Intel Arc A310E vs Intel Arc Pro B60 Comparison

FAQ

Q: What are the architectural generations of the Intel Arc A310E and Intel Arc Pro B60?

A: The Intel Arc A310E belongs to the Alchemist (Arc 3) generation, using the Xe-HPG architecture on the DG2-128 chip. The Intel Arc Pro B60 is from the Battlemage (Pro Series) generation, built on the Xe2-HPG architecture with the BMG-G21 chip.

Q: How do the two cards differ in memory capacity and bandwidth?

A: The Arc A310E has 4 GB of GDDR6 memory on a 64-bit bus, delivering 124.0 GB/s of bandwidth. The Arc Pro B60 has 24 GB of GDDR6 memory on a 192-bit bus, delivering 456.0 GB/s. That is a 3.7x bandwidth advantage and a 6x capacity advantage for the B60.

Q: What is the performance percentile ranking for each card?

A: The Arc A310E sits at the 50th percentile among all GPUs in the database. The Arc Pro B60 ranks at the 20th percentile. The B60's average benchmark score is 3182, while the A310E has no recorded benchmark scores in the database.

Q: Which card has a higher boost clock?

A: Both cards share a 2000 MHz base clock. The Arc Pro B60 boosts to 2400 MHz, whereas the Arc A310E has a boost clock of 2000 MHz, identical to its base clock.

Q: What display outputs does each card provide?

A: The Arc A310E offers 4x mini-DisplayPort 2.0. The Arc Pro B60 offers 4x mini-DisplayPort 2.1. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the launch MSRP of the Arc Pro B60?

A: The Arc Pro B60 has a launch MSRP of 499 USD. The Arc A310E has no recorded launch MSRP in the database.

Architecture Differences

The two Intel GPUs represent distinct architectural generations. The Arc A310E uses the Xe-HPG architecture from the Alchemist line, fabricated on a 6 nm TSMC process. The chip, DG2-128, contains 7,200 million transistors on a 157 mm² die, yielding a transistor density of 45.9M per mm². In contrast, the Arc Pro B60 employs the Xe2-HPG architecture from the Battlemage line, built on a 5 nm TSMC process. Its BMG-G21 chip packs 19,600 million transistors into a 272 mm² die, achieving a density of 72.1M per mm². The process node improvement and the larger die allow the B60 to house significantly more hardware resources.

Compute resources differ substantially. The A310E provides 768 shading units, 32 texture mapping units, 16 raster operation units, and 6 ray tracing cores. The B60 scales this up to 2,560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. That represents a 3.33x increase in shading units, a 5x increase in TMUs, and a 5x increase in ROPs. Neither card lists tensor cores in the database.

The memory subsystem also reflects the architectural gap. The A310E uses 4 GB of GDDR6 on a 64-bit interface with a 1937 MHz memory clock, effective 15.5 Gbps, producing 124.0 GB/s bandwidth. The B60 uses 24 GB of GDDR6 on a 192-bit interface with a 2375 MHz memory clock, effective 19 Gbps, producing 456.0 GB/s. The memory clock is 22.6% higher on the B60, and the bus width is 3x wider.

The power delivery and physical design differ as well. The A310E has a 75 W TDP, a single-slot profile, no power connectors, and a suggested 250 W power supply. The B60 has a 200 W TDP, a dual-slot profile, a 1x 8-pin power connector, and a suggested 550 W power supply. The B60 is longer at 167 mm versus 168 mm for the A310E, but the B60 is 40 mm thick versus 20 mm for the A310E, double the width. The bus interface also differs: PCIe 4.0 x8 for the A310E versus PCIe 5.0 x8 for the B60.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark results between the Intel Arc A310E and the Intel Arc Pro B60. The A310E has no benchmark entries at all, while the B60 has eight recorded tests. This absence of overlapping data prevents a direct score comparison. However, the B60's individual benchmark results can be analyzed on their own merit.

The Arc Pro B60 achieves its highest raw score in PassMark G3D with 14,580 points. Its PassMark GPU Compute score is 7,029. In legacy DirectX tests, the B60 scores 179 in DirectX 9, 122 in DirectX 11, and 76 in DirectX 12. The PassMark DirectX 10 score is 61. The 3DMark Steel Nomad DX12 test yields 2,646 points. The PassMark G2D score is 763.

The B60's nearest rivals in the database provide context. The NVIDIA Quadro P1000 has an average score of 3,163, which is 0.6% below the B60's average of 3,182. The NVIDIA GeForce GT 640 sits at 3,210, 0.9% above the B60. The NVIDIA GeForce 920M scores 3,287, 3.2% above. The NVIDIA GeForce RTX 5080 SUPER averages 3,075, which is 3.5% below the B60. These deltas indicate the B60 performs in a narrow band around these four rivals, within roughly 3.5% either direction.

The A310E's percentile ranking of 50 places it in the middle of the database distribution, but without recorded benchmark scores, its measured performance cannot be quantified. The B60's 20th percentile ranking places it below the median, yet its average score of 3,182 is supported by actual test data. The discrepancy between percentile and average score suggests the B60's ranking is influenced by the distribution of all GPUs in the database, not just its direct competitors.

The Verdict

The data indicates the Intel Arc Pro B60 is the more capable card in raw compute and memory resources. Its 12.29 TFLOPS FP32 performance is 4x the A310E's 3.072 TFLOPS. Its 24 GB memory capacity and 456.0 GB/s bandwidth dwarf the A310E's 4 GB and 124.0 GB/s. The B60 also has more shading units, TMUs, ROPs, and ray tracing cores, plus a higher boost clock and a newer architecture on a smaller process node.

The Intel Arc A310E is positioned as a low-power, compact solution. Its 75 W TDP requires no power connectors, fits in a single slot, and is 20 mm thick. The B60 demands 200 W, a dual-slot layout, an 8-pin connector, and a 550 W power supply. For systems with strict power or space constraints, the A310E is the only viable option from these two.

The production statuses differ: the A310E is end-of-life, while the B60 is active. The A310E was released on 2024-03-31, and the B60 on 2025-09-04. The B60 is the newer product and remains in production. The A310E's predecessor is listed as Xe Graphics and its successor as Battlemage, which aligns with the B60 being part of that successor generation.

The benchmark data only exists for the B60. Its average score of 3,182 places it within 3.5% of four NVIDIA rivals. The A310E has no measured scores, so its performance ranking at the 50th percentile is not backed by recorded test results. For workloads requiring large memory buffers, high bandwidth, or substantial FP32 throughput, the B60 is the clear choice. For minimal power draw and compact physical footprint, the A310E stands alone.

Specification Differences

The two cards differ in nearly every measurable specification. The process node is 6 nm for the A310E and 5 nm for the B60. Transistor count is 7,200 million versus 19,600 million. Die size is 157 mm² versus 272 mm². Transistor density is 45.9M per mm² versus 72.1M per mm².

Clock speeds: base clock is 2000 MHz for both, but boost clock is 2000 MHz for the A310E and 2400 MHz for the B60. Memory clock is 1937 MHz (15.5 Gbps effective) for the A310E and 2375 MHz (19 Gbps effective) for the B60.

Memory: 4 GB versus 24 GB capacity, 64-bit versus 192-bit bus width, 124.0 GB/s versus 456.0 GB/s bandwidth. Both use GDDR6.

Compute units: 768 shading units versus 2,560, 32 TMUs versus 160, 16 ROPs versus 80, 6 ray tracing cores versus 20. FP32 performance is 3.072 TFLOPS versus 12.29 TFLOPS. FP16 is 6.144 TFLOPS versus 24.58 TFLOPS, both at 2:1 ratio.

Pixel rate is 32.00 GPixel/s versus 192.0 GPixel/s. Texture rate is 64.00 GTexel/s versus 384.0 GTexel/s.

Power: 75 W TDP versus 200 W TDP. The A310E is single-slot with no power connectors and a 250 W suggested PSU. The B60 is dual-slot with a 1x 8-pin connector and a 550 W suggested PSU.

Physical: length is 168 mm versus 167 mm, height is 69 mm for both, width is 20 mm versus 40 mm. Bus interface is PCIe 4.0 x8 versus PCIe 5.0 x8. Display outputs are 4x mini-DisplayPort 2.0 versus 4x mini-DisplayPort 2.1.

Production status: end-of-life versus active. Release date: 2024-03-31 versus 2025-09-04. The B60 has a launch MSRP of 499 USD; the A310E has none recorded. The A310E has a predecessor (Xe Graphics) and successor (Battlemage); the B60 has neither listed.

Where Each One Wins

The Intel Arc Pro B60 wins in every compute-heavy category. Its FP32 throughput of 12.29 TFLOPS is exactly 4x the A310E's 3.072 TFLOPS. Its FP16 output of 24.58 TFLOPS is also 4x the A310E's 6.144 TFLOPS. The texture rate of 384.0 GTexel/s is 6x the A310E's 64.00 GTexel/s. The pixel rate of 192.0 GPixel/s is 6x the A310E's 32.00 GPixel/s. These ratios directly follow from the larger counts of TMUs and ROPs.

Memory-intensive workloads favor the B60 decisively. The 24 GB frame buffer can hold datasets and textures that would exhaust the A310E's 4 GB. The 456.0 GB/s bandwidth is 3.68x the A310E's 124.0 GB/s, reducing bottlenecks when streaming large assets. The 192-bit bus width compared to 64-bit further improves memory efficiency for wide data transfers.

Ray tracing workloads benefit from the B60's 20 ray tracing cores versus the A310E's 6, a 3.33x advantage. The newer Xe2-HPG architecture also suggests improved ray tracing efficiency per core, though the database does not provide per-core performance data.

The A310E wins in power efficiency and physical integration. Its 75 W TDP is 37.5% of the B60's 200 W. It requires no auxiliary power connectors, so it can run on motherboard slot power alone. Its single-slot width of 20 mm allows installation in space-constrained chassis where the B60's 40 mm dual-slot design will not fit. The 168 mm length is nearly identical to the B60's 167 mm, so length is not a differentiator.

The A310E also wins on legacy compatibility in one regard: it uses DisplayPort 2.0, while the B60 uses DisplayPort 2.1. Both support the same API set (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4), so software feature parity exists. The A310E's PCIe 4.0 x8 interface is older than the B60's PCIe 5.0 x8, but for a card with only 124.0 GB/s memory bandwidth, the interface is unlikely to be the limiting factor in most workloads.

The production status favors the B60 as the active product, while the A310E is end-of-life. For new system builds, the B60 offers ongoing availability. The A310E may still appear in existing systems or as legacy stock, but its successor (Battlemage) has already arrived, and the B60 is part of that generation.

For users prioritizing raw performance, memory capacity, bandwidth, and modern architecture, the B60 is the only choice. For users prioritizing low power draw, no external power requirement, and single-slot physical compatibility, the A310E is the only option. The data does not show any scenario where both cards meet the same requirement set, so the decision rests on which constraint dominates: compute capability or physical and power limits.