Intel Arc B390 vs NVIDIA GeForce RTX 4070 Mobile Comparison

Intel Arc B390 is an integrated graphics processor built on Intel's 3 nm Panther Lake chip and Xe3-LPG architecture, while NVIDIA GeForce RTX 4070 Mobile is a discrete mobile GPU based on the AD106 chip and Ada Lovelace architecture. The recorded benchmark data shows a decisive performance gap between the two, with the RTX 4070 Mobile dominating in every measured category, while the Arc B390 holds a small but measurable edge over several older low-end NVIDIA parts.

Head-to-Head Benchmarks

The database contains one benchmark result for the Intel Arc B390: a 3DMark Steel Nomad DX12 score of 1482. This result places the Arc B390 at the 9th percentile of all GPUs in the database. The RTX 4070 Mobile, by contrast, has an average benchmark score of 27435 across multiple tests, placing it at the 73rd percentile of all GPUs. The difference in average scores is approximately 18.5 times larger for the NVIDIA part, indicating a completely different performance tier.

The RTX 4070 Mobile delivers 15.62 TFLOPS of FP32 compute, compared to 7.680 TFLOPS for the Arc B390, a difference of roughly 2.03 times. In FP16 throughput, the RTX 4070 Mobile achieves 15.62 TFLOPS at 1:1 ratio, while the Arc B390 reaches 15.36 TFLOPS at 2:1 ratio, meaning the NVIDIA part maintains its full rate without the 2:1 penalty that applies to the Intel iGPU. Texture fill rate heavily favors the NVIDIA GPU as well: 244.1 GTexel/s versus 120.0 GTexel/s, a 2.03 times advantage. Pixel fill rate also favors the RTX 4070 Mobile at 81.36 GPixel/s against 60.00 GPixel/s for the Arc B390, a 1.36 times margin.

The RTX 4070 Mobile's closest rivals in the database include the AMD Radeon RX 6700 XT with an average score of 27425 and a delta of 0.0 percent, the NVIDIA GeForce RTX 3090 at 27565 with a delta of -0.5 percent, and the NVIDIA RTX PRO 4000 Blackwell at 27135 with a delta of 1.1 percent. This places the RTX 4070 Mobile in the same performance class as a desktop RX 6700 XT and RTX 3090, both high-end parts. The Arc B390's nearest rivals are far less capable: the NVIDIA GeForce GT 520MX at 1463 with a delta of 1.3 percent, the NVIDIA GeForce 800M at 1460 with a delta of 1.5 percent, the NVIDIA GeForce GT 625 OEM at 1446 with a delta of 2.5 percent, and the NVIDIA GeForce GT 710 at 1443 with a delta of 2.7 percent. The Arc B390 beats these parts by margins of 1.3 to 2.7 percent, so its performance level sits just above a collection of decade-old entry-level discrete GPUs.

In the PassMark suite, the RTX 4070 Mobile records a G3D score of 19587, a DirectX 12 score of 85, a DirectX 11 score of 179, a DirectX 10 score of 116, a DirectX 9 score of 223, a G2D score of 763, and a GPU compute score of 8399. The Geekbench results show 109197 in OpenCL and 108367 in Vulkan. No corresponding sub-tests exist for the Arc B390 in this database, so the only direct numerical comparison available is the Steel Nomad DX12 score of 1482 against the RTX 4070 Mobile's average of 27435.

The Verdict

The data indicates that the NVIDIA GeForce RTX 4070 Mobile is the substantially faster part in every measurable way. Its average benchmark score of 27435 versus 1482 for the Arc B390 is not a close contest; the RTX 4070 Mobile performs at a level comparable to the AMD Radeon RX 6700 XT and NVIDIA GeForce RTX 3090, both of which are desktop-class GPUs. The Arc B390, with a 9th percentile ranking, competes with the NVIDIA GeForce GT 710 and similar legacy parts, and it leads them by only single-digit percentages. For anyone selecting a GPU for demanding graphical workloads, the RTX 4070 Mobile is the clear choice based on recorded performance alone.

The RTX 4070 Mobile also offers a more complete feature set for compute and ray tracing. It has 36 ray tracing cores and 144 tensor cores, whereas the Arc B390 has 12 ray tracing cores and no tensor cores listed. The NVIDIA part supports 4608 shading units, 144 texture mapping units, and 48 render output units, versus 1536 shading units, 48 TMUs, and 24 ROPs for the Intel part. These hardware differences manifest directly in the compute and fill rate numbers already cited.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The Intel Arc B390 uses the Xe3-LPG architecture on a 3 nm process node manufactured by Intel, built as part of the Panther Lake chip. It is an integrated GPU, meaning it shares system memory and has no dedicated VRAM. The NVIDIA GeForce RTX 4070 Mobile uses the Ada Lovelace architecture on a 5 nm process node manufactured by TSMC, with a dedicated 8 GB GDDR6 memory subsystem on a 128-bit bus providing 256.0 GB/s of bandwidth. The Intel part has no dedicated memory bus width or bandwidth figure, relying instead on system shared memory with bandwidth described as system dependent.

The RTX 4070 Mobile carries 22,900 million transistors on a 188 mm² die, with a transistor density of 121.8 million transistors per mm². The Arc B390's transistor count and die size are listed as unknown. The NVIDIA chip is fabricated by TSMC, the Intel chip by Intel's own foundry. Clock behavior also differs: the Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, while the RTX 4070 Mobile has a base clock of 1395 MHz and a boost clock of 1695 MHz. Despite the Intel part's higher boost clock, its much lower shading unit count results in far lower aggregate throughput.

Power consumption differs as well, with the Arc B390 rated at 80 W TDP and the RTX 4070 Mobile rated at 115 W TDP. Both are integrated into portable devices with no power connectors listed, and both have display outputs described as portable device dependent. The RTX 4070 Mobile uses a PCIe 4.0 x8 bus interface, while the Arc B390 uses an IGP bus interface.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 4070 Mobile has an average benchmark score of 27435, while the Intel Arc B390 has a single recorded score of 1482 in 3DMark Steel Nomad DX12.

Q: How does the Intel Arc B390 compare to its nearest rivals?

A: The Arc B390 leads the NVIDIA GeForce GT 520MX by 1.3 percent, the NVIDIA GeForce 800M by 1.5 percent, the NVIDIA GeForce GT 625 OEM by 2.5 percent, and the NVIDIA GeForce GT 710 by 2.7 percent.

Q: What are the nearest performance equivalents for the RTX 4070 Mobile?

A: The RTX 4070 Mobile is essentially tied with the AMD Radeon RX 6700 XT at a 0.0 percent delta, sits 0.5 percent behind the NVIDIA GeForce RTX 3090, leads the NVIDIA RTX PRO 4000 Blackwell by 1.1 percent, and trails the AMD Radeon Pro Vega 20 by 1.5 percent.

Q: Does the Arc B390 have dedicated video memory?

A: No, the Arc B390 uses system shared memory for both capacity and bus width, with bandwidth listed as system dependent. The RTX 4070 Mobile has 8 GB of GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth.

Q: Which GPU has more ray tracing hardware?

A: The RTX 4070 Mobile has 36 ray tracing cores and 144 tensor cores, while the Arc B390 has 12 ray tracing cores and no tensor cores listed.

Q: What are the FP32 compute figures for both GPUs?

A: The RTX 4070 Mobile delivers 15.62 TFLOPS of FP32 compute, and the Arc B390 delivers 7.680 TFLOPS, a 2.03 times advantage for the NVIDIA part.

Where Each One Wins

The RTX 4070 Mobile wins in raw compute, memory bandwidth, texture throughput, pixel throughput, and overall benchmark scores. Its 256.0 GB/s dedicated memory bandwidth versus system shared memory for the Arc B390 gives it a structural advantage in any memory-intensive workload. The 4608 shading units, 144 TMUs, and 48 ROPs more than double the corresponding counts on the Arc B390, and the 36 RT cores plus 144 tensor cores provide dedicated acceleration for ray tracing and AI workloads that the Intel part cannot match. Its 15.62 TFLOPS FP32 and FP16 output at 1:1 ratio makes it suitable for compute tasks that need consistent precision.

The Arc B390 wins only in a narrow sense: it outperforms a set of very old, low-end NVIDIA GPUs by 1.3 to 2.7 percent, and it does so at a lower TDP of 80 W versus 115 W. Its 300 MHz base clock and 2500 MHz boost clock indicate a design that scales up aggressively under load, but the underlying hardware resources are too limited to produce competitive results. The 9th percentile ranking versus the 73rd percentile ranking for the RTX 4070 Mobile summarizes the gap clearly. The Arc B390 is suitable for basic graphics output and light workloads, while the RTX 4070 Mobile is the part for high-performance gaming, rendering, and compute.

Specification Differences

The two GPUs differ in process node, foundry, memory configuration, compute resources, and power rating. The Arc B390 uses a 3 nm Intel node; the RTX 4070 Mobile uses a 5 nm TSMC node with 22,900 million transistors on a 188 mm² die. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores, while the RTX 4070 Mobile has 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. The Arc B390 has no tensor cores listed. Memory differs completely: system shared for Intel versus 8 GB GDDR6 with a 128-bit bus and 256.0 GB/s bandwidth for NVIDIA. Clock speeds are 300 MHz base and 2500 MHz boost for Intel, 1395 MHz base and 1695 MHz boost for NVIDIA. TDP is 80 W for Intel and 115 W for NVIDIA. The bus interface is IGP for Intel and PCIe 4.0 x8 for NVIDIA. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and both are active production parts with no launch MSRP listed.