Intel Arc B570 vs NVIDIA GeForce RTX 3060 Mobile Comparison

Intel
GPU

Intel Arc B570

CORE STATE BMG-G21
VRAM 10 GB
CLOCK SPEED 2500 MHz
TDP 150 W
BUS WIDTH 160 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

GeForce RTX 3060 Mobile

CORE STATE GA106
VRAM 6 GB
CLOCK SPEED 1425 MHz
TDP 80 W
BUS WIDTH 192 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,649
1,821
geekbench_opencl
83,514
79,483
geekbench_vulkan
96,844
80,344
passmark_directx_10
65
90
passmark_directx_11
118
110
passmark_directx_12
72
58
passmark_directx_9
164
146
passmark_g2d
661
588
passmark_g3d
14,195
13,230
passmark_gpu_compute
7,281
5,718

Analysis: Intel Arc B570 vs NVIDIA GeForce RTX 3060 Mobile

Head-to-Head Benchmarks

The Intel Arc B570 dominates the head-to-head comparison, winning 9 of 10 recorded benchmarks against the NVIDIA GeForce RTX 3060 Mobile. The largest margin comes in the 3DMark Steel Nomad DX12 test, where the Arc B570 scores 2649 versus 1821 for the RTX 3060 Mobile, a decisive 45.5% advantage. This is the clearest indicator that the Intel part holds a substantial lead in modern DirectX 12 rendering workloads.

Vulkan performance also favors the Arc B570 heavily. In Geekbench Vulkan, the Intel GPU scores 96844 against 80344, a 20.5% lead. The gap is consistent with the 3DMark result, suggesting the Arc B570 has a meaningful architectural edge in compute-heavy graphics APIs. OpenCL results are closer: 83514 for the Arc B570 versus 79483 for the RTX 3060 Mobile, a 5.1% margin that still favors Intel but shows the NVIDIA part is competitive in general-purpose compute.

PassMark results tell a more varied story. The Arc B570 wins PassMark G3D with 14195 against 13230, a 7.3% advantage. In PassMark DirectX 11, the Intel GPU again leads by 7.3%, scoring 118 versus 110. The DirectX 12 PassMark test shows a larger 24.1% lead for the Arc B570 (72 versus 58), while DirectX 9 shows a 12.3% edge (164 versus 146). The Arc B570 also wins PassMark G2D by 12.4% (661 versus 588) and PassMark GPU Compute by 27.3% (7281 versus 5718).

The single benchmark the RTX 3060 Mobile wins is PassMark DirectX 10, where it scores 90 against 65, a 27.8% lead for NVIDIA. This is an outlier relative to the rest of the results, likely reflecting legacy driver optimization rather than a general pattern. Outside of that one test, the Arc B570 holds the advantage in every category, with margins ranging from 5.1% to 45.5%.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc B570 has an average score of 20556, while the NVIDIA GeForce RTX 3060 Mobile averages 18159. The Arc B570 also sits at the 65th percentile among all GPUs, compared to the 62nd percentile for the RTX 3060 Mobile.

Q: How does the Arc B570 compare to its nearest rivals?

A: The Arc B570 sits within 0.5% of four nearby GPUs: it is 0.1% ahead of the NVIDIA GeForce RTX 3070 Mobile, 0.1% behind the Intel Arc A750, 0.4% ahead of the NVIDIA Quadro M4000M, and 0.5% behind the AMD Radeon R9 M390X.

Q: What is the biggest performance gap in the head-to-head results?

A: The largest delta is in 3DMark Steel Nomad DX12, where the Arc B570 leads by 45.5%. The next largest gaps are PassMark GPU Compute at 27.3% and Geekbench Vulkan at 20.5%, both favoring the Arc B570.

Q: Does the RTX 3060 Mobile win any benchmarks?

A: Yes, it wins PassMark DirectX 10 with a score of 90 versus 65, a 27.8% margin. This is the only test in the head-to-head set where NVIDIA comes out ahead.

Q: How do the two GPUs compare in compute performance?

A: The Arc B570 leads in PassMark GPU Compute by 27.3% (7281 versus 5718) and in Geekbench OpenCL by 5.1% (83514 versus 79483). The Vulkan gap is even larger, 20.5% in favor of the Arc B570.

Q: What does the percentile ranking indicate?

A: The Arc B570 ranks in the 65th percentile of all GPUs, while the RTX 3060 Mobile ranks in the 62nd. This places both in the upper-middle range, but the Intel part is positioned slightly higher overall.

Architecture Differences

The Intel Arc B570 is built on the BMG-G21 chip using the Xe2-HPG architecture, part of the Battlemage generation (Arc 5). It is manufactured on a 5 nm process at TSMC, with 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1 million per mm². The NVIDIA GeForce RTX 3060 Mobile uses the GA106 chip with the Ampere architecture from the GeForce 30 Mobile generation. It is built on an 8 nm process at Samsung, with 12,000 million transistors on a 276 mm² die, for a density of 43.5 million per mm². The Arc B570 is the denser design by a wide margin.

The Arc B570 has 2304 shading units, 144 texture mapping units, and 80 raster output units. It includes 18 ray tracing cores. The RTX 3060 Mobile has 3840 shading units, 120 TMUs, and 48 ROPs, with 30 ray tracing cores and 120 tensor cores. The NVIDIA part has more shading units and more ray tracing cores, but fewer TMUs and ROPs. The Arc B570 does not list tensor core counts in the database, so direct AI acceleration comparison is not possible from the recorded data.

Memory architecture differs significantly. The Arc B570 uses 10 GB of GDDR6 on a 160-bit bus, delivering 380.0 GB/s of bandwidth. The RTX 3060 Mobile uses 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s. Despite the narrower bus, the Arc B570 achieves higher bandwidth due to faster memory clocks: 2375 MHz (19 Gbps effective) versus 1750 MHz (14 Gbps effective) for the NVIDIA part. The Arc B570 also has a larger memory pool, which matters for texture-heavy workloads and higher resolution rendering.

Compute rates reveal another layer. The Arc B570 lists FP32 throughput of 11.52 TFLOPS and FP16 of 23.04 TFLOPS (2:1 ratio). The RTX 3060 Mobile lists FP32 of 10.94 TFLOPS and FP16 of 10.94 TFLOPS (1:1 ratio). The Intel GPU has higher raw FP32 and much higher FP16 throughput, while the NVIDIA GPU treats FP16 as equal to FP32 rather than doubling it.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Arc B570 is a desktop card with a dual-slot form factor, a 272 mm length, and a 115 mm height. The RTX 3060 Mobile is a mobile part with no listed dimensions, no slot width, and portable-device-dependent display outputs. The Arc B570 outputs via 1x HDMI 2.1a and 3x DisplayPort 2.1, while the RTX 3060 Mobile relies on the host laptop for display connectivity.

Specification Differences

The Intel Arc B570 has a base clock of 2500 MHz and a boost clock of 2500 MHz, both fixed at the same value. The RTX 3060 Mobile has a base clock of 900 MHz and a boost clock of 1425 MHz. The Intel part runs at a much higher clock speed, though the NVIDIA GPU has a larger boost delta over its base.

Memory size differs: 10 GB for the Arc B570 versus 6 GB for the RTX 3060 Mobile. Memory bus width also differs, 160-bit versus 192-bit, but the Arc B570 still achieves higher bandwidth at 380.0 GB/s versus 336.0 GB/s. Effective memory speed is 19 Gbps for the Intel card and 14 Gbps for the NVIDIA card.

Shader configuration differs in count and ratio. The Arc B570 has 2304 shading units, 144 TMUs, and 80 ROPs. The RTX 3060 Mobile has 3840 shading units, 120 TMUs, and 48 ROPs. Pixel rate is 200.0 GPixel/s for the Arc B570 versus 68.40 GPixel/s for the RTX 3060 Mobile. Texture rate is 360.0 GTexel/s versus 171.0 GTexel/s. Both rates heavily favor the Intel GPU.

Power and form factor differ substantially. The Arc B570 has a TDP of 150 W, requires a single 8-pin power connector, and lists a suggested PSU of 450 W. The RTX 3060 Mobile has an 80 W TDP, no power connectors (it draws from the laptop platform), and no suggested PSU. The Arc B570 is a dual-slot desktop card with a 272 mm length and 115 mm height; the RTX 3060 Mobile has no recorded dimensions.

The Arc B570 connects via PCIe 4.0 x8, while the RTX 3060 Mobile uses PCIe 4.0 x16. The Intel card is currently listed as Active production status, while the NVIDIA mobile GPU is End-of-life. Release dates also diverge: the Arc B570 launched on 2025-01-15, while the RTX 3060 Mobile was released on 2021-01-11. The Arc B570 has a launch MSRP of 219 USD. The RTX 3060 Mobile has no recorded launch MSRP.

Where Each One Wins

The Intel Arc B570 wins in modern API workloads. Its 45.5% lead in 3DMark Steel Nomad DX12 and 20.5% lead in Geekbench Vulkan indicate strong performance in current and next-generation rendering paths. The 24.1% advantage in PassMark DirectX 12 reinforces this pattern. Users targeting DirectX 12 or Vulkan titles should favor the Arc B570.

The Arc B570 also wins in compute-heavy applications. Its 27.3% lead in PassMark GPU Compute and 5.1% lead in Geekbench OpenCL show an advantage in non-graphics workloads such as rendering, simulation, and data processing. The FP16 throughput of 23.04 TFLOPS (2:1) is double the FP32 rate, which can benefit workloads that use half-precision math.

The RTX 3060 Mobile wins only in PassMark DirectX 10, where it leads by 27.8%. This suggests the NVIDIA driver stack retains an advantage for legacy DirectX 10 applications. The RTX 3060 Mobile also has a much lower TDP at 80 W versus 150 W for the Arc B570, which matters in mobile contexts where power draw is constrained. The NVIDIA card's 3840 shading units and 120 tensor cores indicate a different compute resource allocation, though the benchmark data does not show a performance advantage from the higher shader count.

For memory-intensive workloads, the Arc B570 wins on capacity (10 GB versus 6 GB) and bandwidth (380.0 GB/s versus 336.0 GB/s). The faster 19 Gbps effective memory speed and the larger pool give it an edge in high-resolution textures and large datasets. The RTX 3060 Mobile's wider 192-bit bus does not compensate for the lower memory clock.

The Verdict

The data clearly favors the Intel Arc B570 for most use cases. It wins 9 of 10 head-to-head benchmarks, has a higher average score (20556 versus 18159), and ranks higher in the overall percentile distribution (65th versus 62nd). Its lead is largest in DirectX 12 and Vulkan workloads, the APIs that matter most for current gaming and professional rendering. The 45.5% margin in 3DMark Steel Nomad DX12 is the single most decisive result in the comparison.

Users who prioritize modern graphics APIs, compute throughput, or memory capacity should choose the Arc B570. It offers 10 GB of memory, 380.0 GB/s of bandwidth, and higher FP32 and FP16 compute rates. Its dual-slot desktop form factor and 150 W TDP make it suitable for desktop builds with a 450 W PSU. The launch MSRP of 219 USD provides a reference point for its market positioning.

The RTX 3060 Mobile is the better choice only in scenarios where legacy DirectX 10 performance is critical, where power draw must stay low, or where a mobile form factor is required. Its 80 W TDP and lack of power connectors make it a laptop-oriented part, and its End-of-life status limits its relevance for new purchases. For desktop users, the Arc B570 is the stronger performer across nearly every recorded metric. The single DirectX 10 win for NVIDIA does not outweigh the consistent advantages the Intel GPU demonstrates elsewhere.

DETAILED SPECIFICATIONS

SPECIFICATION
B570
RTX 3060 Mobile
Core Specs
Shading Units
2,304
3,840 +66.7%
Shaders
2,304
3,840 +66.7%
TMUs
144
120 -16.7%
ROPs
80
48 -40.0%
SM Count
30
Execution Units
18
Clocks
Base Clock
2500 MHz
900 MHz
Boost Clock
2500 MHz
1425 MHz
Memory Clock
2375 MHz 19 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
10 GB
6 GB
VRAM (MB)
10,240
6,144 -40.0%
Memory Type
GDDR6
GDDR6
Memory Bus
160 bit
192 bit
Bandwidth
380.0 GB/s
336.0 GB/s
Cache
L1 Cache
256 KB (per EU)
128 KB (per SM)
L2 Cache
13.5 MB
3 MB
Performance
Pixel Rate
200.0 GPixel/s
68.40 GPixel/s
Texture Rate
360.0 GTexel/s
171.0 GTexel/s
FP32 (TFLOPS)
11.52 TFLOPS
10.94 TFLOPS
FP64 (TFLOPS)
720.0 GFLOPS (1:16)
171.0 GFLOPS (1:64)
FP16 (TFLOPS)
23.04 TFLOPS (2:1)
10.94 TFLOPS (1:1)
AI/RT
RT Cores
18
30 +66.7%
Tensor Cores
120
XMX Cores
144
Power
TDP
150 W
80 W
TDP (W)
150
80 -46.7%
Suggested PSU
450 W
Power Connectors
1x 8-pin
None
Architecture
Architecture
Xe2-HPG
Ampere
GPU Name
BMG-G21
GA106
Generation
Battlemage (Arc 5)
GeForce 30 Mobile
Process Size
5 nm
8 nm
Transistors
19,600 million
12,000 million
Die Size
272 mm²
276 mm²
Foundry
TSMC
Samsung
Density
72.1M / mm²
43.5M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.6
Shader Model
6.6
6.8
Physical
Slot Width
Dual-slot
Length
272 mm 10.7 inches
Height
115 mm 4.5 inches
Outputs
1x HDMI 2.1a3x DisplayPort 2.1
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Other
Launch Price
219 USD
Production
Active
End-of-life
Predecessor
Alchemist
GeForce 20 Mobile
View Arc B570 Details View GeForce RTX 3060 Mobile Details