AMD Radeon AI PRO 9600D vs Intel Arc B370 Comparison

Where Each One Wins

The recorded data splits these two adapters into entirely different performance classes. The AMD Radeon AI PRO 9600D targets a workstation segment with a discrete, single-slot design, while the Intel Arc B370 is an integrated graphics processor (IGP) built into a mobile platform. Their benchmark results reflect that divide.

In the only recorded 3DMark Steel Nomad DX12 test, the Intel Arc B370 scores 1184 points. That places it at the 5th percentile among all GPUs in the database, meaning 95% of recorded adapters outperform it. Its nearest rivals in the database are older, low-power parts: the ATI Mobility Radeon HD 5570 (1186 points, 0.2% faster), the ATI Radeon HD 5770 (1190 points, 0.5% faster), and the AMD Radeon HD 7650M (1192 points, 0.7% faster). The only slower nearby part is the AMD FirePro M2000 at 1168 points, which the Arc B370 beats by 1.4%.

The AMD Radeon AI PRO 9600D has no recorded benchmark scores and no average score in the database. Its percentile rank is 50, squarely in the middle of all GPUs. With zero entries in the benchmark field, the data cannot assign it a win in any specific test. The head-to-head benchmark list is empty, and the win counts for both products are zero. Consequently, the analysis must rely on architectural specifications to differentiate them, as the performance measurements do not overlap.

The Intel Arc B370 wins the only measurable benchmark by existing in the test results. The AMD Radeon AI PRO 9600D wins the specification comparison by offering a far larger memory pool, higher compute throughput, and a higher transistor count. For use cases requiring massive frame buffers and sustained rendering throughput, the AMD part has the hardware resources. For low-power, portable systems where the GPU shares system memory, the Intel part occupies that niche.

The Verdict

The data indicates two separate purchasing rationales. For a standalone workstation GPU with a dedicated 32 GB GDDR6 frame buffer, the AMD Radeon AI PRO 9600D is the only choice between these two. It provides 3072 shading units, 192 texture mapping units, 96 raster operation units, and 48 ray tracing cores. It reaches 24.82 TFLOPS FP32 and the same 24.82 TFLOPS FP16 at a 1:1 ratio. Its 576.0 GB/s memory bandwidth over a 256 bit bus supports large datasets. The Intel Arc B370 cannot match these specifications, as it uses system shared memory and has no dedicated bandwidth figure.

For an integrated solution inside a low-power platform, the Intel Arc B370 is the relevant option. It operates at 25 W, uses no external power connectors, and requires no separate card slot. Its 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1 ratio) are modest but functional for basic rendering. Its 3DMark Steel Nomad score of 1184 places it near the bottom of the database, but for an IGP, that is the expected performance envelope.

The production status of both is Active. The AMD part released on 2025-12-10, and the Intel part released on 2026-01-26. Neither has a recorded launch MSRP, so no price comparison is possible from the data. The choice rests entirely on whether the system needs a discrete card with dedicated memory or an integrated processor with minimal power draw.

Head-to-Head Benchmarks

The head-to-head benchmark table contains no entries. There are no recorded tests where both products ran the same workload. The AMD Radeon AI PRO 9600D has an empty benchmark array, so its average score is 0. The Intel Arc B370 has one recorded test: 3dmark_3dmark_steel_nomad_dx12 with a score of 1184. That single result serves as its average benchmark score.

Without a common test, the only quantitative comparison comes from the Intel part's nearest rivals. The Arc B370 sits within a narrow band of older adapters. It trails the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%. It leads the AMD FirePro M2000 by 1.4%. These deltas are small, indicating the Arc B370 performs roughly on par with a decade-old midrange mobile GPU.

The AMD Radeon AI PRO 9600D has no such rival data. Its percentile rank of 50 suggests median performance across the entire database, but without concrete scores, the exact margin over other GPUs cannot be stated. The specification sheet, however, provides a clear theoretical advantage. The AMD part's 24.82 TFLOPS FP32 is roughly four times the Arc B370's 6.144 TFLOPS. Its 576.0 GB/s memory bandwidth is a fixed figure, whereas the Intel part's bandwidth is listed as system dependent. The AMD's 53,900 million transistors on a 357 mm² die vastly exceed the unknown transistor count of the Intel part.

The pixel rate tells a similar story: the AMD part renders 193.9 GPixel/s versus 48.00 GPixel/s for the Intel part. Texture rate is 387.8 GTexel/s versus 96.00 GTexel/s. These are not benchmark scores but computed throughput limits, and they indicate a roughly 4x advantage for the AMD part in raw fill rate. For any workload that stresses memory bandwidth or rasterization, the AMD part has the clear hardware edge.

FAQ

Q: Which GPU has a higher FP32 compute throughput?

A: The AMD Radeon AI PRO 9600D delivers 24.82 TFLOPS FP32, while the Intel Arc B370 delivers 6.144 TFLOPS FP32. That is a 4x difference in favor of the AMD part.

Q: What memory configuration does each product use?

A: The AMD Radeon AI PRO 9600D has 32 GB of GDDR6 memory on a 256 bit bus, providing 576.0 GB/s bandwidth. The Intel Arc B370 uses system shared memory with a system dependent bandwidth figure and no dedicated memory type.

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

A: The Arc B370 scores 1184 in 3DMark Steel Nomad DX12. It trails the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%. It beats the AMD FirePro M2000 by 1.4%.

Q: What is the power consumption of each adapter?

A: The AMD Radeon AI PRO 9600D has a TDP of 150 W and requires a 450 W suggested power supply with a single 16-pin connector. The Intel Arc B370 has a TDP of 25 W and uses no external power connectors.

Q: Do both products support the same graphics APIs?

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

Q: What are the physical dimensions of the AMD Radeon AI PRO 9600D?

A: It is a single-slot card measuring 241 mm in length, 111 mm in height, and 19 mm in width. The Intel Arc B370 is an IGP with no recorded dimensions.

Architecture Differences

The two products come from different foundries and process nodes. The AMD Radeon AI PRO 9600D uses the Navi 48 chip built on RDNA 4.0 architecture, manufactured by TSMC on a 4 nm process. It contains 53,900 million transistors on a 357 mm² die, yielding a transistor density of 151.0M per mm². The Intel Arc B370 uses the Panther Lake chip with Xe3-LPG architecture, manufactured by Intel on a 3 nm process. Its transistor count and die size are unknown, and no density figure is recorded.

The compute units differ substantially. The AMD part has 3072 shading units, 192 TMUs, and 96 ROPs, plus 48 dedicated ray tracing cores. The Intel part has 1280 shading units, 40 TMUs, and 20 ROPs, plus 10 ray tracing cores. The AMD part has no tensor cores listed, and neither does the Intel part. The AMD part's FP16 rate equals its FP32 rate at 24.82 TFLOPS, indicating a 1:1 ratio. The Intel part's FP16 rate is 12.29 TFLOPS against a 6.144 TFLOPS FP32 rate, showing a 2:1 ratio.

Clock behavior also diverges. The AMD part runs at a 1080 MHz base, a 1080 MHz game clock, and a 2020 MHz boost clock. Memory runs at 2250 MHz with 18 Gbps effective data rate. The Intel part has a 300 MHz base and a 2400 MHz boost clock, with no game clock listed. Its memory clock is listed as system shared, dependent on the host platform.

Memory architecture separates them completely. The AMD part owns 32 GB of GDDR6 on a 256 bit bus, achieving 576.0 GB/s. The Intel part uses system shared memory, with the bus width and bandwidth both listed as system dependent. This means the Intel IGP's performance scales with the host system's RAM configuration, whereas the AMD card has a fixed, dedicated memory subsystem.

The bus interface and physical design differ as well. The AMD part uses PCIe 5.0 x16 and occupies a single slot, measuring 241 mm by 111 mm by 19 mm. It has one DisplayPort 2.1a output. The Intel part is an IGP with no bus interface beyond the integrated graphics path, no slot width, and display outputs described as portable device dependent. The AMD part draws 150 W with a suggested 450 W power supply and a single 16-pin connector. The Intel part draws 25 W and requires no connectors.

The release timeline shows the AMD part arriving first on 2025-12-10, followed by the Intel part on 2026-01-26. The AMD predecessor is the Radeon Pro Vega, while the Intel part has no recorded predecessor. Both remain in Active production status. The architectural split is clear: a discrete, high-bandwidth workstation GPU versus an integrated, low-power mobile GPU.