AMD Radeon 680M vs Intel Arc B770 Comparison

FAQ

Q: What are the average benchmark scores for the AMD Radeon 680M and the Intel Arc B770?

A: The AMD Radeon 680M has an average benchmark score of 15270 across all recorded tests. The Intel Arc B770 currently has no recorded benchmark scores in the database, resulting in an average benchmark score of 0.

Q: How does the AMD Radeon 680M compare to its nearest rivals in the database?

A: The Radeon 680M is essentially level with the NVIDIA GeForce GTX 580, sitting 0.1% behind that card's average score. It is also 0.1% behind the NVIDIA GeForce RTX 2060, while it leads the NVIDIA GeForce RTX 3050 OEM by 0.5% and the AMD Radeon RX 7600 by 0.7%.

Q: What are the memory specifications for each GPU?

A: The Intel Arc B770 uses 16 GB of GDDR6 memory on a 256-bit bus, delivering 512.0 GB/s of bandwidth. The AMD Radeon 680M uses system shared memory, with a system dependent bandwidth.

Q: What process nodes do the two GPUs use?

A: The AMD Radeon 680M is built on a 6 nm process at TSMC. The Intel Arc B770 uses a 5 nm process, also at TSMC.

Q: What are the DirectX support levels for both GPUs?

A: Both the AMD Radeon 680M and the Intel Arc B770 support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the TDP of each GPU?

A: The AMD Radeon 680M has a TDP of 50 W. The Intel Arc B770 has a TDP of 225 W.

Architecture Differences

The AMD Radeon 680M and Intel Arc B770 represent fundamentally different design approaches within the database. The Radeon 680M is an integrated graphics processor based on the RDNA 2.0 architecture, built as part of the Rembrandt+ chip. The Arc B770 is a discrete graphics card using Intel's Xe2-HPG architecture, built on the BMG-G31 chip. The Radeon 680M belongs to the Navi II IGP generation (Rembrandt Mobile), while the Arc B770 belongs to the Battlemage (Arc 7) generation.

Manufacturing details separate the two clearly. The Radeon 680M uses a 6 nm process at TSMC, with a die size of 208 mm² and 13,100 million transistors, yielding a transistor density of 63.0M per mm². The Arc B770 uses a smaller 5 nm process at TSMC, with a larger die size of 368 mm². Its transistor count is listed as unknown in the database.

Compute resources differ by a wide margin. The Radeon 680M contains 768 shading units, 48 texture mapping units, 32 raster output units, and 12 ray tracing cores. The Arc B770 scales this up dramatically with 4096 shading units, 256 TMUs, 128 ROPs, and 32 ray tracing cores. Neither GPU lists tensor cores in the database.

Clock behavior also diverges. The Radeon 680M runs at a 2000 MHz base clock and 2200 MHz boost clock. The Arc B770 runs at 2100 MHz base and 2400 MHz boost. Memory clocks differ entirely: the Radeon 680M relies on system shared memory, while the Arc B770 uses dedicated GDDR6 at 2000 MHz with 16 Gbps effective speed.

The power delivery and physical design reflect their different roles. The Radeon 680M is an IGP with no power connectors and a 50 W TDP. The Arc B770 is a dual-slot card requiring 1x 6-pin and 1x 8-pin power connectors, with a 225 W TDP and a suggested PSU of 550 W. The Radeon 680M connects via PCIe 4.0 x8, while the Arc B770 uses PCIe 4.0 x16. Display outputs are portable device dependent for the integrated part, while the Arc B770 provides 1x HDMI 2.1a and 3x DisplayPort 2.1.

The Verdict

The data in the database shows two GPUs at opposite ends of the spectrum. The AMD Radeon 680M is an integrated solution with a 50 W TDP, designed for portable devices where system shared memory and low power draw are priorities. Its average benchmark score of 15270 places it in the 57th percentile of all GPUs. The recorded results show a 3DMark Steel Nomad DX12 score of 378, a Geekbench OpenCL score of 23468, and a Geekbench Vulkan score of 21965.

The Intel Arc B770 is a discrete, dual-slot card with a 225 W TDP, 16 GB of dedicated GDDR6 memory, and a 512.0 GB/s memory bandwidth. It records a 50th percentile placement, though this is based on no benchmark data currently available in the database.

For systems where low power consumption and integration into a mobile platform matter, the Radeon 680M is the only relevant option. Its nearest rivals in the database, the GTX 580 and RTX 2060, are discrete cards that still score within 0.1% of it, which indicates the integrated part delivers competitive average performance. For a desktop system requiring maximum compute throughput, the Arc B770 offers 19.66 TFLOPS of FP32 performance, 307.2 GPixel/s pixel rate, and 614.4 GTexel/s texture rate, all far above the Radeon 680M's 3.379 TFLOPS, 70.40 GPixel/s, and 105.6 GTexel/s. The choice depends entirely on whether the platform requires an IGP or a discrete card.

Specification Differences

The two GPUs differ across every major specification category in the database.

Process and die: The Radeon 680M uses a 6 nm process with a 208 mm² die and 13,100 million transistors. The Arc B770 uses a 5 nm process with a 368 mm² die and an unknown transistor count.

Clocks: Base clock is 2000 MHz on the Radeon 680M versus 2100 MHz on the Arc B770. Boost clock is 2200 MHz versus 2400 MHz. Memory clock is system shared for the Radeon 680M, while the Arc B770 runs at 2000 MHz with 16 Gbps effective.

Memory: The Radeon 680M uses system shared memory with a system dependent bandwidth. The Arc B770 has 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth.

Compute units: The Radeon 680M has 768 shading units, 48 TMUs, 32 ROPs, and 12 ray tracing cores. The Arc B770 has 4096 shading units, 256 TMUs, 128 ROPs, and 32 ray tracing cores.

Rates and throughput: Pixel rate is 70.40 GPixel/s for the Radeon 680M versus 307.2 GPixel/s for the Arc B770. Texture rate is 105.6 GTexel/s versus 614.4 GTexel/s. FP32 compute is 3.379 TFLOPS versus 19.66 TFLOPS. FP16 compute is 6.758 TFLOPS (2:1) versus 39.32 TFLOPS (2:1).

Power and physical: TDP is 50 W for the Radeon 680M and 225 W for the Arc B770. The Radeon 680M is an IGP with no power connectors; the Arc B770 is dual-slot with 1x 6-pin and 1x 8-pin connectors and a 550 W suggested PSU. Bus interface is PCIe 4.0 x8 versus PCIe 4.0 x16. Display outputs are portable device dependent versus 1x HDMI 2.1a and 3x DisplayPort 2.1.

Release and lineage: The Radeon 680M released on 2023-01-02, with the Vega II IGP as predecessor and Navi III IGP as successor. The Arc B770 releases on 2025-12-31, with Alchemist as predecessor and no successor listed.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between the AMD Radeon 680M and the Intel Arc B770. The wins counter records zero victories for each GPU in direct comparisons. This absence of paired test data means no direct score differential can be calculated from head-to-head runs.

However, the individual recorded benchmarks for the Radeon 680M provide a reference point. Its 3DMark Steel Nomad DX12 result of 378, Geekbench OpenCL score of 23468, and Geekbench Vulkan score of 21965 combine into an average benchmark score of 15270. The Arc B770 has no recorded benchmarks, and therefore no average score.

The nearest rival data for the Radeon 680M offers context for its performance level. The NVIDIA GeForce GTX 580 averages 15283, which is 0.1% higher. The NVIDIA GeForce RTX 2060 averages 15290, also 0.1% higher. The NVIDIA GeForce RTX 3050 OEM averages 15199, putting the Radeon 680M 0.5% ahead. The AMD Radeon RX 7600 averages 15171, with the Radeon 680M 0.7% ahead.

For the Arc B770, the theoretical performance envelope can be estimated from its specification data. Its FP32 throughput of 19.66 TFLOPS is roughly 5.8 times the Radeon 680M's 3.379 TFLOPS. Its texture rate of 614.4 GTexel/s is about 5.8 times the 105.6 GTexel/s of the Radeon 680M. Its pixel rate of 307.2 GPixel/s is about 4.4 times the 70.40 GPixel/s of the Radeon 680M. The memory bandwidth advantage is substantial: 512.0 GB/s of dedicated GDDR6 bandwidth compared to a system dependent figure for the integrated part.

The percentile data places the Radeon 680M at the 57th percentile of all GPUs, while the Arc B770 sits at the 50th percentile. The Radeon 680M's percentile is backed by actual benchmark runs, whereas the Arc B770's percentile reflects its placeholder status without recorded measurements.

The compute resource gap is equally pronounced. The Arc B770 carries 4096 shading units versus 768 on the Radeon 680M, a 5.3 times difference. Ray tracing cores number 32 versus 12, a 2.7 times difference. Texture mapping units number 256 versus 48, a 5.3 times difference. Raster output units number 128 versus 32, a 4 times difference.

Power efficiency trends in the opposite direction. The Radeon 680M delivers its 3.379 TFLOPS within a 50 W TDP, while the Arc B770 delivers 19.66 TFLOPS within a 225 W TDP. The integrated part also relies on system shared memory, which eliminates the dedicated memory power overhead but introduces system dependent bandwidth constraints.

The production status field lists the Radeon 680M as active, while the Arc B770 has no production status recorded. The Radeon 680M has an established benchmark presence in the database; the Arc B770 has none. The specification sheet for the Arc B770 indicates a card designed for a different performance class, but until benchmark data is recorded, its actual measured performance cannot be compared directly to the Radeon 680M.