AMD Radeon 760M vs Intel Arc Pro B370 Comparison
AMD Radeon 760M
Arc Pro B370
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon 760M vs Intel Arc Pro B370
Head-to-Head Benchmarks
The database contains no direct head-to-head benchmark comparisons between the AMD Radeon 760M and the Intel Arc Pro B370. The head-to-head benchmark list is empty, and neither part records a win count in direct comparisons. The only available performance data comes from the AMD Radeon 760M's individual benchmark suite, while the Intel Arc Pro B370 has no recorded benchmark scores at all.
The AMD Radeon 760M posts an average benchmark score of 6019 across its tested workloads. Its percentile standing is 35, meaning it outperforms roughly a third of all GPUs in the database. The nearest rivals bracket this score tightly: the AMD Radeon RX 6400 averages 6001 (0.3% higher), the NVIDIA GeForce GTX 770M averages 6000 (0.3% higher), the NVIDIA RTX PRO 6000 Blackwell Server averages 5996 (0.4% higher), and the NVIDIA Quadro P2000 averages 6049 (0.5% lower). The 760M sits in a dense cluster where a few dozen points separate competitors, indicating that its overall performance level is firmly mid-pack.
Within the 760M's individual tests, the spread is wide. The Geekbench Vulkan result reaches 30336, while the Geekbench OpenCL result lands at 20255. Passmark's G3D score is 5310, the G2D score is 890, and the GPU compute score is 2840. Legacy DirectX tests show lower figures: Passmark DirectX 9 scores 65, DirectX 11 scores 52, DirectX 10 scores 19, and DirectX 12 scores 25. The 3DMark Steel Nomad DX12 test records 400. The gap between the compute-oriented workloads and the older DirectX tests suggests the architecture prioritizes modern APIs and compute tasks.
Because the Intel Arc Pro B370 has no benchmark entries, no numerical comparison between the two can be made from the recorded data. The B370's percentile standing is 50, which indicates it is expected to sit at the median of all GPUs, but this figure is not supported by any actual test scores in the database. Any attempt to declare a winner in specific workloads would require fabricated numbers, which the data does not support.
Architecture Differences
The two integrated GPUs come from different manufacturers, process nodes, and architectural generations. The AMD Radeon 760M uses the Phoenix chip built on RDNA 3.0 architecture, belonging to the Navi III IGP generation. It is fabricated by TSMC on a 4 nm process with 25,390 million transistors on a 178 mm² die, yielding a transistor density of 142.6 million per mm². The Intel Arc Pro B370 uses the Panther Lake chip built on Xe3-LPG architecture, belonging to the Arc Graphics-WM generation. It is fabricated by Intel on a 3 nm process, but its transistor count and die size are listed as unknown.
The execution resources differ substantially. The 760M carries 512 shading units, 32 texture mapping units, 16 render output units, and 8 ray tracing cores. The B370 carries 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The B370 therefore has 2.5 times the shading units, 1.25 times the TMUs, 1.25 times the ROPs, and 1.25 times the RT cores compared to the 760M. Neither part has tensor cores listed.
Clock behavior differs in both base and boost frequencies. The 760M runs at a base clock of 800 MHz with a boost clock of 2599 MHz. The B370 runs at a much lower base clock of 300 MHz but boosts to 2400 MHz. The higher boost on the 760M partially offsets its smaller shader count, but the raw throughput numbers still favor the B370. The 760M delivers 5.323 TFLOPS of FP32 and 5.323 TFLOPS of FP16 at a 1:1 ratio. The B370 delivers 6.144 TFLOPS of FP32 and 12.29 TFLOPS of FP16 at a 2:1 ratio. The B370's FP16 throughput is more than double its FP32 throughput, indicating a different execution path for half-precision work.
Pixel and texture rates follow the same pattern. The 760M achieves 41.58 GPixel/s and 83.17 GTexel/s. The B370 achieves 48.00 GPixel/s and 96.00 GTexel/s, which is roughly 15% higher in both metrics. Power consumption differs as well: the 760M has a TDP of 15 W, while the B370 has a TDP of 25 W. Both are IGP-class parts with no power connectors and no dedicated memory; both use System Shared memory with System Dependent bandwidth. The bus interface differs: the 760M uses PCIe 4.0 x8, while the B370 lists its bus interface as IGP.
API support is identical on paper. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs differ in dependency: the 760M's outputs are Motherboard Dependent, while the B370's are Portable Device Dependent. Release dates differ by two years: the 760M launched on January 30, 2024, and the B370 launched on January 26, 2026. The 760M's predecessor is Navi II IGP; the B370's predecessor is HD Graphics-WM.
FAQ
Q: Which GPU has more shading units?
A: The Intel Arc Pro B370 has 1280 shading units, while the AMD Radeon 760M has 512. The B370's count is 2.5 times higher.
Q: What is the FP32 throughput difference?
A: The B370 delivers 6.144 TFLOPS of FP32, while the 760M delivers 5.323 TFLOPS. The B370 is approximately 15% higher in single-precision compute.
Q: Do both GPUs support ray tracing?
A: Yes. The 760M has 8 ray tracing cores, and the B370 has 10 ray tracing cores.
Q: What process nodes are used?
A: The 760M uses a 4 nm TSMC process. The B370 uses a 3 nm Intel process.
Q: How do their power draws compare?
A: The 760M has a TDP of 15 W, while the B370 has a TDP of 25 W. The B370 consumes more power but also delivers higher raw throughput.
Q: Is there any benchmark data for the Intel Arc Pro B370?
A: The database records no benchmark scores for the B370. Its average benchmark score is listed as 0, and its nearest rivals list is empty. Only the 760M has recorded test results.
The Verdict
The recorded data does not permit a direct performance verdict between these two GPUs. The AMD Radeon 760M has a full suite of benchmark results with an average score of 6019 and a 35th percentile standing. The Intel Arc Pro B370 has no benchmark results, an average score of 0, and no rival comparisons. Its 50th percentile standing is an unverified placeholder rather than a measured outcome.
What the data does show is a clear architectural advantage for the B370 on paper. It has more shading units, more TMUs, more ROPs, more RT cores, higher FP32 throughput, higher FP16 throughput, higher pixel rate, and higher texture rate. It also uses a newer 3 nm process versus the 760M's 4 nm process. These specifications suggest the B370 should outperform the 760M in most compute and graphics workloads, but the absence of measured scores means this remains an inference from specifications, not a confirmed result.
The 760M's position in the database is well established. Its average score of 6019 places it within 0.5% of four nearby rivals, all clustered between 5996 and 6049. This indicates that the 760M performs at a consistent, mid-range level. Its Geekbench Vulkan score of 30336 and OpenCL score of 20255 show strong compute capability, while its Passmark G3D score of 5310 confirms solid general graphics performance.
For a buyer or builder choosing between these two, the data supports the B370 as the specification leader, but only the 760M has proven performance records. The B370's higher TDP of 25 W versus 15 W also indicates it will require more power delivery and cooling, which matters in portable or compact systems. The 760M's lower power draw and established benchmark results make it a known quantity, while the B370 remains an unmeasured specification sheet.
Specification Differences
| Specification | AMD Radeon 760M | Intel Arc Pro B370 |
|---|---|---|
| Architecture | RDNA 3.0 | Xe3-LPG |
| Generation | Navi III IGP (Phoenix) | Arc Graphics-WM (Panther Lake) |
| Process Node | 4 nm | 3 nm |
| Foundry | TSMC | Intel |
| Transistors | 25,390 million | unknown |
| Die Size | 178 mm² | unknown |
| Base Clock | 800 MHz | 300 MHz |
| Boost Clock | 2599 MHz | 2400 MHz |
| Shading Units | 512 | 1280 |
| TMUs | 32 | 40 |
| ROPs | 16 | 20 |
| RT Cores | 8 | 10 |
| Pixel Rate | 41.58 GPixel/s | 48.00 GPixel/s |
| Texture Rate | 83.17 GTexel/s | 96.00 GTexel/s |
| FP32 | 5.323 TFLOPS | 6.144 TFLOPS |
| FP16 | 5.323 TFLOPS (1:1) | 12.29 TFLOPS (2:1) |
| TDP | 15 W | 25 W |
| Bus Interface | PCIe 4.0 x8 | IGP |
| Display Outputs | Motherboard Dependent | Portable Device Dependent |
| Release Date | 2024-01-30 | 2026-01-26 |
| Predecessor | Navi II IGP | HD Graphics-WM |
Where Each One Wins
The AMD Radeon 760M wins in power efficiency and proven performance. Its 15 W TDP is lower than the B370's 25 W, making it the better choice for systems with limited thermal and power budgets. It also has recorded benchmark results across a wide range of tests, including a Geekbench Vulkan score of 30336 and a Passmark G3D score of 5310, which give buyers confidence in its real-world behavior. Its 4 nm TSMC process and 25,390 million transistors on a 178 mm² die are fully documented, unlike the B370's unknown transistor count and die size.
The Intel Arc Pro B370 wins in raw specification comparisons. Its 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores all exceed the 760M's counts. Its FP32 throughput of 6.144 TFLOPS is higher, its FP16 throughput of 12.29 TFLOPS is more than double the 760M's 5.323 TFLOPS, and its pixel rate of 48.00 GPixel/s and texture rate of 96.00 GTexel/s both surpass the 760M's figures. Its 3 nm Intel process is a generation newer than the 760M's 4 nm TSMC node.
The use-case split is therefore straightforward from the data. For systems where power draw is a hard constraint, such as thin-and-light laptops or passively cooled designs, the 760M's 15 W TDP and established benchmark record make it the safer selection. For workloads that demand maximum shader throughput, ray tracing core count, or half-precision compute, the B370's specifications indicate a higher ceiling, but only if the 25 W power envelope is acceptable and the unmeasured performance materializes as the specs suggest. The 760M's 1:1 FP16 ratio suits mixed-precision workloads that treat FP16 and FP32 equally, while the B370's 2:1 ratio favors FP16-heavy tasks. Neither part has tensor cores, so AI acceleration via dedicated tensor hardware is not available on either.