AMD Steam Machine GPU vs Intel Arc B370 Comparison

The Verdict

The database record for the AMD Steam Machine GPU contains no benchmark scores, no average score, and no percentile ranking. The Intel Arc B370, by contrast, has a recorded 3DMark Steel Nomad DX12 score of 1184, placing it in the 5th percentile of all GPUs in the database. The AMD part sits at the 50th percentile, meaning half of all recorded GPUs score below it, but without a concrete benchmark figure, direct performance comparisons cannot be quantified. The data indicates the AMD Steam Machine GPU is positioned for a console-class workload with a 110 W TDP, while the Intel Arc B370 is an integrated graphics processor (IGP) with a 25 W TDP designed for portable devices. Any user selecting between these two should base the decision on the fundamental split: the AMD part is a discrete, high-power console GPU with dedicated memory, and the Intel part is a low-power integrated solution sharing system memory. The recorded data does not support a performance winner; it supports a use-case separation.

Architecture Differences

The AMD Steam Machine GPU uses the Navi 33 chip built on RDNA 3.0 architecture, codenamed Hotpink Bonefish, and belongs to the Console GPU (Valve) generation. It is fabricated on a 6 nm process at TSMC with 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2 million per square millimeter. The Intel Arc B370 uses the Panther Lake chip on Xe3-LPG architecture, belongs to the Arc Graphics-M (Panther Lake) generation, and is fabricated on a 3 nm process at Intel. Intel's transistor count and die size are recorded as unknown, so density cannot be calculated. The AMD GPU operates with a base clock of 1720 MHz, a boost clock of 2450 MHz, and a game clock of 2250 MHz. The Intel part has a base clock of 300 MHz and a boost clock of 2400 MHz. The AMD GPU houses 1792 shading units, 112 texture mapping units, 64 raster output units, and 28 ray tracing cores. The Intel Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. Neither part lists tensor cores. The AMD GPU features 8 GB of GDDR6 memory on a 128-bit bus with 288.0 GB/s of bandwidth and a memory clock of 2250 MHz, 18 Gbps effective. The Intel part uses system shared memory, with type, bus width, and bandwidth all system dependent. The AMD GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Intel Arc B370 supports the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are production active, but the AMD part released on 2026-06-28, while the Intel part released on 2026-01-26, making the Intel solution roughly five months earlier in the release timeline.

Head-to-Head Benchmarks

The database contains no shared head-to-head benchmark entries for these two GPUs, so a direct score-by-score comparison is impossible. The Intel Arc B370 has exactly one recorded benchmark: 3DMark Steel Nomad DX12 with a score of 1184. Its nearest rivals in the database are all older or lower-tier parts. The ATI Mobility Radeon HD 5570 scores 1186, which is 0.2% higher than the Arc B370. The ATI Radeon HD 5770 scores 1190, 0.5% higher. The AMD Radeon HD 7650M scores 1192, 0.7% higher. The AMD FirePro M2000 scores 1168, which is 1.4% lower than the Arc B370. This places the Arc B370 in a very narrow performance band: it is within 1.4% of four rivals, none of which are modern discrete GPUs. The data shows the Arc B370 sits at the 5th percentile of all GPUs, indicating that 95% of recorded GPUs score higher. The AMD Steam Machine GPU has no recorded benchmarks and no nearest rivals, so its position in the database cannot be compared numerically. What the data does show is the asymmetry: one part has a measurable but low benchmark presence, and the other has no measured presence at all. The AMD GPU's 50th percentile ranking is a database-level indicator, not a benchmark-derived score, and it suggests the part is expected to land in the middle of the performance distribution. Without a Steel Nomad score for the AMD part, the only honest reading is that the Arc B370's 1184 score is a low-end result, and the AMD part's percentile suggests it should outperform it substantially, but that inference is not confirmed by any recorded measurement.

FAQ

Q: What is the only benchmark score recorded for the Intel Arc B370?

A: The Intel Arc B370 has a single recorded benchmark score of 1184 in 3DMark Steel Nomad DX12.

Q: How does the Intel Arc B370 compare to its nearest rivals in the database?

A: The Arc B370 scores 0.2% below the ATI Mobility Radeon HD 5570, 0.5% below the ATI Radeon HD 5770, 0.7% below the AMD Radeon HD 7650M, and 1.4% above the AMD FirePro M2000.

Q: Does the AMD Steam Machine GPU have any recorded benchmark scores?

A: No, the database lists no benchmarks for the AMD Steam Machine GPU, and its average benchmark score is recorded as 0.

Q: What percentile does each GPU hold in the database?

A: The AMD Steam Machine GPU is in the 50th percentile of all GPUs, while the Intel Arc B370 is in the 5th percentile.

Q: What is the TDP difference between the two GPUs?

A: The AMD Steam Machine GPU has a TDP of 110 W, and the Intel Arc B370 has a TDP of 25 W.

Q: What memory configuration does each GPU use?

A: The AMD Steam Machine GPU uses 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth, while the Intel Arc B370 uses system shared memory with system dependent bandwidth.

Q: What is the release date difference between the two parts?

A: The Intel Arc B370 was released on 2026-01-26, and the AMD Steam Machine GPU was released on 2026-06-28.

Where Each One Wins

The AMD Steam Machine GPU wins on raw compute resources. It has 1792 shading units against 1280, 112 TMUs against 40, 64 ROPs against 20, and 28 ray tracing cores against 10. Its FP32 throughput is 17.56 TFLOPS, nearly three times the Arc B370's 6.144 TFLOPS. Its FP16 throughput is 17.56 TFLOPS at a 1:1 ratio, while the Intel part reaches 12.29 TFLOPS at a 2:1 ratio. The AMD GPU's pixel rate is 156.8 GPixel/s versus 48.00 GPixel/s for the Intel part, and its texture rate is 274.4 GTexel/s versus 96.00 GTexel/s. The AMD GPU also delivers 288.0 GB/s of dedicated memory bandwidth, which the Intel part cannot match because its bandwidth is system dependent. The AMD part's 204 mm² die with 13,300 million transistors on a 6 nm TSMC process indicates a much larger and more complex silicon implementation.

The Intel Arc B370 wins on power efficiency and integration. Its 25 W TDP is less than a quarter of the AMD part's 110 W TDP. It is classified as an IGP with a slot width of IGP and a bus interface of IGP, meaning it requires no power connectors, just like the AMD GPU, but it also requires no separate card installation. Its base clock of 300 MHz is dramatically lower than the AMD part's 1720 MHz, which allows for aggressive power scaling in portable devices. The Intel part's display outputs are listed as portable device dependent, confirming its role in mobile hardware. Its 3 nm Intel process node is more advanced than the AMD part's 6 nm TSMC node, which partially explains how it achieves a functional GPU at 25 W. The Intel part also has a higher FP16-to-FP32 ratio at 2:1, suggesting it can double throughput on half-precision workloads, a feature the AMD part does not offer at its 1:1 ratio. The Intel part released earlier on 2026-01-26, giving it a head start in availability.

Specification Differences

The two GPUs differ across nearly every recorded specification. The AMD Steam Machine GPU uses the Navi 33 chip with RDNA 3.0 architecture and the codename Hotpink Bonefish, while the Intel Arc B370 uses the Panther Lake chip with Xe3-LPG architecture and no recorded codename. The process nodes differ: AMD uses 6 nm at TSMC, Intel uses 3 nm at Intel. The AMD part has 13,300 million transistors on a 204 mm² die with a density of 65.2 million per square millimeter; Intel's transistor count, die size, and density are unknown. Clock speeds differ: AMD has a 1720 MHz base, 2450 MHz boost, and 2250 MHz game clock; Intel has a 300 MHz base and 2400 MHz boost with no game clock recorded. Memory configurations are entirely different: AMD uses 8 GB GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth and an 18 Gbps effective memory clock; Intel uses system shared memory with system dependent bandwidth. Compute unit counts differ: AMD has 1792 shading units, 112 TMUs, 64 ROPs, and 28 ray tracing cores; Intel has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The AMD GPU achieves 156.8 GPixel/s and 274.4 GTexel/s, while the Intel part achieves 48.00 GPixel/s and 96.00 GTexel/s. FP32 performance is 17.56 TFLOPS for AMD and 6.144 TFLOPS for Intel. FP16 performance is 17.56 TFLOPS at 1:1 for AMD and 12.29 TFLOPS at 2:1 for Intel. TDP is 110 W for AMD and 25 W for Intel. The AMD GPU has physical dimensions of 156 mm by 152 mm by 162 mm, while the Intel part has no recorded dimensions. Display outputs differ: AMD has 1x HDMI 2.1a and 1x DisplayPort 2.1, while Intel's outputs are portable device dependent. The Intel part is an IGP with an IGP bus interface; the AMD part has no recorded bus interface. Both share the same API support, power connector requirement of none, and production status of active. Release dates differ by five months, with Intel on 2026-01-26 and AMD on 2026-06-28. Neither part has a recorded launch MSRP.