AMD Radeon RX 6450M vs Intel Arc Pro B370 Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark scores between the AMD Radeon RX 6450M and the Intel Arc Pro B370. Both entries show empty benchmark arrays and zero wins for either side. This means the comparison must rely entirely on the specification data and derived performance metrics available in the database.

The absence of direct measurements does not prevent analysis. The database provides theoretical peak rates for each GPU, which serve as the baseline for comparing raw compute and rendering capabilities. The AMD Radeon RX 6450M delivers 3.779 TFLOPS FP32 and 7.557 TFLOPS FP16 (2:1). The Intel Arc Pro B370 counters with 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1). That translates to the Intel part holding a 62.6% lead in FP32 throughput and a 62.6% lead in FP16 throughput as well, since both ratios are identical. These figures represent the maximum theoretical output, not real-world application results.

Pixel throughput tells a different story. The AMD Radeon RX 6450M reaches 78.72 GPixel/s, while the Intel Arc Pro B370 reaches 48.00 GPixel/s. Here the AMD part leads by 64.0%. Texture fill rates show the AMD GPU at 118.1 GTexel/s versus the Intel GPU at 96.00 GTexel/s, a 23.0% advantage for AMD. These discrepancies arise from the different combinations of shading units, texture mapping units, and raster output units each chip employs.

The AMD Radeon RX 6450M uses 768 shading units, 48 TMUs, and 32 ROPs. The Intel Arc Pro B370 uses 1280 shading units, 40 TMUs, and 20 ROPs. Despite having fewer shaders, the AMD chip produces higher pixel and texture rates because of its ROP and TMU counts. The Intel chip compensates with more shader units, which drives its FP32 and FP16 compute superiority. Neither GPU exposes tensor core counts in the database, so AI acceleration comparisons cannot be quantified.

Memory bandwidth also diverges sharply. The AMD Radeon RX 6450M has 4 GB of GDDR6 on a 64-bit bus, yielding 128.0 GB/s. The Intel Arc Pro B370 relies on system shared memory, with bandwidth listed as system dependent. No fixed number exists for the Intel part, so a direct bandwidth comparison is impossible from the data. The AMD GPU's dedicated VRAM offers a predictable 128.0 GB/s, while the Intel GPU's performance hinges on the host system's memory configuration.

The Verdict

Benchmark results indicate a split decision based on workload type. For raw compute tasks, the Intel Arc Pro B370 holds the advantage. Its FP32 throughput of 6.144 TFLOPS exceeds the AMD Radeon RX 6450M's 3.779 TFLOPS by 62.6%. Any application that scales with shader throughput, such as general-purpose GPU compute or heavily parallel workloads, should favor the Intel part according to the recorded data.

For rasterization-focused tasks, the AMD Radeon RX 6450M appears stronger. Its pixel rate of 78.72 GPixel/s beats the Intel Arc Pro B370's 48.00 GPixel/s by 64.0%. The texture rate of 118.1 GTexel/s also surpasses the Intel part's 96.00 GTexel/s by 23.0%. Games and rendering workloads that depend on fill rates rather than pure shader count would likely prefer the AMD GPU.

Power consumption adds another layer. The AMD Radeon RX 6450M has a TDP of 50 W, while the Intel Arc Pro B370 has a TDP of 25 W. The Intel part delivers higher compute per watt, a relevant factor for thermally constrained portable devices. The AMD part uses double the power budget to achieve its fill-rate advantages.

Both GPUs are integrated-class parts with an IGP slot width and portable device dependent display outputs. Neither requires external power connectors. The AMD Radeon RX 6450M connects via PCIe 4.0 x4, while the Intel Arc Pro B370 uses the IGP bus interface. System integration differs accordingly.

Architecture Differences

The AMD Radeon RX 6450M belongs to the Radeon RX 6000 series, built on the RDNA 2.0 architecture. Its chip is Navi 24, fabricated on a 6 nm process at TSMC. The die size measures 107 mm² with 5,400 million transistors, yielding a transistor density of 50.5 million per square millimeter. This is a dedicated mobile GPU from the Navi Mobile (RX 6000M) generation, released on January 3, 2023.

The Intel Arc Pro B370 uses the Xe3-LPG architecture on the Panther Lake chip. It is fabricated on a 3 nm process at Intel's own foundry. The database records transistor count and die size as unknown, so no density figure exists. This part belongs to the Arc Graphics-WM (Panther Lake) generation and was released on January 26, 2026, roughly three years after the AMD part.

Ray tracing capabilities differ in core counts. The AMD Radeon RX 6450M includes 12 RT cores, while the Intel Arc Pro B370 includes 10 RT cores. The database does not provide RT performance benchmarks, so the practical impact remains unquantified. Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, indicating parity in API feature levels.

The AMD predecessor is Polaris Mobile, while the Intel predecessor is HD Graphics-WM. Neither GPU has a recorded successor. The production status for both is active. The Intel part's much smaller process node, 3 nm versus 6 nm, suggests a newer manufacturing approach, but without die size or transistor data for the Intel chip, density comparisons cannot be made.

Specification Differences

Clock speeds present a notable contrast. The AMD Radeon RX 6450M has a base clock of 2000 MHz, a game clock of 2220 MHz, and a boost clock of 2460 MHz. The Intel Arc Pro B370 has a base clock of 300 MHz and a boost clock of 2400 MHz, with no game clock recorded. The AMD base clock runs 6.7 times higher, but the boost clocks fall within 2.5% of each other. The low Intel base clock suggests aggressive power management, consistent with its 25 W TDP.

Memory configuration separates the two entirely. The AMD Radeon RX 6450M uses 4 GB of GDDR6 with a 64-bit bus and 128.0 GB/s bandwidth, running at 2000 MHz with 16 Gbps effective speed. The Intel Arc Pro B370 uses system shared memory, with type, bus width, and bandwidth all listed as system dependent. The AMD part offers fixed, dedicated memory resources, while the Intel part's memory performance depends on the host platform.

Shading resources differ in composition. The AMD GPU has 768 shading units, 48 TMUs, and 32 ROPs. The Intel GPU has 1280 shading units, 40 TMUs, and 20 ROPs. The Intel part has 66.7% more shading units but 16.7% fewer TMUs and 37.5% fewer ROPs. These ratios explain the compute advantage for Intel and the fill-rate advantage for AMD.

Power and interface specs diverge as well. The AMD part consumes 50 W, the Intel part 25 W. Both have no power connectors and an IGP slot width. The AMD GPU uses PCIe 4.0 x4, while the Intel GPU uses the IGP bus interface. Neither has a launch MSRP recorded in the database, so no pricing information exists.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B370 delivers 6.144 TFLOPS FP32, which is 62.6% higher than the AMD Radeon RX 6450M's 3.779 TFLOPS.

Q: Which GPU achieves a higher pixel fill rate?

A: The AMD Radeon RX 6450M reaches 78.72 GPixel/s, which is 64.0% higher than the Intel Arc Pro B370's 48.00 GPixel/s.

Q: What memory configurations do these GPUs use?

A: The AMD Radeon RX 6450M uses 4 GB of GDDR6 on a 64-bit bus with 128.0 GB/s bandwidth. The Intel Arc Pro B370 uses system shared memory, with bandwidth listed as system dependent.

Q: How do the TDP figures compare?

A: The AMD Radeon RX 6450M has a TDP of 50 W, while the Intel Arc Pro B370 has a TDP of 25 W. The Intel part consumes half the power.

Q: Do both GPUs support the same DirectX version?

A: Yes, both support DirectX 12 Ultimate (12_2), along with OpenGL 4.6 and Vulkan 1.4.

Q: What are the process nodes for each chip?

A: The AMD Radeon RX 6450M uses a 6 nm process at TSMC. The Intel Arc Pro B370 uses a 3 nm process at Intel.

Where Each One Wins

The Intel Arc Pro B370 wins in compute-bound scenarios. Its FP32 output of 6.144 TFLOPS and FP16 output of 12.29 TFLOPS both exceed the AMD Radeon RX 6450M by 62.6%. Workloads such as scientific simulation, data processing, or any shader-heavy compute task should favor the Intel part based on the recorded data. The 1280 shading units provide the raw parallelism needed for these operations. The lower TDP of 25 W also makes the Intel GPU attractive for power-constrained systems that still require substantial compute throughput.

The AMD Radeon RX 6450M wins in rasterization-bound scenarios. Its 78.72 GPixel/s pixel rate and 118.1 GTexel/s texture rate surpass the Intel Arc Pro B370's 48.00 GPixel/s and 96.00 GTexel/s. Games and rendering applications that stress fill rates, such as high-resolution texture mapping or heavy overdraw, should benefit from the AMD part's ROP and TMU configuration. The dedicated 4 GB GDDR6 with 128.0 GB/s bandwidth provides a fixed memory pipeline that does not depend on host system variables.

Ray tracing workloads present an ambiguous case. The AMD GPU has 12 RT cores versus the Intel GPU's 10 RT cores, but no benchmark data exists to quantify the difference. Both support DirectX 12 Ultimate, so feature parity holds. Without recorded measurements, the database cannot assign a winner in this category.

The release timeline separates the two as well. The AMD Radeon RX 6450M launched on January 3, 2023, while the Intel Arc Pro B370 launched on January 26, 2026. The three-year gap means the Intel part benefits from a more advanced 3 nm process, though the AMD part's 6 nm process still delivers competitive fill rates. The Intel predecessor is HD Graphics-WM, while the AMD predecessor is Polaris Mobile, showing different evolutionary paths within each manufacturer's mobile lineup.

Both GPUs remain active in production status. Neither has a successor recorded. The database shows no direct head-to-head benchmarks, so these conclusions derive entirely from the theoretical performance metrics and specification comparisons available. Users requiring raw compute should examine the Intel Arc Pro B370. Users prioritizing rendering fill rates should examine the AMD Radeon RX 6450M. Power-sensitive designs may prefer the Intel part's 25 W TDP, while memory-sensitive designs may prefer the AMD part's fixed 128.0 GB/s bandwidth.