Intel Arc Pro B60 vs NVIDIA GeForce RTX 5070 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a clear and consistent sweep across all seven head-to-head benchmark comparisons, with the NVIDIA GeForce RTX 5070 Mobile winning every test. The largest margin appears in the DirectX 10 test, where the NVIDIA part scores 129 against the Intel Arc Pro B60's 61, a 52.7% deficit for Intel. This is a substantial gap, indicating that the Intel GPU's legacy DirectX performance lags considerably behind the newer architecture.

The DirectX 11 test follows a similar pattern. The RTX 5070 Mobile posts 192 points, while the Arc Pro B60 manages 122, a 36.5% difference. The gap narrows somewhat in DirectX 12, where the scores are 93 versus 76, a 18.3% difference, but the NVIDIA part still holds a clear advantage. The DirectX 9 result shows 214 versus 179, a 16.4% gap, suggesting that even in older APIs, the RTX 5070 Mobile maintains its lead.

The 2D graphics test (PassMark G2D) shows a smaller but still meaningful difference: 896 for the NVIDIA part against 763 for the Intel part, a 14.8% gap. The compute-oriented PassMark GPU Compute test also favors NVIDIA, with 8279 versus 7029, a 15.1% difference. The most important overall score, PassMark G3D, shows the RTX 5070 Mobile at 20355 versus 14580 for the Arc Pro B60, a 28.4% deficit for Intel. This G3D score is often considered a general indicator of gaming and 3D rendering performance, and the data indicates the NVIDIA part is substantially stronger in this regard.

The average benchmark score (calculated across all recorded tests in the database) reinforces this picture. The RTX 5070 Mobile has an average score of 29928, while the Intel Arc Pro B60 has an average of 3182. This is a massive difference, but it is important to note that these averages are calculated over different test sets; the Intel part's average is dominated by its PassMark tests, while the NVIDIA part includes Geekbench OpenCL and Vulkan results, which score much higher numerically. Therefore, the head-to-head tests, where both parts run the same PassMark suite, provide the more reliable comparison.

Looking at the percentile rankings, the RTX 5070 Mobile sits in the 75th percentile of all GPUs in the database, while the Arc Pro B60 is in the 20th percentile. The nearest rivals for the NVIDIA part are the GeForce RTX 3070 Ti (average score 29945, a 0.1% difference) and the RTX 2080 Ti (29783, a 0.5% difference). This places the RTX 5070 Mobile in the same performance class as those desktop parts. The Intel Arc Pro B60's nearest rivals are the Quadro P1000 (3163, a 0.6% difference) and the GeForce GT 640 (3210, a 0.9% difference), placing it in a much lower performance tier.

FAQ

Q: Which GPU wins the most head-to-head benchmark tests?

A: The NVIDIA GeForce RTX 5070 Mobile wins all seven recorded head-to-head tests, covering DirectX 9 through DirectX 12, 2D, 3D, and compute workloads.

Q: What is the largest performance gap between the two in any single test?

A: The largest gap is in the PassMark DirectX 10 test, where the NVIDIA part scores 129 and the Intel part scores 61, a 52.7% difference in favor of NVIDIA.

Q: How does the Intel Arc Pro B60 compare to its nearest rivals in average benchmark score?

A: The Intel part has an average score of 3182, which is 0.6% above the Quadro P1000 (3163) and 0.9% below the GeForce GT 640 (3210). The data places it in a similar performance class to those older cards.

Q: How does the NVIDIA GeForce RTX 5070 Mobile compare to its nearest rivals?

A: The RTX 5070 Mobile has an average score of 29928. Its closest rival is the RTX 3070 Ti at 29945 (a 0.1% difference), followed by the RTX 2080 Ti at 29783 (a 0.5% difference). The data shows it is essentially on par with those parts.

Q: Which GPU has a higher 3D graphics score in the PassMark suite?

A: The NVIDIA GeForce RTX 5070 Mobile achieves a PassMark G3D score of 20355, while the Intel Arc Pro B60 scores 14580, a 28.4% difference.

Q: What are the percentile rankings for each GPU?

A: The NVIDIA GeForce RTX 5070 Mobile is in the 75th percentile of all GPUs in the database, while the Intel Arc Pro B60 is in the 20th percentile.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc Pro B60 is built on the Xe2-HPG architecture, part of the Battlemage generation, specifically the Pro Series. It uses the BMG-G21 chip. The NVIDIA GeForce RTX 5070 Mobile uses the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation, built on the GB206 chip.

Both are fabricated on a 5 nm process at TSMC, but the similarities end there. The Intel chip has a die size of 272 mm² and contains 19,600 million transistors, resulting in a transistor density of 72.1M per mm². The NVIDIA chip is smaller at 181 mm² but packs more transistors, 21,900 million, leading to a higher density of 121.0M per mm².

The core configurations differ significantly. The Intel part has 2560 shading units, 160 texture mapping units, and 80 raster output units. It also includes 20 ray tracing cores. The NVIDIA part has 4608 shading units, 144 TMUs, and 48 ROPs, with 36 RT cores and 144 tensor cores. The NVIDIA part has no tensor core counterpart on the Intel side, as the data does not list any for the Arc Pro B60.

Clock speeds show a stark contrast. The Intel part has a base clock of 2000 MHz and a boost clock of 2400 MHz. The NVIDIA part has a much lower base of 907 MHz and a boost of 1425 MHz. The Intel part also has higher pixel and texture rates: 192.0 GPixel/s and 384.0 GTexel/s, versus 68.40 GPixel/s and 205.2 GTexel/s for the NVIDIA part. However, the NVIDIA part has a higher FP32 compute rating at 13.13 TFLOPS compared to 12.29 TFLOPS for Intel. The FP16 rating also differs: Intel provides 24.58 TFLOPS at a 2:1 ratio, while NVIDIA provides 13.13 TFLOPS at a 1:1 ratio.

Memory architecture is another major differentiator. The Intel Arc Pro B60 uses 24 GB of GDDR6 memory on a 192-bit bus, delivering 456.0 GB/s of bandwidth. The NVIDIA part uses 8 GB of GDDR7 memory on a 128-bit bus, providing 384.0 GB/s. The Intel part has a larger memory pool and higher bandwidth, while the NVIDIA part uses a newer memory type.

The Verdict

The benchmark data indicates that the NVIDIA GeForce RTX 5070 Mobile is the stronger performer in every measured workload within this comparison. The 75th percentile ranking versus the 20th percentile for the Intel part, combined with the 28.4% lead in G3D and the 52.7% lead in DirectX 10, establishes a clear performance hierarchy. The RTX 5070 Mobile also lands in the same performance class as desktop parts like the RTX 3070 Ti and RTX 2080 Ti, which is a notable data point.

The Intel Arc Pro B60, however, is not without its own advantages in the recorded specifications. It offers a significantly larger memory capacity of 24 GB versus 8 GB, and higher memory bandwidth at 456.0 GB/s versus 384.0 GB/s. Its pixel and texture rates are also much higher, at 192.0 GPixel/s and 384.0 GTexel/s, which could be relevant for certain rasterization-heavy workloads. Its power envelope is also different, with a 200 W TDP versus 50 W for the NVIDIA part, indicating a different target use case.

The verdict from the data is that the RTX 5070 Mobile is the choice for raw performance, particularly in 3D rendering and legacy API compatibility. The Intel part, with its larger memory and higher fill rates, may be more suited for workloads that require large data sets in memory, but the overall compute and graphics scores do not favor it. The data does not support a scenario where the Intel part wins on measured performance; it wins only on certain specification fields like memory size and texture throughput.

Specification Differences

The following table lists the fields where the two GPUs differ in their recorded specifications.

| Field | Intel Arc Pro B60 | NVIDIA GeForce RTX 5070 Mobile |

| :--- | :--- | :--- |

| Architecture | Xe2-HPG | Blackwell 2.0 |

| Generation | Battlemage (Pro Series) | GeForce 50 Mobile |

| Chip | BMG-G21 | GB206 |

| Transistors | 19,600 million | 21,900 million |

| Die Size | 272 mm² | 181 mm² |

| Transistor Density | 72.1M / mm² | 121.0M / mm² |

| Base Clock | 2000 MHz | 907 MHz |

| Boost Clock | 2400 MHz | 1425 MHz |

| Memory Clock | 2375 MHz 19 Gbps effective | 1500 MHz 24 Gbps effective |

| Memory Size | 24 GB | 8 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 456.0 GB/s | 384.0 GB/s |

| Shading Units | 2560 | 4608 |

| TMUs | 160 | 144 |

| ROPs | 80 | 48 |

| RT Cores | 20 | 36 |

| Tensor Cores | Not listed | 144 |

| Pixel Rate | 192.0 GPixel/s | 68.40 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 205.2 GTexel/s |

| FP32 | 12.29 TFLOPS | 13.13 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 13.13 TFLOPS (1:1) |

| TDP | 200 W | 50 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 550 W | Not listed |

| Bus Interface | PCIe 5.0 x8 | PCIe 5.0 x16 |

| Display Outputs | 4x mini-DisplayPort 2.1 | Portable Device Dependent |

| Dimensions | 167 mm 6.6 inches | Not listed |

| Release Date | 2025-09-04 | 2025-04-14 |

| Predecessor | Not listed | GeForce 40 Mobile |

| Launch MSRP | 499 USD | Not listed |

Where Each One Wins

Based strictly on the benchmark results, the NVIDIA GeForce RTX 5070 Mobile wins in all seven recorded head-to-head tests. Its most significant wins are in DirectX 10 (52.7% ahead), DirectX 11 (36.5% ahead), and the G3D test (28.4% ahead). The data indicates this is the superior choice for any workload measured by these tests, including legacy DirectX titles, modern 3D rendering, and general compute tasks. Its percentile ranking of 75 also places it in a higher performance tier overall.

The Intel Arc Pro B60 wins no head-to-head benchmark tests. However, the specification data shows it has advantages in memory capacity (24 GB versus 8 GB), memory bandwidth (456.0 GB/s versus 384.0 GB/s), pixel rate (192.0 GPixel/s versus 68.40 GPixel/s), and texture rate (384.0 GTexel/s versus 205.2 GTexel/s). These fields suggest that for workloads that are heavily dependent on memory storage or raw fill rates, such as large texture datasets or certain compute tasks that fit in memory, the Intel part may have a use case. The data, however, does not provide a benchmark test that isolates these advantages, so the practical impact is not measured. The Intel part also has a higher FP16 throughput at 24.58 TFLOPS, which could be relevant for half-precision compute, but the NVIDIA part's FP32 is higher at 13.13 TFLOPS. The Intel part is a dual-slot desktop card with a 200 W TDP, while the NVIDIA part is an integrated graphics processor (IGP) for portable devices with a 50 W TDP, indicating very different physical deployment scenarios.