Intel Arc B370 vs Intel Iris Xe Graphics 80EU Mobile Comparison

Intel Arc B370 and Intel Iris Xe Graphics 80EU Mobile represent two distinct points in Intel’s integrated graphics lineup. The Arc B370, built on the Panther Lake chip with Xe3-LPG architecture, targets higher compute throughput and modern API support. The Iris Xe 80EU, based on Raptor Lake with Generation 12.2 architecture, serves as a mature, widely deployed mobile graphics solution. The recorded data shows a substantial performance gap, driven by differences in shading units, clock speeds, and architectural generation.

The Verdict

The data indicates that the Intel Arc B370 is the stronger graphics processor in nearly every measurable category. Its 3DMark Steel Nomad DX12 score of 1184 places it in the 5th percentile of all GPUs, a low rank that reflects the overall GPU market’s high-end bias, but its nearest rivals cluster tightly around that score. The ATI Mobility Radeon HD 5570 averages 1186, a delta of -0.2%, meaning the Arc B370 trails that card by a hair. The ATI Radeon HD 5770 averages 1190, a delta of -0.5%, and the AMD Radeon HD 7650M averages 1192, a delta of -0.7%. The AMD FirePro M2000 averages 1168, and the Arc B370 leads it by 1.4%. These deltas show a GPU that sits in a narrow competitive band, effectively matching older discrete and professional mobile GPUs despite being an integrated part.

The Iris Xe 80EU Mobile has no recorded benchmark scores and no nearest rivals in the database. Its average benchmark score is listed as zero, so direct quantitative comparison between the two is impossible on that metric. However, the specification data provides a clear hierarchy. The Arc B370 uses 1280 shading units, doubled the Iris Xe’s 640. Its boost clock reaches 2400 MHz versus 1450 MHz. Those two factors alone yield 6.144 TFLOPS of FP32 compute against 1.856 TFLOPS, a 3.3x advantage. Pixel rate is 48.00 GPixel/s versus 29.00 GPixel/s, and texture rate is 96.00 GTexel/s versus 58.00 GTexel/s.

For users selecting between these two, the database points to the Arc B370 for any workload that benefits from raw compute, higher fill rates, or hardware ray tracing. The Arc B370 includes 10 RT cores; the Iris Xe has none. The Arc B370 supports DirectX 12 Ultimate (12_2), while the Iris Xe is limited to DirectX 12 (12_1). The Arc B370 also carries a 25 W TDP against the Iris Xe’s 15 W, so it demands more power budget within a mobile platform. The Iris Xe remains a functional option for systems prioritizing lower power consumption, but the performance data, where available, does not favor it.

FAQ

Q: Which GPU has the higher FP32 compute throughput?

A: The Intel Arc B370 delivers 6.144 TFLOPS of FP32 performance, while the Intel Iris Xe Graphics 80EU Mobile delivers 1.856 TFLOPS. The Arc B370 is approximately 3.3 times higher in this metric.

Q: Does the Intel Arc B370 support hardware ray tracing?

A: Yes. The Arc B370 lists 10 RT cores. The Iris Xe Graphics 80EU Mobile lists no RT cores, so it lacks that hardware capability.

Q: What are the DirectX API differences between the two?

A: The Arc B370 supports DirectX 12 Ultimate (12_2). The Iris Xe supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Q: How do the two compare on pixel and texture fill rates?

A: The Arc B370 achieves 48.00 GPixel/s and 96.00 GTexel/s. The Iris Xe achieves 29.00 GPixel/s and 58.00 GTexel/s. The Arc B370 is higher in both.

Q: What is the power consumption difference?

A: The Arc B370 has a TDP of 25 W. The Iris Xe has a TDP of 15 W. This indicates a 10 W higher power envelope for the Arc B370.

Q: Are there any benchmark scores recorded for the Iris Xe Graphics 80EU Mobile?

A: No. The database lists no benchmarks for that GPU, and its average benchmark score is 0. The Arc B370 has a recorded 3DMark Steel Nomad DX12 score of 1184.

Architecture Differences

The two GPUs come from different architectural generations. The Intel Arc B370 uses the Xe3-LPG architecture, built on the Panther Lake chip. The Intel Iris Xe Graphics 80EU Mobile uses Generation 12.2 architecture, built on the Raptor Lake chip. This generational gap shows up across multiple design points.

The process node differs significantly. The Arc B370 is fabricated on a 3 nm process, while the Iris Xe uses a 10 nm process. Both are produced at Intel’s foundry, but the smaller node allows for denser packing of compute units and higher clock speeds at comparable power. Transistor counts and die sizes are not recorded for either GPU, so no direct comparison exists there.

The shading unit count is a primary architectural differentiator. The Arc B370 packs 1280 shading units, exactly double the Iris Xe’s 640. Texture mapping units are equal at 40 for both, and render output units are also equal at 20. That means the two GPUs share the same number of TMUs and ROPs, but the Arc B370 has twice the shader array. This asymmetry explains why the Arc B370’s texture rate is not double the Iris Xe’s; texture rate depends on TMUs and clock, so 40 TMUs at 2400 MHz produce 96.00 GTexel/s, while 40 TMUs at 1450 MHz produce 58.00 GTexel/s. The pixel rate follows the same pattern: 20 ROPs at 2400 MHz gives 48.00 GPixel/s, and 20 ROPs at 1450 MHz gives 29.00 GPixel/s.

Ray tracing is exclusive to the Arc B370. It carries 10 RT cores, and the Iris Xe lists no RT core count. The Arc B370’s DirectX 12 Ultimate (12_2) support enables features that the Iris Xe, with DirectX 12 (12_1), cannot expose. Both GPUs support OpenGL 4.6 and Vulkan 1.4.

The bus interface also differs. The Arc B370 uses an IGP interface, while the Iris Xe uses a Ring Bus interface. Both are integrated graphics processors with no slot width, and the Arc B370 lists no power connectors. Display outputs for both are portable device dependent, so no fixed output configuration is recorded.

The Iris Xe lists a successor, Arc Graphics-M, which matches the generation grouping of the Arc B370. The Arc B370 has no predecessor or successor listed in the database. Both GPUs are marked as Active in production status.

Specification Differences

The recorded specifications show a clear split between the two parts across clock speeds, compute rates, and power.

Clock speeds: The Arc B370 has a base clock of 300 MHz and a boost clock of 2400 MHz. The Iris Xe also has a base clock of 300 MHz, but its boost clock is 1450 MHz. The base clocks match exactly.

Memory: Both use System Shared memory in size, type, and bus width. Memory bandwidth is System Dependent for both.

Shading units: The Arc B370 has 1280; the Iris Xe has 640. TMUs are 40 for both. ROPs are 20 for both.

Ray tracing cores: The Arc B370 has 10; the Iris Xe has none.

Pixel rate: The Arc B370 reaches 48.00 GPixel/s; the Iris Xe reaches 29.00 GPixel/s.

Texture rate: The Arc B370 reaches 96.00 GTexel/s; the Iris Xe reaches 58.00 GTexel/s.

FP32 performance: The Arc B370 delivers 6.144 TFLOPS; the Iris Xe delivers 1.856 TFLOPS.

FP16 performance: The Arc B370 delivers 12.29 TFLOPS (2:1); the Iris Xe delivers 3.712 TFLOPS (2:1).

TDP: The Arc B370 is rated at 25 W; the Iris Xe at 15 W.

Bus interface: The Arc B370 uses IGP; the Iris Xe uses Ring Bus.

DirectX support: The Arc B370 supports 12 Ultimate (12_2); the Iris Xe supports 12 (12_1).

Process node: The Arc B370 is 3 nm; the Iris Xe is 10 nm.

Chip and architecture: The Arc B370 is Panther Lake with Xe3-LPG; the Iris Xe is Raptor Lake with Generation 12.2.

Release dates: The Arc B370 was released on 2026-01-26. The Iris Xe was released on 2023-01-03.

Production status: Both are Active.

Launch MSRP: Neither GPU has a recorded launch MSRP.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two GPUs. The wins counters for each are zero. However, the Arc B370 has a standalone benchmark result that can be positioned against its nearest rivals, and the specification data allows a side-by-side analysis of expected performance.

The Arc B370’s 3DMark Steel Nomad DX12 score is 1184. Its nearest rival, the ATI Mobility Radeon HD 5570, scores 1186, a delta of -0.2%. That places the Arc B370 essentially at parity with that older mobile discrete GPU. The ATI Radeon HD 5770 scores 1190, a delta of -0.5%, and the AMD Radeon HD 7650M scores 1192, a delta of -0.7%. The AMD FirePro M2000 scores 1168, and the Arc B370 leads by 1.4%. These four rivals span a range of only 24 points, from 1168 to 1192, and the Arc B370 sits inside that band. The data suggests the Arc B370’s performance is competitive with a specific tier of legacy discrete GPUs, despite being an integrated solution.

The Iris Xe has no benchmark scores, no average score, and no nearest rivals. Its percentile ranking of 50 means it sits at the median of all GPUs in the database, but that ranking is not tied to a specific benchmark result. The Arc B370’s percentile of 5 reflects its score relative to a much larger, higher-performing GPU population.

The biggest advantage for the Arc B370 in the specification data is FP32 compute. At 6.144 TFLOPS, it is 3.3 times the Iris Xe’s 1.856 TFLOPS. This gap is driven by twice the shading units and a 65.5% higher boost clock (2400 MHz versus 1450 MHz). The FP16 advantage is similar: 12.29 TFLOPS versus 3.712 TFLOPS, again a 3.3x ratio.

Pixel rate favors the Arc B370 by 19.00 GPixel/s, from 29.00 to 48.00. Texture rate favors the Arc B370 by 38.00 GTexel/s, from 58.00 to 96.00. Both of these differences come entirely from the clock speed advantage, since TMU and ROP counts are identical.

The Arc B370’s 10 RT cores give it a capability the Iris Xe completely lacks. Combined with DirectX 12 Ultimate support, the Arc B370 can handle workloads that require hardware ray tracing or the higher-tier DirectX feature set. The Iris Xe’s DirectX 12 (12_1) support is one level lower.

Power consumption is the one category where the Iris Xe is lower. Its 15 W TDP is 10 W below the Arc B370’s 25 W. For a mobile platform, that difference matters for thermal design and battery life, but it comes with a substantial compute penalty.

The release timing also separates the two. The Iris Xe arrived on 2023-01-03, and the Arc B370 arrived on 2026-01-26. That three-year gap aligns with the architectural jump from Generation 12.2 to Xe3-LPG and the process shrink from 10 nm to 3 nm.

In summary, the Arc B370 leads in every performance-related specification, with a 3.3x FP32 advantage, higher fill rates, exclusive ray tracing hardware, and a newer API tier. The Iris Xe’s only recorded advantages are a lower TDP and an earlier release date. Without any benchmark entries for the Iris Xe, the quantitative comparison rests on the Arc B370’s 3DMark result and the specification deltas, both of which point in the same direction.