Intel Arc Pro B60 Dual vs NVIDIA GeForce RTX 4070 SUPER Comparison

Head-to-Head Benchmarks

The recorded data provides a clear performance picture for the NVIDIA GeForce RTX 4070 SUPER, while the Intel Arc Pro B60 Dual has no individual benchmark scores listed in the database. This makes direct numerical comparisons impossible for most tests. Instead, the analysis must focus on the RTX 4070 SUPER’s measured results and the architectural specifications that define the Intel card’s expected behavior.

The RTX 4070 SUPER delivers a 3DMark Steel Nomad DX12 score of 4627, which places it in the 83rd percentile among all GPUs in the database. Its average benchmark score across all recorded tests is 43223. The nearest rivals in the database confirm its positioning: the NVIDIA Quadro M6000 24 GB scores 43262, which is 0.1% ahead, the NVIDIA GeForce RTX 5050 Mobile scores 43268, also 0.1% ahead, the NVIDIA Quadro M6000 scores 43301, 0.2% ahead, and the NVIDIA GeForce RTX 4090 Mobile scores 43667, which is 1% ahead. These deltas are small, indicating that the RTX 4070 SUPER sits in a tightly contested performance band.

In Geekbench compute tests, the RTX 4070 SUPER records an OpenCL score of 172795 and a Vulkan score of 205624. These are strong numbers for a desktop GPU in the 40-series lineup. The PassMark suite shows a G3D score of 29995, a GPU compute score of 17108, and a G2D score of 1184. For legacy DirectX tests, the card scores 344 in DirectX 9, 273 in DirectX 11, 167 in DirectX 10, and 110 in DirectX 12. The DirectX 12 PassMark score of 110 appears low relative to the 3DMark Steel Nomad result, but the two tests measure different workloads and API paths.

The Intel Arc Pro B60 Dual has an average benchmark score of 0 and sits in the 50th percentile, with no recorded benchmark entries. The head-to-head benchmark array is empty, and wins count as 0 for both cards. This means the database currently offers no direct measured comparison. What can be compared is the theoretical throughput derived from specifications. The RTX 4070 SUPER delivers 35.48 TFLOPS FP32 performance, while the Arc Pro B60 Dual delivers 12.29 TFLOPS FP32. That is a substantial difference, roughly 2.9 times higher for the NVIDIA card in raw shader throughput. The RTX 4070 SUPER also leads in texture rate with 554.4 GTexel/s versus 384.0 GTexel/s for the Intel card. Pixel rates are closer: 198.0 GPixel/s for the RTX 4070 SUPER versus 192.0 GPixel/s for the Arc Pro B60 Dual.

Memory bandwidth favors the RTX 4070 SUPER at 504.2 GB/s, compared to 456.0 GB/s for the Intel card. However, the Intel card has twice the memory capacity at 24 GB versus 12 GB. This capacity advantage matters in professional workloads with large datasets, but the bandwidth deficit still limits overall throughput. The RTX 4070 SUPER also has significantly more shading units at 7168 versus 2560, more texture mapping units at 224 versus 160, and more ray tracing cores at 56 versus 20. The NVIDIA card includes 224 tensor cores, while the Intel card lists none.

The Verdict

The data shows that the RTX 4070 SUPER is the stronger performer in almost every measured and specification-based metric. Its 83rd percentile ranking versus the Intel card’s 50th percentile ranking confirms this. The RTX 4070 SUPER’s average benchmark score of 43223 puts it in the same class as the Quadro M6000 variants and the RTX 4090 Mobile, all within 1% of each other. The Intel Arc Pro B60 Dual, with no recorded scores, cannot compete on measured performance.

The RTX 4070 SUPER also leads in raw compute. Its FP32 throughput of 35.48 TFLOPS is nearly three times the Intel card’s 12.29 TFLOPS. Texture rate is 44% higher, and pixel rate is 3% higher. The NVIDIA card has more shading units, more ROPs at parity (80 each), more ray tracing cores, and the only tensor cores in this comparison. The RTX 4070 SUPER is also more power efficient in terms of performance per watt, though the data does not provide direct efficiency ratios. Its TDP is 220 W versus 400 W for the Intel card, and its suggested PSU is 550 W versus 800 W.

The Intel card’s advantages are limited to memory capacity, with 24 GB versus 12 GB, and a smaller die size at 272 mm² versus 294 mm². It also uses a PCIe 5.0 x8 interface, which offers higher per-lane bandwidth than the RTX 4070 SUPER’s PCIe 4.0 x16, though the practical impact depends on workload. The Intel card has a higher transistor density at 72.1M per mm² versus 121.8M for NVIDIA, but that reflects the different chip designs. The RTX 4070 SUPER uses 35,800 million transistors versus 19,600 million for the Intel card.

For users prioritizing raw performance, the RTX 4070 SUPER is the clear choice based on the recorded data. For users needing large memory capacity in a professional context, the Intel card offers that advantage, but at the cost of significantly lower compute throughput. The RTX 4070 SUPER is also an active product with an end-of-life predecessor and successor, while the Intel card is currently active in production.

Where Each One Wins

The RTX 4070 SUPER wins in raw compute and rendering throughput. Its FP32 performance of 35.48 TFLOPS, texture rate of 554.4 GTexel/s, and pixel rate of 198.0 GPixel/s all exceed the Intel Arc Pro B60 Dual. The NVIDIA card also wins in memory bandwidth at 504.2 GB/s, which benefits high-resolution textures and data-intensive rendering. The 224 tensor cores provide hardware acceleration for AI workloads, a feature the Intel card lacks entirely. The 56 ray tracing cores versus 20 give the RTX 4070 SUPER a substantial advantage in ray-traced scenes.

The RTX 4070 SUPER also wins on power efficiency. Its 220 W TDP is 180 W lower than the Intel card’s 400 W TDP. The suggested PSU of 550 W versus 800 W means the NVIDIA card fits into more systems without requiring a PSU upgrade. The RTX 4070 SUPER is shorter at 267 mm versus 300 mm, making it easier to fit in compact cases. Its launch MSRP was 599 USD, which the database records.

The Intel Arc Pro B60 Dual wins on memory capacity with 24 GB versus 12 GB. This doubles the available VRAM for workloads such as large model inference, high-resolution video editing, or multi-monitor professional rendering. The Intel card also uses GDDR6 memory, which is generally more affordable than GDDR6X, though the database does not provide pricing for memory types. The Intel card has a wider display output configuration with 4x mini-DisplayPort 2.1, which supports newer display standards compared to the RTX 4070 SUPER’s 1x HDMI 2.1 and 3x DisplayPort 1.4a. The Intel card also uses a PCIe 5.0 x8 interface, which offers higher bandwidth per lane than PCIe 4.0 x16.

The Intel card is taller at 110 mm versus 112 mm, which is nearly identical. Its width is 40 mm versus 42 mm, making it slightly thinner. Both cards are dual-slot designs and use a single 16-pin power connector. The Intel card has a longer length, which may require careful case selection.

FAQ

Q: Which GPU has higher raw compute performance?

A: The NVIDIA GeForce RTX 4070 SUPER delivers 35.48 TFLOPS FP32, while the Intel Arc Pro B60 Dual delivers 12.29 TFLOPS FP32. The NVIDIA card is roughly 2.9 times faster in this metric.

Q: How does memory capacity compare between the two cards?

A: The Intel Arc Pro B60 Dual has 24 GB of GDDR6 memory, while the NVIDIA GeForce RTX 4070 SUPER has 12 GB of GDDR6X memory. The Intel card has double the capacity.

Q: Which card has higher memory bandwidth?

A: The NVIDIA GeForce RTX 4070 SUPER has 504.2 GB/s of bandwidth, compared to 456.0 GB/s for the Intel Arc Pro B60 Dual. The NVIDIA card leads by approximately 10%.

Q: What is the performance percentile for each card?

A: The NVIDIA GeForce RTX 4070 SUPER is in the 83rd percentile among all GPUs in the database. The Intel Arc Pro B60 Dual is in the 50th percentile.

Q: Which card has more ray tracing cores?

A: The NVIDIA GeForce RTX 4070 SUPER has 56 ray tracing cores, while the Intel Arc Pro B60 Dual has 20. The NVIDIA card has 2.8 times more.

Q: What are the power requirements for each card?

A: The NVIDIA GeForce RTX 4070 SUPER has a TDP of 220 W and a suggested PSU of 550 W. The Intel Arc Pro B60 Dual has a TDP of 400 W and a suggested PSU of 800 W.

Architecture Differences

The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage Pro Series generation. It is fabricated on a 5 nm process at TSMC with 19,600 million transistors on a 272 mm² die. The transistor density is 72.1 million per mm². The NVIDIA GeForce RTX 4070 SUPER uses the AD104 chip built on the Ada Lovelace architecture, part of the GeForce 40 generation. It is also fabricated on a 5 nm process at TSMC, but with 35,800 million transistors on a 294 mm² die. The transistor density is 121.8 million per mm².

The two architectures differ significantly in compute organization. The Intel card has 2560 shading units, 160 texture mapping units, and 80 ROPs. It includes 20 ray tracing cores and no tensor cores. The NVIDIA card has 7168 shading units, 224 texture mapping units, and 80 ROPs. It includes 56 ray tracing cores and 224 tensor cores. The NVIDIA architecture dedicates significant silicon to tensor operations, which the Intel card does not implement.

The memory architectures also differ. The Intel card uses 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The NVIDIA card uses 12 GB of GDDR6X on a 192-bit bus with 504.2 GB/s bandwidth. The memory clock for the Intel card is 2375 MHz with 19 Gbps effective speed, while the NVIDIA card runs at 1313 MHz with 21 Gbps effective speed. Both cards use a 192-bit bus, but the NVIDIA card achieves higher bandwidth through faster memory technology.

The clock speeds are similar. The Intel card has a base clock of 2000 MHz and a boost clock of 2400 MHz. The NVIDIA card has a base clock of 1980 MHz and a boost clock of 2475 MHz. The NVIDIA card boosts slightly higher, but the Intel card has a higher base clock. The FP16 throughput differs: the Intel card delivers 24.58 TFLOPS at a 2:1 ratio, while the NVIDIA card delivers 35.48 TFLOPS at a 1:1 ratio, meaning the NVIDIA card does not double its FP16 rate.

The bus interfaces differ. The Intel card uses PCIe 5.0 x8, while the NVIDIA card uses PCIe 4.0 x16. The PCIe 5.0 x8 interface provides the same total bandwidth as PCIe 4.0 x16, but the newer standard offers higher per-lane throughput. The display outputs differ as well: the Intel card provides 4x mini-DisplayPort 2.1, while the NVIDIA card provides 1x HDMI 2.1 and 3x DisplayPort 1.4a. Both cards support DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4.

Specification Differences

The NVIDIA GeForce RTX 4070 SUPER has a TDP of 220 W, while the Intel Arc Pro B60 Dual has a TDP of 400 W. The suggested PSU is 550 W for the NVIDIA card and 800 W for the Intel card. The NVIDIA card has a shorter length at 267 mm (10.5 inches) versus 300 mm (11.8 inches) for the Intel card. The heights are nearly identical at 112 mm (4.4 inches) for NVIDIA and 110 mm (4.3 inches) for Intel. The widths are 42 mm (1.7 inches) for NVIDIA and 40 mm (1.6 inches) for Intel. Both are dual-slot cards with a single 16-pin power connector.

The NVIDIA card has 7168 shading units, 224 texture mapping units, and 80 ROPs. The Intel card has 2560 shading units, 160 texture mapping units, and 80 ROPs. The NVIDIA card has 56 ray tracing cores and 224 tensor cores, while the Intel card has 20 ray tracing cores and no tensor cores. The NVIDIA card has a boost clock of 2475 MHz and a base clock of 1980 MHz. The Intel card has a boost clock of 2400 MHz and a base clock of 2000 MHz.

Memory specifications differ in capacity and type. The NVIDIA card has 12 GB of GDDR6X with 504.2 GB/s bandwidth. The Intel card has 24 GB of GDDR6 with 456.0 GB/s bandwidth. Both use a 192-bit bus. The NVIDIA card has a pixel rate of 198.0 GPixel/s and a texture rate of 554.4 GTexel/s. The Intel card has a pixel rate of 192.0 GPixel/s and a texture rate of 384.0 GTexel/s. The NVIDIA card delivers 35.48 TFLOPS FP32 and 35.48 TFLOPS FP16 (1:1). The Intel card delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1).

The NVIDIA card uses 35,800 million transistors on a 294 mm² die with a density of 121.8M per mm². The Intel card uses 19,600 million transistors on a 272 mm² die with a density of 72.1M per mm². The NVIDIA card has a production status of end-of-life, while the Intel card is active. The NVIDIA card was released on 2024-01-16, while the Intel card was released on 2025-09-04. The NVIDIA card has a predecessor named GeForce 30 and a successor named GeForce 50. The Intel card has no predecessor or successor listed. The NVIDIA card’s launch MSRP was 599 USD, while the Intel card’s launch MSRP was 1,199 USD.