AMD Radeon 760M vs Intel Arc B390 Comparison

Where Each One Wins

The benchmark data splits cleanly between these two integrated graphics parts. The AMD Radeon 760M wins no recorded tests in the head-to-head comparison, while the Intel Arc B390 takes the single available shared benchmark. That test, 3DMark Steel Nomad DX12, shows a 73% delta in favor of Intel, with the Arc B390 scoring 1482 against the Radeon 760M's 400.

However, the broader database paints a different picture of overall capability. The AMD Radeon 760M holds an average benchmark score of 6019 across ten recorded tests, placing it in the 35th percentile of all GPUs. The Intel Arc B390, with only one recorded benchmark, averages 1482 and sits in the 9th percentile. This means the AMD part delivers far more consistent performance across traditional workloads like Geekbench and Passmark, while the Intel part shows a single strong result in a modern DX12 test.

The use-case split is about workload type. The AMD Radeon 760M wins on general compute and older API performance, as evidenced by its Geekbench OpenCL score of 20255, Geekbench Vulkan score of 30336, and Passmark G3D score of 5310. The Intel Arc B390 wins specifically on the newest DirectX 12 path, where its architecture appears better optimized for the Steel Nomad workload. For legacy DirectX 9, 10, and 11 titles, the AMD part's Passmark scores of 65, 19, and 52 respectively suggest broader compatibility, while the Intel part has no recorded data in those categories.

Architecture Differences

The two processors come from different foundries and process nodes. The AMD Radeon 760M uses the Phoenix chip built on TSMC's 4 nm process with RDNA 3.0 architecture, part of the Navi III IGP generation. It packs 25,390 million transistors into a 178 mm² die, yielding a transistor density of 142.6 million per square millimeter. The Intel Arc B390 uses the Panther Lake chip built on Intel's 3 nm process with Xe3-LPG architecture, part of the Arc Graphics-M generation. Its transistor count and die size are listed as unknown in the database.

Core counts differ substantially. The AMD Radeon 760M has 512 shading units, 32 texture mapping units, 16 raster operation units, and 8 ray tracing cores. The Intel Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. That is three times the shading units and 50% more TMUs and ROPs on the Intel side, though the AMD part compensates with a much higher boost clock.

Clock speeds tell part of the story. The AMD Radeon 760M runs at a base clock of 800 MHz and boosts to 2599 MHz. The Intel Arc B390 runs at a base clock of 300 MHz and boosts to 2500 MHz. The AMD part has a 99 MHz higher boost ceiling, which helps narrow the raw throughput gap created by the Intel part's larger core count.

The compute rates follow the core and clock differences. The AMD Radeon 760M delivers 5.323 TFLOPS of FP32 performance and the same 5.323 TFLOPS for FP16, a 1:1 ratio. The Intel Arc B390 delivers 7.680 TFLOPS of FP32 and 15.36 TFLOPS of FP16, a 2:1 ratio. The Intel part has a clear advantage in FP16 workloads, doubling its throughput for half-precision math.

Pixel and texture rates favor Intel as well. The AMD Radeon 760M sustains 41.58 GPixel/s and 83.17 GTexel/s. The Intel Arc B390 reaches 60.00 GPixel/s and 120.0 GTexel/s. These are 44% and 44% higher respectively, reflecting the larger ROP and TMU counts.

Power envelopes differ significantly. The AMD Radeon 760M has a TDP of 15 W, while the Intel Arc B390 has a TDP of 80 W. Both are integrated graphics with no power connectors and an IGP slot width. The AMD part uses a PCIe 4.0 x8 bus interface, while the Intel part uses an unspecified IGP bus interface. Display outputs are motherboard dependent for the AMD part and portable device dependent for the Intel part.

Both support identical API levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has tensor cores listed. The AMD part uses system shared memory with system dependent bandwidth, as does the Intel part. Release dates differ, with the AMD Radeon 760M launching on 2024-01-30 and the Intel Arc B390 launching on 2026-01-26.

Head-to-Head Benchmarks

The only direct comparison in the database is the 3DMark Steel Nomad DX12 test. The Intel Arc B390 scores 1482, while the AMD Radeon 760M scores 400. The delta is -73%, meaning the AMD part trails by 73% in this specific workload. This is an overwhelming win for Intel in modern DirectX 12 rendering, with the Arc B390 delivering 3.7 times the performance of the Radeon 760M.

Context from the nearest rivals clarifies the meaning of these scores. The AMD Radeon 760M's average score of 6019 places it within 0.3% of the AMD Radeon RX 6400 (6001) and the NVIDIA GeForce GTX 770M (6000), and within 0.4% of the NVIDIA RTX PRO 6000 Blackwell Server (5996). It trails the NVIDIA Quadro P2000 (6049) by 0.5%. These are all desktop-class discrete GPUs, and the Radeon 760M essentially matches them on average.

The Intel Arc B390's average score of 1482 places it within 1.3% of the NVIDIA GeForce GT 520MX (1463), within 1.5% of the NVIDIA GeForce 800M (1460), within 2.5% of the NVIDIA GeForce GT 625 OEM (1446), and within 2.7% of the NVIDIA GeForce GT 710 (1443). These are entry-level parts from previous generations, and the Arc B390 sits at the top of that group.

The individual benchmark scores for the AMD Radeon 760M show its strengths. The Geekbench Vulkan score of 30336 is the highest recorded result, followed by Geekbench OpenCL at 20255. Passmark G3D comes in at 5310, with Passmark GPU Compute at 2840. The older API scores are much lower: Passmark DirectX 9 at 65, DirectX 11 at 52, DirectX 12 at 25, and DirectX 10 at 19. Passmark G2D scores 890.

These numbers indicate the AMD part scales well with newer compute APIs but struggles in legacy DirectX paths. The Vulkan and OpenCL results are strong, suggesting good driver optimization for those interfaces. The low Passmark DirectX scores may reflect the integrated nature of the part or specific driver limitations in those older APIs.

The Intel Arc B390 has no comparable data outside the Steel Nomad test. Its 1482 score in that test exceeds the AMD part's 400 by a wide margin, but without additional benchmarks, the database cannot confirm whether this advantage extends to other workloads. The percentile ranking of 9 for the Arc B390 versus 35 for the Radeon 760M suggests the Intel part's single result is not representative of overall GPU capability.

The Verdict

The data indicates two different design philosophies. The AMD Radeon 760M is a low-power integrated GPU with a 15 W TDP that delivers consistent performance across a wide range of benchmarks. Its average score of 6019 places it in the 35th percentile of all GPUs, matching desktop discrete cards like the RX 6400 and GTX 770M. The Intel Arc B390 is a higher-power integrated GPU with an 80 W TDP that shows a single strong result in 3DMark Steel Nomad DX12 but otherwise lacks recorded data.

For users running modern DirectX 12 titles, the Intel Arc B390 has the edge in the one measured test. Its 1482 score versus 400 represents a 73% advantage, a decisive margin. The larger core configuration of 1536 shading units and 12 ray tracing cores supports this result, as does the 7.680 TFLOPS FP32 throughput and 60.00 GPixel/s pixel rate.

For users needing broad compatibility across OpenCL, Vulkan, and older DirectX versions, the AMD Radeon 760M is the safer choice. Its Geekbench scores of 20255 and 30336, along with a Passmark G3D score of 5310, demonstrate solid performance in general compute. The 5.323 TFLOPS FP32 rate, while lower than the Intel part, still provides usable throughput, and the 15 W TDP makes it suitable for power-constrained systems.

The architectural differences reinforce this split. The AMD part uses RDNA 3.0 on a 4 nm TSMC process, while the Intel part uses Xe3-LPG on a 3 nm Intel process. The AMD part has a higher boost clock at 2599 MHz versus 2500 MHz, but the Intel part has three times the shading units. The FP16 ratio also differs: 1:1 for AMD versus 2:1 for Intel, giving the Intel part 15.36 TFLOPS of half-precision performance.

The production status is Active for both. The AMD Radeon 760M has a predecessor listed as Navi II IGP, while the Intel Arc B390 has no listed predecessor. The AMD part launched in January 2024, the Intel part in January 2026. Neither has a successor listed.

The final choice depends on the workload. For 3DMark Steel Nomad DX12 specifically, the Intel Arc B390 is the clear winner. For everything else in the database, the AMD Radeon 760M has the broader set of results and the higher average score. The Intel part's 9th percentile ranking, based on a single benchmark, does not inspire confidence for general use. The AMD part's 35th percentile ranking, based on ten benchmarks, reflects more consistent performance.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 760M has an average benchmark score of 6019, while the Intel Arc B390 has an average benchmark score of 1482.

Q: How do the two compare in 3DMark Steel Nomad DX12?

A: The Intel Arc B390 scores 1482, which is 73% higher than the AMD Radeon 760M's score of 400.

Q: What are the shading unit counts for each GPU?

A: The AMD Radeon 760M has 512 shading units, while the Intel Arc B390 has 1536 shading units.

Q: What is the TDP difference between the two?

A: The AMD Radeon 760M has a TDP of 15 W, while the Intel Arc B390 has a TDP of 80 W.

Q: Which GPU has a higher boost clock?

A: The AMD Radeon 760M boosts to 2599 MHz, while the Intel Arc B390 boosts to 2500 MHz.

Q: What FP16 performance does each GPU deliver?

A: The AMD Radeon 760M delivers 5.323 TFLOPS of FP16 with a 1:1 ratio, while the Intel Arc B390 delivers 15.36 TFLOPS of FP16 with a 2:1 ratio.

Specification Differences

| Specification | AMD Radeon 760M | Intel Arc B390 |

|---|---|---|

| Architecture | RDNA 3.0 | Xe3-LPG |

| 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 | 2500 MHz |

| Shading Units | 512 | 1536 |

| TMUs | 32 | 48 |

| ROPs | 16 | 24 |

| Ray Tracing Cores | 8 | 12 |

| Pixel Rate | 41.58 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 83.17 GTexel/s | 120.0 GTexel/s |

| FP32 Performance | 5.323 TFLOPS | 7.680 TFLOPS |

| FP16 Performance | 5.323 TFLOPS (1:1) | 15.36 TFLOPS (2:1) |

| TDP | 15 W | 80 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 | None |

| Average Benchmark Score | 6019 | 1482 |

| Percentile vs All GPUs | 35 | 9 |