the database. Its nearest rivals show the Arc B370 is nearly identical in performance: it trails the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%, while leading the AMD FirePro M2000 by 1.4%. These deltas are all within a narrow band, indicating the Arc B370 delivers consistent, low-end discrete-class results in the Steel Nomad workload. The database records no wins for the Arc B370 in head-to-head benchmarks, but it does have a complete API stack: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, which allows it to run modern graphics workloads.

The NVIDIA N1X 48SM wins on raw hardware resources. It features 6144 shading units, 384 texture mapping units, 48 raster output units, 48 ray tracing cores, and 192 tensor cores. The Arc B370 counters with 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores, and it has no tensor cores listed. The N1X 48SM’s texture rate is 900.9 GTexel/s versus 96.00 GTexel/s for the Arc B370, a 9.4x advantage. Pixel rate stands at 112.6 GPixel/s versus 48.00 GPixel/s, a 2.3x advantage. Floating-point performance: the N1X 48SM delivers 28.83 TFLOPS FP32 and 28.83 TFLOPS FP16 (1:1), while the Arc B370 provides 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1). The N1X 48SM also has a substantial memory subsystem: 128 GB of LPDDR5X on a 256-bit bus with 273.2 GB/s bandwidth, whereas the Arc B370 uses system shared memory with system-dependent bandwidth.

For use-case splits, the Arc B370 is positioned for integrated graphics scenarios where the host platform provides memory, and its API support enables current DirectX and Vulkan titles. The N1X 48SM is built for compute-heavy tasks: its tensor cores, ray tracing cores, and high FP32 throughput suggest workloads like AI inference, ray-traced rendering, and parallel processing. The N1X 48SM’s lack of recorded benchmarks means its actual in-game performance is unmeasured, but its specification sheet indicates a much higher ceiling for raw throughput.

The Verdict

Based strictly on the recorded data, the Intel Arc B370 is the only one of the two with a measurable benchmark score. Its 1184 points in 3DMark Steel Nomad places it near the ATI Radeon HD 5770 (1190, delta -0.5%) and AMD Radeon HD 7650M (1192, delta -0.7%), which are older discrete GPUs. This suggests the Arc B370, as an integrated part of the Panther Lake chip, performs at a level comparable to early-2010s mid-range discrete cards. The N1X 48SM has no benchmark scores, so its real-world graphics performance cannot be verified from the database. However, its hardware resources are far larger: 6144 shading units, 48 ROPs, 48 RT cores, and 192 tensor cores, which would logically place it far above the Arc B370 in any compute-bound task, provided drivers and software support exist. The N1X 48SM’s API support is listed as N/A for DirectX, OpenGL, and Vulkan, which is a critical limitation. Without those APIs, it cannot run conventional graphics benchmarks or games that rely on those interfaces. Therefore, the Arc B370 is the only choice for standard gaming or graphics workloads that require DirectX, OpenGL, or Vulkan. The N1X 48SM is suited for specialized compute environments where its tensor cores and high FP32 throughput are directly usable, but the database lacks evidence of such usage.

The percentile data reinforces this split: the Arc B370 sits at the 5th percentile, meaning 95% of all GPUs in the database are faster. The N1X 48SM sits at the 50th percentile, but with no benchmark scores, that percentile is based on hardware specifications or other unlisted factors, not measured performance. Users seeking a verified, API-compatible graphics solution should select the Arc B370. Users needing maximum raw compute resources, especially tensor and ray tracing capabilities, should consider the N1X 48SM, but with the caveat that its API support is absent and its performance is unmeasured.

Head-to-Head Benchmarks

The database lists no head-to-head benchmark entries between the Intel Arc B370 and NVIDIA N1X 48SM, and the wins counters are zero for both. The only directly comparable data point is the Arc B370’s 3DMark Steel Nomad DX12 score of 1184, which has no counterpart for the N1X 48SM. The nearest rivals for the Arc B370 provide context: it is 0.2% slower than the ATI Mobility Radeon HD 5570, 0.5% slower than the ATI Radeon HD 5770, 0.7% slower than the AMD Radeon HD 7650M, and 1.4% faster than the AMD FirePro M2000. These deltas are all under 2%, so the Arc B370 performs essentially at parity with those older GPUs. The N1X 48SM’s hardware resources, however, are far beyond those rivals. Its FP32 throughput of 28.83 TFLOPS is 4.7x the Arc B370’s 6.144 TFLOPS. Its texture rate of 900.9 GTexel/s is 9.4x the Arc B370’s 96.00 GTexel/s. Its pixel rate of 112.6 GPixel/s is 2.3x the Arc B370’s 48.00 GPixel/s. Memory bandwidth: 273.2 GB/s versus system dependent, which could be lower or higher depending on the host system’s shared memory configuration. The N1X 48SM also has 48 ray tracing cores versus 10, and 192 tensor cores versus none listed for the Arc B370. These differences indicate that in any benchmark that exercises shading units, texture mapping, or ray tracing, the N1X 48SM would dominate, but no such benchmark results exist in the database. The Arc B370’s only recorded win is its presence in the benchmark suite; the N1X 48SM has zero entries.

FAQ

Q: What is the Intel Arc B370’s recorded benchmark score?

A: The Arc B370 scores 1184 in 3dmark_3dmark_steel_nomad_dx12, placing it in the 5th percentile of all GPUs.

Q: How does the Arc B370 compare to its nearest rivals?

A: It trails the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%, while leading the AMD FirePro M2000 by 1.4%.

Q: Does the NVIDIA N1X 48SM have any benchmark scores?

A: No. The database lists zero benchmark entries for the N1X 48SM, and its average benchmark score is 0.

Q: What are the key memory differences between the two?

A: The N1X 48SM has 128 GB of LPDDR5X on a 256-bit bus with 273.2 GB/s bandwidth. The Arc B370 uses system shared memory with system-dependent bandwidth and no fixed bus width.

Q: Which GPU supports DirectX?

A: The Intel Arc B370 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA N1X 48SM lists N/A for DirectX, OpenGL, and Vulkan.

Q: What is the process node and foundry for each?

A: The Arc B370 uses a 3 nm process from Intel, while the N1X 48SM uses a 5 nm process from TSMC, with a die size of 382 mm².

Architecture Differences

The Intel Arc B370 is built on the Xe3-LPG architecture, part of the Panther Lake chip, belonging to the Arc Graphics-M generation. It uses a 3 nm process at Intel’s foundry. The NVIDIA N1X 48SM uses the Blackwell 2.0 architecture, built on the GB20B chip, part of the Blackwell IGP (N1x) generation, fabricated on a 5 nm process at TSMC with a die size of 382 mm².

Core configuration differs substantially. The Arc B370 has 1280 shading units, 40 texture mapping units, 20 raster output units, and 10 ray tracing cores. It has no tensor cores listed. The N1X 48SM has 6144 shading units, 384 TMUs, 48 ROPs, 48 ray tracing cores, and 192 tensor cores. The N1X 48SM’s shading unit count is 4.8x higher, TMUs are 9.6x higher, ROPs are 2.4x higher, and RT cores are 4.8x higher.

Clock speeds: the Arc B370 has a base clock of 300 MHz and a boost of 2400 MHz. The N1X 48SM has a base of 741 MHz and a boost of 2346 MHz. The Arc B370’s boost is slightly higher, but the N1X 48SM’s base is more than double. Memory clock for the N1X 48SM is 1067 MHz, rated at 8.5 Gbps effective.

Memory architecture: the Arc B370 uses system shared memory with no dedicated size, type, bus width, or bandwidth; the database lists all as system shared or system dependent. The N1X 48SM has 128 GB of LPDDR5X on a 256-bit bus, delivering 273.2 GB/s.

Compute rates: the Arc B370 delivers 48.00 GPixel/s pixel rate and 96.00 GTexel/s texture rate, with FP32 at 6.144 TFLOPS and FP16 at 12.29 TFLOPS (2:1 ratio). The N1X 48SM delivers 112.6 GPixel/s and 900.9 GTexel/s, with FP32 at 28.83 TFLOPS and FP16 at 28.83 TFLOPS (1:1 ratio). The N1X 48SM’s FP16 throughput matches its FP32, indicating no rate reduction for half-precision work.

Power and interface: the Arc B370 has a TDP of 25 W, is an IGP with no power connectors, and uses an IGP bus interface. The N1X 48SM has an unknown TDP, is also an IGP with no power connectors, but uses a PCIe 5.0 x16 bus interface. Display outputs: the Arc B370 lists portable device dependent, while the N1X 48SM has 1x HDMI.

API support differs sharply. The Arc B370 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 48SM lists N/A for all three APIs, which means it cannot run standard graphics software that relies on those interfaces. This is a fundamental architectural distinction: the Arc B370 is designed for conventional graphics stacks, while the N1X 48SM appears oriented toward compute or proprietary environments.

Release dates: the Arc B370 was released on 2026-01-26, and the N1X 48SM on 2026-05-31. Both are marked as active in production. The Arc B370 has a 5th percentile rank among all GPUs, while the N1X 48SM sits at the 50th percentile, though the latter is unverified by any benchmark score.

DETAILED SPECIFICATIONS

SPECIFICATION
B370
N1X 48SM
Core Specs
Shading Units
1,280
6,144 +380.0%
Shaders
1,280
6,144 +380.0%
TMUs
40
384 +860.0%
ROPs
20
48 +140.0%
SM Count
48
Execution Units
10
Clocks
Base Clock
300 MHz
741 MHz
Boost Clock
2400 MHz
2346 MHz
Memory Clock
System Shared
1067 MHz 8.5 Gbps effective
Memory
Memory Size
System Shared
128 GB
VRAM (MB)
131,072
Memory Type
System Shared
LPDDR5X
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
273.2 GB/s
Cache
L1 Cache
64 KB (per EU)
128 KB (per SM)
L2 Cache
16 MB
50 MB
Performance
Pixel Rate
48.00 GPixel/s
112.6 GPixel/s
Texture Rate
96.00 GTexel/s
900.9 GTexel/s
FP32 (TFLOPS)
6.144 TFLOPS
28.83 TFLOPS
FP64 (TFLOPS)
768.0 GFLOPS (1:8)
450.4 GFLOPS (1:64)
FP16 (TFLOPS)
12.29 TFLOPS (2:1)
28.83 TFLOPS (1:1)
AI/RT
RT Cores
10
48 +380.0%
Tensor Cores
192
XMX Cores
80
Power
TDP
25 W
unknown
TDP (W)
25
Power Connectors
None
None
Architecture
Architecture
Xe3-LPG
Blackwell 2.0
GPU Name
Panther Lake
GB20B
Generation
Arc Graphics-M (Panther Lake)
Blackwell IGP (N1x)
Process Size
3 nm
5 nm
Transistors
unknown
unknown
Die Size
unknown
382 mm²
Foundry
Intel
TSMC
API Support
DirectX
12 Ultimate (12_2)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
12.1
Shader Model
6.9
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
1x HDMI
Bus Interface
IGP
PCIe 5.0 x16
Other
Production
Active
Active
View Arc B370 Details View N1X 48SM Details