AMD Ryzen Z2 Extreme GPU vs Intel Arc B370 Comparison

Head-to-Head Benchmarks

The sole recorded benchmark in the database, 3DMark Steel Nomad (DX12), delivers a decisive result. The Intel Arc B370 scores 1184 points, while the AMD Ryzen Z2 Extreme GPU scores 516 points. This translates to a delta of -56.4% for the AMD part, meaning the Intel Arc B370 outperforms the AMD Ryzen Z2 Extreme GPU by a substantial margin in this synthetic DirectX 12 workload.

The magnitude of this gap is noteworthy. The AMD Ryzen Z2 Extreme GPU's score places it at the 1st percentile of all GPUs in the database, whereas the Intel Arc B370 sits at the 5th percentile. While both are low in the overall distribution, the Intel part is positioned considerably higher. The AMD part's nearest rivals are the Intel HD Graphics P4000 (534 points, -3.4% delta) and the AMD Radeon HD 6870 (536 points, -3.7% delta). This indicates that the AMD GPU's performance clusters with older integrated and discrete parts from a previous era. The Intel Arc B370, by contrast, sits alongside the ATI Mobility Radeon HD 5570 (1186 points, -0.2% delta) and the ATI Radeon HD 5770 (1190 points, -0.5% delta). The Intel part is effectively matching those older desktop-class discrete GPUs, which is a far higher performance tier than where the AMD part lands.

The delta between the two is not a marginal edge; it is a doubling of performance. The Intel Arc B370 delivers roughly 2.3 times the score of the AMD Ryzen Z2 Extreme GPU in this test. The data suggests that in this specific DX12 benchmark, the Intel part is in a different performance class entirely. The AMD part's score of 516 is only 6.6% above its nearest rival below it, the AMD Radeon HD 6750M (484 points), and 9.3% below the AMD Radeon HD 6770M (569 points). This tight cluster reinforces that the AMD GPU is positioned at the very bottom of the performance scale. The Intel Arc B370, with a score of 1184, has no rival within 1% below it except the ATI Mobility Radeon HD 5570. The data indicates a clear hierarchy: the Intel Arc B370 is the superior performer in this head-to-head comparison.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc B370 holds a significantly higher average benchmark score of 1184 compared to the AMD Ryzen Z2 Extreme GPU's 516. This represents a 56.4% deficit for the AMD part in the recorded 3DMark Steel Nomad DX12 test.

Q: How do the two GPUs compare in terms of percentile ranking?

A: The Intel Arc B370 ranks at the 5th percentile of all GPUs in the database, while the AMD Ryzen Z2 Extreme GPU ranks at the 1st percentile. This indicates that the Intel part outperforms a larger share of the overall GPU population.

Q: What are the nearest rivals for each GPU based on average scores?

A: The AMD Ryzen Z2 Extreme GPU's nearest rivals are the Intel HD Graphics P4000 (534 points, -3.4% delta) and the AMD Radeon HD 6870 (536 points, -3.7% delta). The Intel Arc B370's nearest rivals are the ATI Mobility Radeon HD 5570 (1186 points, -0.2% delta) and the ATI Radeon HD 5770 (1190 points, -0.5% delta).

Q: Which GPU has more shading units?

A: The Intel Arc B370 features 1280 shading units, whereas the AMD Ryzen Z2 Extreme GPU has 1024 shading units. This gives the Intel part a 25% advantage in raw shader count.

Q: What is the difference in FP32 floating-point performance?

A: The Intel Arc B370 delivers 6.144 TFLOPS of FP32 performance, while the AMD Ryzen Z2 Extreme GPU delivers 5.530 TFLOPS. The Intel part holds a lead of roughly 11% in this metric.

Q: Do both GPUs support the same DirectX and Vulkan versions?

A: Yes, both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Their API feature sets are identical according to the database.

Architecture Differences

The two GPUs come from different manufacturers and employ distinct architectural approaches. The AMD Ryzen Z2 Extreme GPU is built on the RDNA 3.5 architecture, specifically using the Strix Point chip. It is manufactured on a 4 nm process at TSMC, with a die size of 233 mm² and a transistor count of 34,000 million. This results in a transistor density of 145.9 million transistors per mm². The Intel Arc B370, conversely, uses the Xe3-LPG architecture with the Panther Lake chip. It is fabricated on Intel's 3 nm process, though the database lists its transistor count and die size as unknown.

The memory subsystems differ fundamentally. The AMD part uses 16 GB of LPDDR5X memory on a 128-bit bus, yielding a fixed bandwidth of 128.0 GB/s. Its memory clock is listed as 1000 MHz with 8 Gbps effective transfer. The Intel Arc B370 uses System Shared memory, with the type, bus width, and bandwidth all listed as "System Shared" or "System Dependent". This means the Intel part's memory performance is not fixed and depends on the host system's configuration.

The compute resources are distributed differently. The AMD Ryzen Z2 Extreme GPU has 1024 shading units, 64 texture mapping units (TMUs), and 48 raster operation units (ROPs). It also includes 16 ray tracing cores. The Intel Arc B370 has 1280 shading units, but only 40 TMUs and 20 ROPs. It includes 10 ray tracing cores. Despite having fewer TMUs and ROPs, the Intel part achieves a higher FP32 throughput of 6.144 TFLOPS versus 5.530 TFLOPS for the AMD part. The FP16 performance also diverges: the AMD part achieves 5.530 TFLOPS (1:1 ratio with FP32), while the Intel part achieves 12.29 TFLOPS (2:1 ratio). This indicates the Intel architecture can process FP16 data at twice the rate of FP32, whereas the AMD part processes both at the same rate.

The clock speeds show a different strategy. The AMD Ryzen Z2 Extreme GPU has a base clock of 800 MHz and a boost clock of 2700 MHz. The Intel Arc B370 has a much lower base clock of 300 MHz and a boost clock of 2400 MHz. Despite the lower clocks, the Intel part's higher shading unit count and architectural efficiency allow it to surpass the AMD part in raw throughput and benchmark scores.

Power characteristics also differ. The AMD part has a TDP of 28 W, while the Intel part has a TDP of 25 W. Both use no power connectors and are designed for low-power, integrated or portable environments. The AMD part has a single display output listed as 1x USB Type-C, while the Intel part's display outputs are listed as "Portable Device Dependent". The Intel part is classified as an IGP (integrated graphics processor) with a bus interface of "IGP", whereas the AMD part has no bus interface listed.

The Verdict

The benchmark data is unambiguous. The Intel Arc B370 delivers 1184 points in 3DMark Steel Nomad DX12, which is 56.4% higher than the AMD Ryzen Z2 Extreme GPU's 516 points. In a direct comparison, the Intel part is the clear winner in the only recorded performance test.

The percentile rankings support this conclusion. The Intel Arc B370 sits at the 5th percentile, while the AMD Ryzen Z2 Extreme GPU sits at the 1st percentile. The nearest rival data reinforces the gap: the AMD part's closest competitors are older integrated and discrete GPUs like the Intel HD Graphics P4000 and AMD Radeon HD 6870, while the Intel part's closest competitors are the ATI Radeon HD 5770 and ATI Mobility Radeon HD 5570, which represent a higher performance tier.

However, the data also shows trade-offs. The AMD Ryzen Z2 Extreme GPU offers fixed 16 GB of LPDDR5X memory with a defined 128.0 GB/s bandwidth, while the Intel Arc B370 relies on system-shared memory with variable performance. For users who require predictable memory behavior, the AMD part has a structural advantage. The AMD part also has more TMUs (64 vs 40) and more ROPs (48 vs 20), which could matter in specific rendering workloads not captured by the single benchmark. The AMD part's pixel rate of 129.6 GPixel/s and texture rate of 172.8 GTexel/s are both higher than the Intel part's 48.00 GPixel/s and 96.00 GTexel/s. These metrics suggest the AMD part may have advantages in fill-rate-bound scenarios, even though the Intel part wins the overall DX12 benchmark.

For raw performance in the recorded synthetic test, the Intel Arc B370 is the choice. For scenarios where fixed memory capacity and higher fill rates are prioritized, the AMD Ryzen Z2 Extreme GPU has measurable advantages. The data does not support a universal recommendation, but it does indicate that the Intel part is the stronger overall performer in the tested workload.

Specification Differences

The two GPUs differ across nearly every recorded specification. The AMD Ryzen Z2 Extreme GPU uses the RDNA 3.5 architecture on a 4 nm TSMC process, while the Intel Arc B370 uses Xe3-LPG on Intel's 3 nm process. The AMD part has a known die size of 233 mm² and 34,000 million transistors, whereas the Intel part's die size and transistor count are unknown.

Memory configurations are starkly different. The AMD part has 16 GB of LPDDR5X on a 128-bit bus with 128.0 GB/s bandwidth. The Intel part uses System Shared memory with System Dependent bandwidth. The AMD part's memory clock is 1000 MHz (8 Gbps effective), while the Intel part has no fixed memory clock.

Compute resources: the AMD part has 1024 shading units, 64 TMUs, 48 ROPs, and 16 RT cores. The Intel part has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. FP32 performance is 5.530 TFLOPS for AMD and 6.144 TFLOPS for Intel. FP16 performance is 5.530 TFLOPS (1:1) for AMD and 12.29 TFLOPS (2:1) for Intel.

Clocks: the AMD part has a base clock of 800 MHz and boost of 2700 MHz. The Intel part has a base of 300 MHz and boost of 2400 MHz. Pixel rate is 129.6 GPixel/s for AMD versus 48.00 GPixel/s for Intel. Texture rate is 172.8 GTexel/s for AMD versus 96.00 GTexel/s for Intel.

Power and physical attributes: the AMD part has a TDP of 28 W, the Intel part 25 W. Both use no power connectors. The Intel part is classified as an IGP with an IGP bus interface and "Portable Device Dependent" display outputs. The AMD part has a single USB Type-C display output. Release dates differ: the AMD part was released on July 8, 2025, while the Intel part was released on January 26, 2026.

Where Each One Wins

The Intel Arc B370 wins in the only recorded benchmark, 3DMark Steel Nomad DX12, with a score of 1184 versus 516. It also wins on shading units (1280 vs 1024), FP32 throughput (6.144 vs 5.530 TFLOPS), FP16 throughput (12.29 vs 5.530 TFLOPS), and percentile ranking (5th vs 1st). The Intel part also has a lower TDP of 25 W versus 28 W, making it slightly more power-efficient on paper.

The AMD Ryzen Z2 Extreme GPU wins on several structural specifications. It has more TMUs (64 vs 40) and more ROPs (48 vs 20). Its pixel rate of 129.6 GPixel/s is significantly higher than the Intel part's 48.00 GPixel/s, and its texture rate of 172.8 GTexel/s exceeds the Intel part's 96.00 GTexel/s. The AMD part also has fixed 16 GB of LPDDR5X memory with a dedicated 128.0 GB/s bandwidth, which is a clear advantage over the Intel part's system-dependent shared memory. The AMD part's higher boost clock of 2700 MHz versus 2400 MHz also favors it in clock-sensitive tasks.

The use-case split is therefore based on workload type. For general DX12 synthetic benchmarks, the Intel Arc B370 is the stronger performer. For fill-rate-intensive workloads that rely on pixel and texture throughput, the AMD Ryzen Z2 Extreme GPU's specifications suggest an advantage. The AMD part's fixed memory pool also makes it more suitable for environments where memory bandwidth must be guaranteed rather than shared with the system. The Intel part's higher shader count and FP32/FP16 throughput make it better suited for compute-heavy tasks. The recorded data, however, only confirms the Intel part's superiority in the single test performed.