Intel Arc Pro B370 vs Intel Arc Pro B60 Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark results for the Intel Arc Pro B370 and the Intel Arc Pro B60. The database shows zero wins for each part in a direct comparison, which is a significant finding in itself. The B370 has no benchmark entries, while the B60 carries an average benchmark score of 3182 across eight tests.

The B60's benchmark profile is instructive. In 3DMark Steel Nomad DX12, it scores 2646. PassMark G3D shows 14580, while PassMark GPU Compute is 7029. Legacy DirectX tests are lower: DirectX 9 scores 179, DirectX 11 scores 122, DirectX 10 scores 61, and DirectX 12 scores 76. The G2D score is 763. These figures place the B60 at the 20th percentile among all GPUs in the database.

The nearest rivals for the B60 clarify its standing. The NVIDIA Quadro P1000 scores 3163, a delta of 0.6% above the B60. The NVIDIA GeForce GT 640 scores 3210, which is 0.9% below the B60. The NVIDIA GeForce 920M scores 3287, a 3.2% gap. Interestingly, the NVIDIA GeForce RTX 5080 SUPER scores 3075, which is 3.5% lower than the B60. This places the B60 in a narrow band of mid-range performance, roughly equivalent to older or lower-tier discrete GPUs.

Because the B370 has no benchmark scores, no percentile rank, and no rival data, the analysis cannot quantify its performance. The B370 does have theoretical throughput figures. Its FP32 is 6.144 TFLOPS, its texture rate is 96.00 GTexel/s, and its pixel rate is 48.00 GPixel/s. The B60 doubles these figures exactly: FP32 is 12.29 TFLOPS, texture rate is 384.0 GTexel/s, and pixel rate is 192.0 GPixel/s. That 2:1 ratio in FP32, a 4:1 ratio in texture rate, and a 4:1 ratio in pixel rate suggests the B60 has substantially more raw execution resources.

The absence of direct measurements means the comparison rests on architectural and specification differences rather than empirical wins. The data shows the B60 has a clear specification advantage in almost every measurable category, but the B370's integrated nature and much lower power envelope point to a different design goal.

The Verdict

The benchmark data indicates the Intel Arc Pro B60 is the performance-focused part. Its average benchmark score of 3182 places it at the 20th percentile, which is modest but real. The B370, with no recorded benchmarks, cannot be positioned on the same scale. The B60 delivers 12.29 TFLOPS FP32, 24 GB of GDDR6 memory at 456.0 GB/s, and a 192-bit bus. The B370 relies on system shared memory with system dependent bandwidth, and its FP32 is exactly half at 6.144 TFLOPS.

For workloads that require sustained compute, the B60 is the data-supported choice. It has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. Every resource count is exactly double or less on the B370. The B60 also uses a dual-slot form factor with a 1x 8-pin power connector and a suggested 550 W PSU, while the B370 is an IGP with no power connectors and a 25 W TDP.

The B370 targets integrated graphics scenarios. Its 25 W TDP is one-eighth of the B60's 200 W TDP. The B370 has a base clock of 300 MHz and a boost of 2400 MHz. The B60 has a base clock of 2000 MHz and the same 2400 MHz boost. The B60's sustained base clock is far higher, indicating it can maintain performance without the power constraints of an IGP.

The verdict from the data is straightforward: the B60 for discrete, high-throughput tasks, the B370 for low-power integrated deployment. The B60's launch MSRP is 499 USD. No price data exists for the B370.

Architecture Differences

The two GPUs come from different architectural families. The Intel Arc Pro B370 uses the Xe3-LPG architecture on a 3 nm process node, fabricated by Intel. Its chip is Panther Lake, and it belongs to the Arc Graphics-WM generation. The Intel Arc Pro B60 uses the Xe2-HPG architecture on a 5 nm process node, fabricated by TSMC. Its chip is BMG-G21, and it belongs to the Battlemage Pro Series.

The process node difference is significant. The B370's 3 nm node is a newer lithography compared to the B60's 5 nm node. The B60's die size is 272 mm², with 19,600 million transistors and a transistor density of 72.1M per mm². The B370's transistor count and die size are listed as unknown, so no direct density comparison is possible.

The memory architecture is another major divergence. The B370 uses system shared memory, meaning it has no dedicated VRAM. Its memory type, bus width, and bandwidth are all system dependent. The B60 has 24 GB of GDDR6 memory on a 192-bit bus, delivering 456.0 GB/s of bandwidth. The memory clock is 2375 MHz, with 19 Gbps effective.

The API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B370's bus interface is IGP, while the B60 uses PCIe 5.0 x8. Display outputs differ: the B370 is portable device dependent, while the B60 has 4x mini-DisplayPort 2.1.

The B60's predecessor is listed as null, while the B370's predecessor is HD Graphics-WM. Neither has a successor. The B370's production status is active, and so is the B60's. The B370 released on 2026-01-26, while the B60 released on 2025-09-04.

FAQ

Q: Which GPU has a higher FP32 compute throughput?

A: The Intel Arc Pro B60 delivers 12.29 TFLOPS FP32, which is exactly double the 6.144 TFLOPS of the Intel Arc Pro B370.

Q: Does the B60 have dedicated video memory?

A: Yes. The B60 has 24 GB of GDDR6 memory on a 192-bit bus with 456.0 GB/s bandwidth. The B370 uses system shared memory with system dependent bandwidth.

Q: What is the power consumption difference?

A: The B60 has a TDP of 200 W and requires a 1x 8-pin power connector and a suggested 550 W PSU. The B370 has a TDP of 25 W and uses no power connectors as an IGP.

Q: How do their benchmark scores compare?

A: The B60 has an average benchmark score of 3182 across eight tests. The B370 has no recorded benchmark scores in the database, so no direct numerical comparison exists.

Q: Which GPU has more shading units and RT cores?

A: The B60 has 2560 shading units and 20 RT cores. The B370 has 1280 shading units and 10 RT cores, exactly half of the B60's counts.

Q: What are the form factor differences?

A: The B60 is a dual-slot card with dimensions of 167 mm length, 69 mm height, and 40 mm width. The B370 is an IGP with no listed dimensions and a portable device dependent display output.

Where Each One Wins

The Intel Arc Pro B60 wins in every category where the database records performance metrics. Its FP32 throughput of 12.29 TFLOPS is double the B370's 6.144 TFLOPS. Its texture rate of 384.0 GTexel/s is four times the B370's 96.00 GTexel/s. Its pixel rate of 192.0 GPixel/s is four times the B370's 48.00 GPixel/s. The B60 also has twice the shading units, four times the TMUs, four times the ROPs, and twice the RT cores.

The B60's memory subsystem is a clear advantage. With 24 GB of dedicated GDDR6 and 456.0 GB/s bandwidth, it avoids the system dependent bandwidth of the B370's shared memory. The B60's base clock of 2000 MHz is far higher than the B370's 300 MHz base clock, though both boost to 2400 MHz.

The Intel Arc Pro B370 wins in power efficiency and integration. Its 25 W TDP is one-eighth of the B60's 200 W. It requires no power connectors, no PCIe slot, and no suggested PSU. Its 3 nm process node, fabricated by Intel, is a newer lithography than the B60's 5 nm TSMC node. The B370 is an IGP, meaning it fits into portable devices with system dependent display outputs. The B60 is a dual-slot discrete card with 4x mini-DisplayPort 2.1.

For compute-heavy workloads like GPU compute, the B60's PassMark GPU Compute score of 7029 confirms its capability. For legacy DirectX tasks, the B60's scores range from 61 to 179. The B370 has no such data. The B60's 3DMark Steel Nomad DX12 score of 2646 shows it can handle modern DX12 workloads. The B370's absence from these tests means its wins are limited to lower power draw and integrated form factor advantages.

Specification Differences

The two GPUs differ in nearly every specification field. The process node is 3 nm for the B370 versus 5 nm for the B60. The foundry is Intel for the B370 and TSMC for the B60. The B60 has a known transistor count of 19,600 million and a die size of 272 mm², while the B370 lists both as unknown.

Clock speeds differ at base: the B370 runs at 300 MHz, the B60 at 2000 MHz. Both boost to 2400 MHz. Memory is system shared for the B370, while the B60 has 24 GB GDDR6 at 2375 MHz with 19 Gbps effective. The B370's memory bus is system shared, the B60's is 192 bit. Bandwidth is system dependent for the B370, 456.0 GB/s for the B60.

Compute resources: the B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The B60 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The B370's pixel rate is 48.00 GPixel/s and texture rate is 96.00 GTexel/s. The B60's are 192.0 GPixel/s and 384.0 GTexel/s. FP32 is 6.144 TFLOPS versus 12.29 TFLOPS. FP16 is 12.29 TFLOPS versus 24.58 TFLOPS, both at 2:1 ratio.

Power and form factor: the B370 has a 25 W TDP, IGP slot width, no power connectors, and no suggested PSU. The B60 has a 200 W TDP, dual-slot width, 1x 8-pin power connector, and a suggested 550 W PSU. The B370's bus interface is IGP, the B60's is PCIe 5.0 x8. Display outputs are portable device dependent for the B370, 4x mini-DisplayPort 2.1 for the B60.

Dimensions exist only for the B60: 167 mm length, 69 mm height, 40 mm width. The B370 has null dimensions. The release dates differ by months: the B60 on 2025-09-04, the B370 on 2026-01-26. The B370 has a predecessor, HD Graphics-WM. The B60 has no predecessor. The B60 has a launch MSRP of 499 USD; the B370 has none.