Intel Arc B770 vs Intel Arc Pro A60 Comparison

Head-to-Head Benchmarks

The recorded data shows a significant gap between these two Intel graphics cards, though direct head-to-head benchmark comparisons are limited. The Intel Arc Pro A60 has two recorded benchmark scores in the database: 63,485 in Geekbench OpenCL and 57,166 in Geekbench Vulkan. Its average benchmark score is 60,326. The Intel Arc B770 has no recorded benchmark scores in the database, which limits direct quantitative comparison.

The Arc Pro A60's average score of 60,326 places it at the 88th percentile of all GPUs in the database. This is a strong showing for a professional-oriented card. Its nearest rivals in the database include the NVIDIA GeForce RTX 4090 with an average score of 60,347, a delta of 0%, meaning the Arc Pro A60 performs essentially identically to that flagship consumer card in these aggregate measurements. The AMD Radeon Pro W6600M scores 61,896, which is 2.5% higher than the Arc Pro A60, while the AMD Radeon PRO V710 scores 58,657, putting it 2.8% behind. The AMD Radeon Pro Vega 48 scores 60,140, a 0.3% gap.

The Arc B770's percentile rank is 50, and its average benchmark score is 0 in the database, indicating that no validated benchmark results have been recorded for it yet. This means the data cannot support a direct performance comparison between the two cards based on measured scores. What can be stated is that the Arc Pro A60 delivers performance that rivals top-tier GPUs in aggregate compute benchmarks, while the Arc B770's performance profile remains unmeasured in the current database.

Architecture Differences

The two cards represent different generations of Intel's GPU architectures. The Arc B770 uses the BMG-G31 chip built on the Xe2-HPG architecture, belonging to the Battlemage (Arc 7) generation. The Arc Pro A60 uses the DG2-256 chip built on the older Xe-HPG architecture, belonging to the Alchemist (Pro Series) generation. This generational leap is significant for the B770.

Manufacturing processes differ as well. The B770 is fabricated on a 5 nm process at TSMC, while the A60 uses a 6 nm process, also at TSMC. The B770's die size is 368 mm², compared to the A60's 269 mm². The A60 has a recorded transistor count of 11,500 million and a transistor density of 42.8 million per mm². The B770's transistor count is listed as unknown in the database, though its larger die size on a smaller process node suggests a higher transistor count.

Compute resources show a substantial disparity. The Arc B770 features 4,096 shading units, 256 texture mapping units, 128 raster operation pipelines, and 32 ray tracing cores. The Arc Pro A60 has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 ray tracing cores. The B770 therefore has exactly double the shading units, TMUs, ROPs, and ray tracing cores of the A60. Neither card has tensor cores listed in the database.

Clock speeds differ considerably. The B770 has a base clock of 2,100 MHz and a boost clock of 2,400 MHz. The A60 has a base clock of 900 MHz and a boost clock of 2,050 MHz. This gives the B770 substantially higher base and boost frequencies. Memory clocks are identical at 2,000 MHz with 16 Gbps effective speed, but the memory subsystems differ otherwise.

The B770 uses 16 GB of GDDR6 memory on a 256-bit bus, delivering 512.0 GB/s of bandwidth. The A60 uses 12 GB of GDDR6 on a 192-bit bus, delivering 384.0 GB/s. Both use PCIe 4.0 x16 interfaces. The B770 is a dual-slot card with power connectors of 1x 6-pin plus 1x 8-pin, while the A60 is a single-slot card with no power connectors listed. The B770 has a TDP of 225 W and a suggested PSU of 550 W, while the A60 has a TDP of 130 W and a suggested PSU of 300 W.

The B770 offers display outputs of 1x HDMI 2.1a and 3x DisplayPort 2.1. The A60 offers 4x DisplayPort 2.0. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B770's release date is recorded as 2025-12-31, while the A60's release date is 2023-06-05, and it remains in active production status.

FAQ

Q: Which card has more shading units?

A: The Intel Arc B770 has 4,096 shading units, double the 2,048 shading units found in the Intel Arc Pro A60.

Q: What is the memory bandwidth difference between the two cards?

A: The Arc B770 delivers 512.0 GB/s of memory bandwidth from 16 GB of GDDR6 on a 256-bit bus. The Arc Pro A60 delivers 384.0 GB/s from 12 GB of GDDR6 on a 192-bit bus.

Q: How do the two cards compare in ray tracing resources?

A: The Arc B770 has 32 ray tracing cores, while the Arc Pro A60 has 16 ray tracing cores, a 2:1 ratio in favor of the B770.

Q: Which card has a higher boost clock?

A: The Arc B770 has a boost clock of 2,400 MHz, compared to the Arc Pro A60's boost clock of 2,050 MHz. The B770 also has a much higher base clock at 2,100 MHz versus 900 MHz.

Q: What are the power requirements for each card?

A: The Arc B770 has a TDP of 225 W and requires a suggested PSU of 550 W, with 1x 6-pin and 1x 8-pin power connectors. The Arc Pro A60 has a TDP of 130 W and a suggested PSU of 300 W, with no power connectors listed.

Q: Which card has recorded benchmark scores in the database?

A: Only the Intel Arc Pro A60 has recorded benchmark scores: 63,485 in Geekbench OpenCL and 57,166 in Geekbench Vulkan, averaging 60,326. The Arc B770 has no recorded benchmark scores.

Specification Differences

The following specifications differ between the two cards. The Arc B770 uses the BMG-G31 chip on Xe2-HPG architecture from the Battlemage (Arc 7) generation, while the Arc Pro A60 uses the DG2-256 chip on Xe-HPG from the Alchemist (Pro Series) generation. The process node is 5 nm for the B770 and 6 nm for the A60, both from TSMC. Die size is 368 mm² for the B770 and 269 mm² for the A60. Transistor count is unknown for the B770 and 11,500 million for the A60.

Base clock is 2,100 MHz for the B770 and 900 MHz for the A60. Boost clock is 2,400 MHz for the B770 and 2,050 MHz for the A60. Memory size is 16 GB for the B770 and 12 GB for the A60. Bus width is 256 bit for the B770 and 192 bit for the A60. Memory bandwidth is 512.0 GB/s for the B770 and 384.0 GB/s for the A60.

Shading units are 4,096 for the B770 and 2,048 for the A60. TMUs are 256 versus 128. ROPs are 128 versus 64. Ray tracing cores are 32 versus 16. Pixel rate is 307.2 GPixel/s for the B770 and 131.2 GPixel/s for the A60. Texture rate is 614.4 GTexel/s for the B770 and 262.4 GTexel/s for the A60. FP32 performance is 19.66 TFLOPS for the B770 and 8.397 TFLOPS for the A60. FP16 performance is 39.32 TFLOPS for the B770 and 16.79 TFLOPS for the A60.

TDP is 225 W for the B770 and 130 W for the A60. Slot width is dual-slot for the B770 and single-slot for the A60. Power connectors are 1x 6-pin plus 1x 8-pin for the B770 and none for the A60. Suggested PSU is 550 W for the B770 and 300 W for the A60. Display outputs are 1x HDMI 2.1a plus 3x DisplayPort 2.1 for the B770 and 4x DisplayPort 2.0 for the A60. The A60 has a production status of Active; the B770's production status is not listed. Release dates are 2025-12-31 for the B770 and 2023-06-05 for the A60.

Where Each One Wins

The Intel Arc Pro A60 wins in the area of validated performance data. It has recorded benchmark scores of 63,485 in Geekbench OpenCL and 57,166 in Geekbench Vulkan, placing it at the 88th percentile of all GPUs. Its average score of 60,326 matches the NVIDIA GeForce RTX 4090 within 0%, and it sits 2.8% ahead of the AMD Radeon PRO V710. This indicates that the A60 delivers compute performance competitive with top-tier cards despite its professional positioning.

The A60 also wins on power efficiency and physical footprint. Its TDP of 130 W and suggested PSU of 300 W are substantially lower than the B770's 225 W and 550 W. The A60 is a single-slot card with no power connectors required, making it suitable for dense workstation configurations where space and power delivery are constrained. Its 4x DisplayPort 2.0 outputs provide multi-monitor professional workflows.

The Intel Arc B770 wins on raw compute resources and specifications. It has double the shading units, TMUs, ROPs, and ray tracing cores of the A60. Its FP32 throughput of 19.66 TFLOPS is more than double the A60's 8.397 TFLOPS. Its FP16 throughput of 39.32 TFLOPS similarly more than doubles the A60's 16.79 TFLOPS. The B770's pixel rate of 307.2 GPixel/s and texture rate of 614.4 GTexel/s both exceed the A60's 131.2 GPixel/s and 262.4 GTexel/s by more than a factor of two.

The B770 also wins on memory capacity and bandwidth. It offers 16 GB of GDDR6 with 512.0 GB/s bandwidth, compared to the A60's 12 GB with 384.0 GB/s. The B770's newer Xe2-HPG architecture, 5 nm process, and higher clock speeds position it as the more advanced part. Its base clock of 2,100 MHz is over twice the A60's 900 MHz base clock.

The Verdict

The data points to a clear specification hierarchy. The Intel Arc B770 is the more powerful card on paper in every compute metric: shading units, TMUs, ROPs, ray tracing cores, clock speeds, memory size, memory bandwidth, pixel rate, texture rate, and FP32/FP16 throughput. It uses a newer architecture, a smaller process node, and a larger die. Its release date of 2025-12-31 places it as the newer product.

The Intel Arc Pro A60 is the only card with validated benchmark results. Its 88th percentile ranking and near-parity with the NVIDIA GeForce RTX 4090 in average score demonstrate that it holds its own in measured compute workloads. Its lower TDP of 130 W, single-slot design, and lack of power connectors make it suitable for professional environments where power and space are at a premium.

For workloads that depend on measured compute performance, the Arc Pro A60 has the evidence in the database. For workloads that depend on raw specification headroom, the Arc B770's doubled resources and higher bandwidth make it the stronger candidate on paper. The B770's lack of recorded benchmark scores means its real-world performance cannot be verified from the current data. Users who prioritize validated performance should rely on the A60's recorded results. Users who prioritize architectural generation and specification superiority should note the B770's advantages, but the database contains no measured scores to confirm its actual performance level.