Intel Arc B370 vs NVIDIA GeForce RTX 4060 Comparison

The Verdict

The recorded data positions the NVIDIA GeForce RTX 4060 as the clear performance leader in this comparison. In the single shared benchmark, 3DMark Steel Nomad DX12, the RTX 4060 scores 2302 against the Intel Arc B370's 1184, a 48.6% advantage. The RTX 4060 sits at the 61st percentile among all GPUs in the database, while the Intel Arc B370 sits at only the 5th percentile. The Arc B370's average benchmark score is 1184, while the RTX 4060's average is 17639, a massive gap that reflects both the breadth of benchmarks recorded for the NVIDIA part and its superior raw performance.

The Intel Arc B370 is an integrated graphics processor (IGP) with a 25 W TDP, designed for portable devices. The NVIDIA GeForce RTX 4060 is a dual-slot discrete card with a 115 W TDP and a suggested 300 W power supply. The data shows these are not competing products for the same buyer. The Arc B370 belongs in thin, power-constrained systems where its 3 nm process and low power draw matter more than raw frame rates. The RTX 4060 is for a desktop or larger laptop chassis that can accommodate a 240 mm long, dual-slot card with a 12-pin power connector.

The RTX 4060 also offers a much richer benchmark profile. The database records ten benchmark results for the RTX 4060, spanning OpenCL, Vulkan, DirectX 9 through 12, and compute workloads. The Arc B370 has only a single recorded 3DMark result. For any application that can use the RTX 4060's 8 GB of dedicated GDDR6 memory, the choice is unambiguous. The verdict from the data: the RTX 4060 is the performance part, and the Arc B370 is a low-power integrated solution for different use cases.

Architecture Differences

The two GPUs come from different manufacturers and use fundamentally different underlying designs. The Intel Arc B370 uses the Xe3-LPG architecture on a 3 nm process node from Intel's own foundry. Its chip is codenamed Panther Lake, and it belongs to the Arc Graphics-M (Panther Lake) generation. The RTX 4060 uses NVIDIA's Ada Lovelace architecture on a 5 nm process node from TSMC, built around the AD107 chip.

The RTX 4060's chip contains 18,900 million transistors on a 159 mm² die, giving a transistor density of 118.9M per mm². The Arc B370's transistor count and die size are listed as unknown in the database, so no direct density comparison is possible. The RTX 4060 relies on dedicated GDDR6 memory: 8 GB on a 128-bit bus with 272.0 GB/s bandwidth. The Arc B370 uses System Shared memory, with bandwidth described as System Dependent. This is a critical architectural difference: the RTX 4060 has its own high-speed memory pool, while the Arc B370 must share system memory and its bandwidth varies with the host platform.

Compute resources differ substantially. The RTX 4060 has 3072 shading units, 96 texture mapping units, 48 ROPs, 24 ray tracing cores, and 96 tensor cores. The Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores; its tensor core count is not recorded. The RTX 4060 delivers 15.11 TFLOPS of FP32 and 15.11 TFLOPS of FP16 with a 1:1 ratio. The Arc B370 delivers 6.144 TFLOPS of FP32 and 12.29 TFLOPS of FP16 with a 2:1 ratio. The NVIDIA part has more than twice the FP32 throughput and a different FP16 strategy.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 4060 uses a PCIe 4.0 x8 bus interface, while the Arc B370 is an IGP with no separate bus interface. The RTX 4060 has dedicated display outputs (1x HDMI 2.1 and 3x DisplayPort 1.4a), while the Arc B370's display outputs are Portable Device Dependent. Clock behavior also differs: the Arc B370 has a 300 MHz base and 2400 MHz boost, while the RTX 4060 has a 1830 MHz base and 2460 MHz boost.

Where Each One Wins

The RTX 4060 wins in every recorded benchmark category. In 3DMark Steel Nomad DX12, it scores 2302 versus 1184 for the Arc B370, a 48.6% lead. The RTX 4060's additional benchmark results show strength across compute and legacy APIs: Geekbench OpenCL scores 95057, Geekbench Vulkan scores 48643, and Passmark GPU Compute scores 9213. These are not just gaming wins; they indicate general compute capability that the Arc B370 cannot match based on the recorded data.

The Arc B370's domain is power efficiency and integration. At 25 W TDP, it draws a fraction of the RTX 4060's 115 W. It requires no power connectors, no cooling slot beyond the IGP form factor, and no separate power supply recommendation. The RTX 4060 needs a 1x 12-pin connector and a suggested 300 W power supply. The Arc B370 is a 3 nm part, while the RTX 4060 is 5 nm, which contributes to the power disparity.

For portable devices, the Arc B370 is the only viable option between the two: an IGP cannot be installed into a discrete slot. The RTX 4060's 240 mm length, 111 mm height, and 40 mm width, along with its dual-slot profile, restrict it to larger systems. The Arc B370's production status is Active, while the RTX 4060 is End-of-life, with a release date of 2023-05-17 and a successor in the GeForce 50 series. The Arc B370's release date is 2026-01-26.

FAQ

Q: Which GPU is faster in 3DMark Steel Nomad DX12?

A: The NVIDIA GeForce RTX 4060 scores 2302, which is 48.6% higher than the Intel Arc B370's 1184 in the same test.

Q: How much memory does each GPU have?

A: The RTX 4060 has 8 GB of dedicated GDDR6 memory on a 128-bit bus with 272.0 GB/s bandwidth. The Arc B370 uses System Shared memory with System Dependent bandwidth.

Q: What is the power consumption difference?

A: The Arc B370 has a 25 W TDP and requires no power connectors. The RTX 4060 has a 115 W TDP and requires a 1x 12-pin power connector with a suggested 300 W power supply.

Q: Are these GPUs in the same performance percentile?

A: No. The RTX 4060 is at the 61st percentile among all GPUs, while the Arc B370 is at the 5th percentile.

Q: What are the nearest rivals for each GPU in the database?

A: The Arc B370's nearest rivals are the ATI Mobility Radeon HD 5570 (1186 average score, 0.2% ahead), ATI Radeon HD 5770 (1190, 0.5% ahead), and AMD Radeon HD 7650M (1192, 0.7% ahead). The RTX 4060's nearest rivals are the AMD Radeon HD 7790 (17666, 0.2% ahead), AMD Radeon 780M (17588, 0.3% behind), and AMD Radeon Pro 560 (17551, 0.5% behind).

Q: What is the production status of each GPU?

A: The Arc B370 is Active. The RTX 4060 is End-of-life, released on 2023-05-17, with the GeForce 50 as its successor.

Head-to-Head Benchmarks

The database records only one head-to-head benchmark between these two GPUs: 3DMark Steel Nomad DX12. The RTX 4060 wins with a score of 2302 against the Arc B370's 1184. The delta is -48.6% from the Arc B370's perspective, meaning the Intel part scores just under half of the NVIDIA part.

This single result aligns with the broader benchmark gap. The RTX 4060's average benchmark score across all recorded tests is 17639, while the Arc B370's average is 1184. The RTX 4060's nearest rival, the AMD Radeon HD 7790, averages 17666, only 0.2% higher. The Arc B370's nearest rival, the ATI Mobility Radeon HD 5570, averages 1186, only 0.2% higher. The Arc B370 performs at a level comparable to decade-old integrated and low-end discrete graphics, while the RTX 4060 performs at a level comparable to mid-range desktop cards.

The RTX 4060's additional benchmarks provide context for its strengths. Passmark G3D scores 19545, Passmark G2D scores 1037, and Passmark DirectX 11 scores 175. The Arc B370 has no recorded results in these tests. Geekbench OpenCL at 95057 and Vulkan at 48643 suggest strong compute and modern API performance. The Arc B370's single 3DMark result cannot be compared across these workloads.

The delta between the two in the shared test, 48.6%, is the only direct head-to-head measurement available. It confirms the percentile gap: 61st versus 5th. No other head-to-head benchmarks exist in the database, so the conclusion rests on this one test plus the RTX 4060's broader benchmark suite.

Specification Differences

The two GPUs differ in nearly every recorded specification. The Arc B370 uses a 3 nm process from Intel; the RTX 4060 uses a 5 nm process from TSMC. The RTX 4060's chip has 18,900 million transistors on a 159 mm² die with a density of 118.9M per mm²; the Arc B370's transistor count and die size are unknown.

The Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The RTX 4060 has 3072 shading units, 96 TMUs, 48 ROPs, 24 ray tracing cores, and 96 tensor cores. The Arc B370 has no recorded tensor core count. The RTX 4060's pixel rate is 118.1 GPixel/s and texture rate is 236.2 GTexel/s. The Arc B370's pixel rate is 48.00 GPixel/s and texture rate is 96.00 GTexel/s.

FP32 performance is 6.144 TFLOPS for the Arc B370 versus 15.11 TFLOPS for the RTX 4060. FP16 is 12.29 TFLOPS (2:1) for the Arc B370 versus 15.11 TFLOPS (1:1) for the RTX 4060. The RTX 4060 has more than double the FP32 throughput and a different FP16 ratio.

Memory is another major split. The Arc B370 uses System Shared memory with System Dependent bandwidth. The RTX 4060 has 8 GB GDDR6, a 128-bit bus, and 272.0 GB/s bandwidth. The Arc B370's memory clock is listed as System Shared; the RTX 4060's memory clock is 2125 MHz with 17 Gbps effective.

The TDP is 25 W for the Arc B370 versus 115 W for the RTX 4060. The Arc B370 is an IGP with no power connectors and no suggested PSU. The RTX 4060 is dual-slot, uses a 1x 12-pin connector, and suggests a 300 W power supply. The Arc B370's bus interface is IGP; the RTX 4060 uses PCIe 4.0 x8.

Physical dimensions are recorded only for the RTX 4060: 240 mm length, 111 mm height, and 40 mm width. The Arc B370's dimensions are null in the database. Display outputs are Portable Device Dependent for the Arc B370; the RTX 4060 has 1x HDMI 2.1 and 3x DisplayPort 1.4a.

Release dates differ by more than two and a half years. The RTX 4060 launched on 2023-05-17 with a launch MSRP of 299 USD. The Arc B370 launched on 2026-01-26 with no recorded MSRP. The RTX 4060's predecessor is GeForce 30 and its successor is GeForce 50. The Arc B370 has no recorded predecessor or successor. The RTX 4060 is End-of-life; the Arc B370 is Active. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.