AMD Radeon 760M vs Intel Arc B370 Comparison

FAQ

Q: What is the AMD Radeon 760M?

A: The AMD Radeon 760M is an integrated graphics processor (IGP) from AMD, built on the Phoenix chip with RDNA 3.0 architecture. It uses a 4 nm process node from TSMC and contains 25,390 million transistors on a 178 mm² die. It was released on January 30, 2024.

Q: What is the Intel Arc B370?

A: The Intel Arc B370 is an integrated graphics processor from Intel, based on the Panther Lake chip with Xe3-LPG architecture. It uses a 3 nm process node from Intel and was released on January 26, 2026.

Q: How do the two compare in raw compute performance?

A: The Intel Arc B370 delivers 6.144 TFLOPS of FP32 performance, which is higher than the AMD Radeon 760M's 5.323 TFLOPS. The Arc B370 also has a higher FP16 output at 12.29 TFLOPS (2:1 ratio) compared to the Radeon 760M's 5.323 TFLOPS (1:1 ratio).

Q: Which GPU has more shading units and texture units?

A: The Intel Arc B370 has 1,280 shading units, 40 texture mapping units (TMUs), and 20 raster operations units (ROPs). The AMD Radeon 760M has 512 shading units, 32 TMUs, and 16 ROPs.

Q: What is the memory setup for both GPUs?

A: Both GPUs use System Shared memory, meaning the memory size, type, and bus width are all system dependent. The bandwidth is also system dependent for both.

Q: How do their benchmark scores compare?

A: In the only shared benchmark, 3DMark Steel Nomad DX12, the Intel Arc B370 scores 1184 while the AMD Radeon 760M scores 400. This gives the Arc B370 a 66.2% advantage in that test.

Where Each One Wins

The data shows a clear split between the two integrated GPUs. The Intel Arc B370 wins the only head-to-head benchmark available, the 3DMark Steel Nomad DX12 test, with a score of 1184 versus the AMD Radeon 760M's 400. That represents a 66.2% delta in favor of Intel.

However, the AMD Radeon 760M has a much broader benchmark profile. It has scores across 10 different tests, including Geekbench OpenCL (20255), Geekbench Vulkan (30336), and Passmark G3D (5310). The Intel Arc B370 only has a single recorded benchmark in the database. For users looking at compute workloads covered by OpenCL or Vulkan, the Radeon 760M has verified results, while the Arc B370's performance in those specific tests is not recorded.

The Radeon 760M also sits at the 35th percentile among all GPUs, with an average benchmark score of 6019. The Arc B370 sits at the 5th percentile with an average score of 1184. This means the Radeon 760M outperforms a much larger portion of the GPU landscape based on its aggregate data.

Where the Arc B370 wins is in raw peak throughput and the specific DX12 workload measured. Its higher shading unit count, TMU count, ROP count, and FP32 throughput all point to a design that should handle modern DirectX 12 titles with more headroom, at least based on the Steel Nomad result.

Architecture Differences

The AMD Radeon 760M uses the RDNA 3.0 architecture, built on the Phoenix chip. This is part of the Navi III IGP generation. The process node is 4 nm at TSMC, and the die size is 178 mm² with 25,390 million transistors. The transistor density works out to 142.6 million transistors per square millimeter.

The Intel Arc B370 uses the Xe3-LPG architecture, built on the Panther Lake chip. This is part of the Arc Graphics-M generation. The process node is 3 nm at Intel's own foundry. The database does not list transistor count or die size for this chip.

The Radeon 760M has 512 shading units, 32 TMUs, and 16 ROPs. It includes 8 ray tracing cores. The Arc B370 has 1,280 shading units, 40 TMUs, and 20 ROPs, with 10 ray tracing cores. Neither GPU lists tensor cores.

Clock behavior differs significantly. The Radeon 760M runs at a base clock of 800 MHz and boosts to 2599 MHz. The Arc B370 has a much lower base clock of 300 MHz but boosts to 2400 MHz. The wider gap between base and boost on the Intel part suggests a more aggressive power management scheme.

The FP16 implementation also differs. The Radeon 760M does FP16 at a 1:1 ratio with FP32, meaning both hit 5.323 TFLOPS. The Arc B370 does FP16 at a 2:1 ratio, delivering 12.29 TFLOPS versus its 6.144 TFLOPS FP32. This indicates the Intel architecture can double throughput on half-precision workloads.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Radeon 760M uses a PCIe 4.0 x8 bus interface, while the Arc B370's bus interface is listed simply as IGP.

Specification Differences

The two GPUs differ in several key specification fields. The process node is 4 nm for AMD and 3 nm for Intel. The foundry is TSMC for AMD and Intel for the Arc B370. The Radeon 760M has known transistor count and die size, while the Arc B370 has unknown values for both.

The shading unit count is 512 for AMD versus 1280 for Intel. TMUs are 32 versus 40. ROPs are 16 versus 20. Ray tracing cores are 8 versus 10.

Clock speeds: the Radeon 760M has a base clock of 800 MHz and a boost of 2599 MHz. The Arc B370 has a base of 300 MHz and a boost of 2400 MHz.

Pixel rate is 41.58 GPixel/s for AMD and 48.00 GPixel/s for Intel. Texture rate is 83.17 GTexel/s for AMD and 96.00 GTexel/s for Intel.

FP32 throughput is 5.323 TFLOPS for AMD and 6.144 TFLOPS for Intel. FP16 is 5.323 TFLOPS for AMD and 12.29 TFLOPS for Intel.

The TDP is 15 W for the Radeon 760M and 25 W for the Arc B370. Both are IGPs with no power connectors and no suggested PSU.

The bus interface is PCIe 4.0 x8 for AMD and IGP for Intel. Display outputs are motherboard dependent for AMD and portable device dependent for Intel.

The release dates are January 30, 2024 for AMD and January 26, 2026 for Intel. The Radeon 760M's predecessor is Navi II IGP; the Arc B370 has no listed predecessor.

Head-to-Head Benchmarks

The database contains exactly one shared benchmark between these two GPUs: 3DMark Steel Nomad DX12. The Intel Arc B370 scores 1184, and the AMD Radeon 760M scores 400. The delta is 66.2% in favor of Intel.

This is a substantial margin. The Arc B370 nearly triples the Radeon 760M's score in this specific DirectX 12 test. Given that both GPUs support DirectX 12 Ultimate, the difference suggests the Intel architecture handles the workload patterns in Steel Nomad significantly better.

Looking at the broader benchmark context, the Radeon 760M's average score across all its recorded tests is 6019. The Arc B370's average is 1184, but that average is based on a single test. The Radeon 760M's percentile ranking of 35 means it beats 35% of all GPUs in the database. The Arc B370's percentile of 5 means it beats only 5% of all GPUs. However, this comparison is skewed by the fact that the Arc B370 has only one data point.

The Radeon 760M's nearest rivals include the AMD Radeon RX 6400 (6001 average score, 0.3% delta), the NVIDIA GeForce GTX 770M (6000, 0.3%), and the NVIDIA RTX PRO 6000 Blackwell Server (5996, 0.4%). The Arc B370's nearest rivals are all much older parts: the ATI Mobility Radeon HD 5570 (1186, -0.2%), the ATI Radeon HD 5770 (1190, -0.5%), and the AMD Radeon HD 7650M (1192, -0.7%).

The Radeon 760M's Passmark scores show a mixed profile: DirectX 9 at 65, DirectX 10 at 19, DirectX 11 at 52, and DirectX 12 at 25. The G2D score is 890, G3D is 5310, and GPU compute is 2840. These are all absent for the Arc B370.

The Verdict

The Intel Arc B370 wins the only direct comparison available. Its 3DMark Steel Nomad DX12 score of 1184 versus the Radeon 760M's 400 is a decisive 66.2% margin. The Arc B370 also has superior raw specifications: more shading units (1280 versus 512), more TMUs (40 versus 32), more ROPs (20 versus 16), higher FP32 throughput (6.144 TFLOPS versus 5.323 TFLOPS), and higher pixel and texture rates.

The Radeon 760M has advantages in other areas. It has a higher boost clock (2599 MHz versus 2400 MHz), a lower TDP (15 W versus 25 W), and a much larger body of benchmark data showing consistent performance across OpenCL, Vulkan, and DirectX tests. Its average benchmark score of 6019 places it at the 35th percentile, far above the Arc B370's 5th percentile.

For users who prioritize the single recorded DX12 workload, the Arc B370 is clearly the stronger choice. Its architectural headroom in shading units and ray tracing cores suggests it can handle newer graphics workloads more effectively. The 3 nm Intel process node also indicates a more modern manufacturing approach.

For users who need verified performance across a range of compute and graphics APIs, the Radeon 760M has the evidence. Its Geekbench OpenCL score of 20255 and Vulkan score of 30336 demonstrate solid compute capability. The Passmark G3D score of 5310 confirms its graphics performance in that benchmark suite.

The Arc B370's 25 W TDP makes it suitable for systems with slightly more thermal headroom, while the Radeon 760M's 15 W TDP fits more power-constrained designs. Both are integrated GPUs, so neither requires external power connectors.

The choice depends on the specific workload. The database shows one clear benchmark win for Intel, but the AMD part has broader verified performance data. Users targeting modern DirectX 12 gaming should favor the Arc B370 based on the Steel Nomad result. Users needing general compute across OpenCL, Vulkan, and older DirectX versions have more evidence for the Radeon 760M.