Intel Arc A580 vs Intel Arc B370 Comparison

Intel Arc A580 vs Intel Arc B370

The database comparison between the Intel Arc A580 and the Intel Arc B370 reveals two graphics solutions with fundamentally different roles. The A580 is a discrete, dual-slot add-in card built on the Xe-HPG architecture with the DG2-512 chip, while the B370 is an integrated graphics processor (IGP) based on the Xe3-LPG architecture with the Panther Lake chip. The recorded benchmark data shows a decisive performance gap, with the A580 delivering a 3DMark Steel Nomad DX12 score of 2229 against the B370’s 1184, a delta of 88.3% in favor of the A580. This single head-to-head result frames the entire comparison, but the underlying specifications and architectural choices explain why these two parts occupy entirely different segments.

Head-to-Head Benchmarks

The only common benchmark recorded for both parts is 3DMark Steel Nomad DX12. In this test, the Intel Arc A580 scores 2229, while the Intel Arc B370 scores 1184. The A580 wins by 88.3%, a massive margin that speaks to the raw compute and memory resources available to the discrete card. The A580’s average benchmark score across all recorded tests is 57756, which places it in the 87th percentile of all GPUs in the database. The B370, by contrast, has an average benchmark score of 1184, placing it in the 5th percentile. The gap between the 87th and 5th percentiles is enormous, indicating that the A580 is positioned for demanding desktop workloads while the B370 is designed for minimal power consumption in portable or integrated environments.

Looking at the A580’s nearest rivals in the database, its average score of 57756 sits close to several AMD parts. The AMD Radeon RX 5600 OEM averages 58085, a delta of -0.6%, meaning the A580 is nearly identical to that card. The AMD Radeon RX 9070 GRE averages 57367, putting the A580 0.7% ahead. The Intel Arc A570M averages 58239, with the A580 trailing by -0.8%. Finally, the AMD Radeon RX 6950 XT averages 58392, a delta of -1.1%. These close margins show that the A580 competes directly with a cluster of mid-range and older high-end cards, all within roughly one percent of each other. The A580 is not an outlier in its class; it is firmly embedded in a competitive group.

For the B370, the nearest rivals are much older and slower parts. The ATI Mobility Radeon HD 5570 averages 1186, a delta of -0.2%. The ATI Radeon HD 5770 averages 1190, a delta of -0.5%. The AMD Radeon HD 7650M averages 1192, a delta of -0.7%. The AMD FirePro M2000 averages 1168, with the B370 1.4% ahead. This grouping places the B370 at a performance level comparable to integrated and entry-level discrete GPUs from more than a decade ago. The B370’s 3DMark Steel Nomad score of 1184 is less than half of the A580’s 2229, and the percentile rankings reinforce this separation.

Where Each One Wins

The Intel Arc A580 wins the only direct benchmark comparison, and it also holds the advantage in every measurable performance category recorded in the database. It has 3072 shading units, 192 texture mapping units, and 96 raster output units, compared to the B370’s 1280 shading units, 40 TMUs, and 20 ROPs. The A580’s pixel rate is 192.0 GPixel/s versus 48.00 GPixel/s for the B370, a 4x difference. Its texture rate is 384.0 GTexel/s versus 96.00 GTexel/s, another 4x difference. The FP32 compute is 12.29 TFLOPS against 6.144 TFLOPS, exactly double. The FP16 rate is 24.58 TFLOPS (2:1) versus 12.29 TFLOPS (2:1), also double. The A580 also has 24 ray tracing cores versus 10 for the B370.

The B370’s wins are not in performance but in efficiency and integration. Its TDP is 25 W, compared to the A580’s 175 W, a reduction of 150 W. The B370 requires no power connectors, while the A580 needs 2x 8-pin connectors. The A580’s suggested PSU is 450 W, while the B370 has no suggested PSU listed because it is an IGP. The B370 uses system shared memory, meaning there is no dedicated VRAM allocation, no separate memory bus, and no independent bandwidth figure. The A580, by contrast, has 8 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s of bandwidth. The B370’s memory bandwidth is listed as system dependent, which means its performance will vary based on the host platform’s memory configuration.

Architecture Differences

The architectural split between these two Intel parts is stark. The A580 uses the Xe-HPG architecture on the DG2-512 chip, fabricated on TSMC’s 6 nm process. It contains 21,700 million transistors on a 406 mm² die, giving a transistor density of 53.4 million per square millimeter. The B370 uses the Xe3-LPG architecture on the Panther Lake chip, built on Intel’s 3 nm process. Its transistor count and die size are both listed as unknown in the database, so no density figure is available. The A580 belongs to the Alchemist generation under the Arc 5 label, while the B370 belongs to the Arc Graphics-M generation for Panther Lake. The A580’s predecessor is Xe Graphics, and its successor is Battlemage. The B370 has no predecessor or successor listed.

The process node difference is significant: 6 nm for the A580 versus 3 nm for the B370. The B370’s newer process allows for dramatically lower power consumption, with a TDP of 25 W against 175 W. The B370 also has a much lower base clock of 300 MHz versus 1700 MHz for the A580, but a higher boost clock of 2400 MHz versus 2000 MHz. This suggests the B370 is designed to ramp up to high clocks when needed but idle at very low frequencies to conserve power. The A580’s memory clock is 2000 MHz with 16 Gbps effective, while the B370 relies entirely on system shared memory with no dedicated clock listed.

Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The A580 has 24 ray tracing cores, while the B370 has 10. Neither part has tensor cores listed. The A580 is a dual-slot card with PCIe 4.0 x16 interface and display outputs of 1x HDMI 2.1 and 3x DisplayPort 2.0. The B370 is an IGP with a portable device dependent display output configuration and no expansion slot interface. The A580’s production status is Active, and the B370’s is also Active. The A580 was released on 2023-10-09, while the B370’s release date is listed as 2026-01-26, over two years later.

Specification Differences

The most obvious difference is the form factor. The A580 is a dual-slot discrete card, while the B370 is an IGP. The A580 has a 256-bit memory bus with 8 GB of GDDR6 and 512.0 GB/s bandwidth. The B370 uses system shared memory with no dedicated size, type, bus width, or bandwidth. The A580 has 3072 shading units, 192 TMUs, and 96 ROPs. The B370 has 1280 shading units, 40 TMUs, and 20 ROPs. The A580 has 24 RT cores, the B370 has 10. The A580’s base clock is 1700 MHz, boost is 2000 MHz. The B370’s base clock is 300 MHz, boost is 2400 MHz. The A580’s FP32 is 12.29 TFLOPS, FP16 is 24.58 TFLOPS (2:1). The B370’s FP32 is 6.144 TFLOPS, FP16 is 12.29 TFLOPS (2:1). The A580’s TDP is 175 W with a suggested PSU of 450 W, while the B370 has a TDP of 25 W with no suggested PSU. The A580 uses 2x 8-pin power connectors; the B370 uses none. The A580’s process node is 6 nm from TSMC; the B370’s is 3 nm from Intel.

The A580’s pixel rate is 192.0 GPixel/s, and its texture rate is 384.0 GTexel/s. The B370’s pixel rate is 48.00 GPixel/s, and its texture rate is 96.00 GTexel/s. The A580 has a transistor count of 21,700 million on a 406 mm² die. The B370’s transistor count and die size are unknown. The A580 uses PCIe 4.0 x16, while the B370 uses an IGP bus interface. The A580 has 1x HDMI 2.1 and 3x DisplayPort 2.0 outputs; the B370’s display outputs are portable device dependent. The A580’s release date is 2023-10-09; the B370’s is 2026-01-26. The A580’s generation is Alchemist (Arc 5); the B370’s is Arc Graphics-M (Panther Lake).

FAQ

Q: Which GPU has the higher 3DMark Steel Nomad DX12 score?

A: The Intel Arc A580 scores 2229, which is 88.3% higher than the Intel Arc B370’s 1184.

Q: How does the Intel Arc A580 compare to its nearest rivals in average benchmark score?

A: The A580’s average benchmark score is 57756. It trails the AMD Radeon RX 5600 OEM by -0.6%, the Intel Arc A570M by -0.8%, and the AMD Radeon RX 6950 XT by -1.1%, while leading the AMD Radeon RX 9070 GRE by 0.7%.

Q: What is the performance class of the Intel Arc B370 based on its rivals?

A: The B370’s average benchmark score is 1184, placing it near the ATI Mobility Radeon HD 5570 (1186), ATI Radeon HD 5770 (1190), and AMD Radeon HD 7650M (1192), with the AMD FirePro M2000 at 1168.

Q: How much memory and bandwidth does each GPU have?

A: The A580 has 8 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth. The B370 uses system shared memory, with bandwidth listed as system dependent.

Q: What are the power requirements for each GPU?

A: The A580 has a TDP of 175 W, requires 2x 8-pin power connectors, and has a suggested PSU of 450 W. The B370 has a TDP of 25 W, uses no power connectors, and has no suggested PSU listed.

Q: Which GPU has more shading units and ray tracing cores?

A: The A580 has 3072 shading units and 24 ray tracing cores. The B370 has 1280 shading units and 10 ray tracing cores.

The Verdict

The data indicates that the Intel Arc A580 is the clear performance leader in every recorded benchmark and specification category. Its 3DMark Steel Nomad score of 2229 is nearly double the B370’s 1184, and its 87th percentile ranking versus the B370’s 5th percentile confirms a massive gulf in capability. The A580 delivers 12.29 TFLOPS of FP32 compute, 512.0 GB/s of memory bandwidth, and 8 GB of dedicated GDDR6 memory. It is built for desktop systems with a 175 W TDP, dual-slot cooler, and PCIe 4.0 x16 interface. The B370, on the other hand, is an integrated solution with 6.144 TFLOPS of FP32 compute, system shared memory, and a 25 W TDP. Its 3 nm process and high 2400 MHz boost clock suggest efficiency is the priority, not raw throughput.

The A580 should be selected by anyone who needs discrete desktop graphics performance comparable to the AMD Radeon RX 5600 OEM, RX 9070 GRE, or RX 6950 XT, all of which sit within 1.1% of its average score. The B370 is appropriate for systems where an IGP is the only option, such as portable devices, and where the lower power draw and lack of dedicated memory are acceptable trade-offs. The A580’s 24 ray tracing cores and 192 TMUs make it suitable for more demanding rendering tasks, while the B370’s 10 RT cores and 40 TMUs limit it to lighter workloads. The benchmark results do not show any scenario where the B370 outperforms the A580. The choice comes down to whether the user needs a discrete card for full desktop performance or an integrated processor for minimal power consumption.