AMD Radeon 890M vs AMD Radeon Pro 5300M Comparison

The AMD Radeon 890M is the clear benchmark victor over the AMD Radeon Pro 5300M, winning 8 of 9 direct comparisons and delivering substantially higher raw performance despite being an integrated graphics processor. The Radeon Pro 5300M, a now end-of-life discrete mobile GPU from 2019, manages only a single narrow win in one legacy DirectX 10 test. The data reveals a generational shift: the newer RDNA 3.5-based 890M outclasses the older RDNA 1.0 part in nearly every measurable workload, with the integrated solution’s higher clock speeds and architectural efficiency overcoming the discrete card’s dedicated memory advantages.

Head-to-Head Benchmarks

The AMD Radeon 890M dominates the modern compute and graphics workloads. In Geekbench OpenCL, the 890M scores 37,254 against the Pro 5300M’s 29,252, a 21.5% advantage. The gap widens significantly in Geekbench Vulkan, where the 890M posts 40,808 versus 27,912, a 31.6% lead. This indicates the RDNA 3.5 architecture handles modern API overhead far more efficiently, translating to a substantial performance edge in Vulkan-based applications.

The PassMark G3D suite reinforces this trend, with the 890M scoring 8,076 compared to the Pro 5300M’s 5,918, a 26.7% difference. GPU compute performance follows suit: the 890M achieves 4,157 in PassMark GPU Compute, outpacing the Pro 5300M’s 2,658 by 36.1%. This consistent double-digit margin across compute and 3D rendering suggests the 890M is not just marginally better but fundamentally faster in throughput-oriented tasks.

DirectX 11 and DirectX 12 results show the largest deltas. In PassMark DirectX 11, the 890M scores 73 versus 37 for the Pro 5300M, a massive 49.3% advantage. DirectX 12 shows a 32.4% lead for the 890M (37 vs 25). These results are particularly telling because they represent the API workloads most relevant to modern gaming and professional applications. The 890M’s support for DirectX 12 Ultimate (12_2) versus the Pro 5300M’s DirectX 12 (12_1) likely contributes to this substantial performance gap.

Even in 2D performance, the 890M excels. PassMark G2D scores 979 for the 890M versus 582 for the Pro 5300M, a 40.6% advantage. This suggests the integrated GPU benefits from faster system memory access and newer display controllers. The only bright spot for the Pro 5300M is PassMark DirectX 10, where it scores 36 versus 33 for the 890M, a 9.1% win. This legacy workload favors the older architecture’s simpler pipeline, but it is a minor consolation given the comprehensive defeat elsewhere. The 890M also wins PassMark DirectX 9 with 97 versus 80, a 17.5% margin, showing even older APIs run faster on the newer silicon.

FAQ

Q: Which GPU has higher raw compute performance?

A: The AMD Radeon 890M is significantly ahead in FP32 compute, delivering 5.939 TFLOPS versus the Pro 5300M’s 3.200 TFLOPS. This 85% theoretical advantage is reflected in real-world benchmarks where the 890M leads by 36.1% in PassMark GPU Compute.

Q: How do the memory configurations differ?

A: The Pro 5300M uses 4 GB of dedicated GDDR6 memory on a 128-bit bus with 192.0 GB/s bandwidth. The 890M uses System Shared memory with System Dependent bandwidth, meaning it relies on the host system’s RAM rather than dedicated VRAM.

Q: Does the newer architecture support hardware ray tracing?

A: Yes, the 890M features 16 dedicated ray tracing cores, while the Pro 5300M has no RT cores listed. This makes the 890M capable of hardware-accelerated ray tracing, a feature entirely absent on the older RDNA 1.0 part.

Q: What is the power consumption difference?

A: The Pro 5300M has a TDP of 85 W, while the 890M is rated at just 15 W. This makes the integrated 890M dramatically more power-efficient, delivering higher performance at a fraction of the power draw.

Q: Which GPU has better API support?

A: The 890M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Pro 5300M supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The 890M’s higher DirectX version enables features like DirectX Raytracing and mesh shaders.

Q: What is the production status of each GPU?

A: The Pro 5300M is listed as End-of-life, released on 2019-11-12. The 890M is Active, released on 2024-07-14, and has a predecessor called Navi II IGP.

Architecture Differences

The two GPUs represent distinct generations of AMD graphics architecture. The Pro 5300M uses RDNA 1.0 on the Navi 14 chip, built on TSMC’s 7 nm process. The 890M uses RDNA 3.5 on the Strix Point chip, fabricated on TSMC’s 4 nm node. This process shrink allows the 890M to pack 34,000 million transistors into a 233 mm² die, achieving a transistor density of 145.9M per mm². In contrast, the Pro 5300M contains 6,400 million transistors on a 158 mm² die, with a density of just 40.5M per mm².

The 890M’s architecture supports hardware ray tracing with 16 RT cores, a feature completely absent from the RDNA 1.0-based Pro 5300M. The newer architecture also implements FP16 at 1:1 ratio (5.939 TFLOPS), while the Pro 5300M uses 2:1 ratio (6.400 TFLOPS FP16 from 3.200 TFLOPS FP32). This means the 890M has no packed math penalty, offering equal FP16 and FP32 throughput. The 890M also carries DirectX 12 Ultimate (12_2) support, enabling advanced features like variable rate shading and mesh shaders, whereas the Pro 5300M is limited to DirectX 12 (12_1).

Clock speeds show a dramatic difference. The 890M boosts to 2900 MHz with a base of 400 MHz, while the Pro 5300M boosts to just 1250 MHz with a 1000 MHz base. This 132% boost clock advantage is the primary driver behind the 890M’s superior performance despite having fewer shading units (1024 vs 1280). The 890M also achieves higher pixel and texture rates: 92.80 GPixel/s and 185.6 GTexel/s respectively, versus 40.00 GPixel/s and 100.0 GTexel/s for the Pro 5300M.

Specification Differences

| Specification | AMD Radeon Pro 5300M | AMD Radeon 890M |

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

| Architecture | RDNA 1.0 | RDNA 3.5 |

| Process Node | 7 nm | 4 nm |

| Transistors | 6,400 million | 34,000 million |

| Die Size | 158 mm² | 233 mm² |

| Transistor Density | 40.5M / mm² | 145.9M / mm² |

| Base Clock | 1000 MHz | 400 MHz |

| Boost Clock | 1250 MHz | 2900 MHz |

| Memory | 4 GB GDDR6 | System Shared |

| Memory Bus | 128 bit | System Shared |

| Bandwidth | 192.0 GB/s | System Dependent |

| Shading Units | 1280 | 1024 |

| TMUs | 80 | 64 |

| ROPs | 32 | 32 |

| RT Cores | None | 16 |

| Pixel Rate | 40.00 GPixel/s | 92.80 GPixel/s |

| Texture Rate | 100.0 GTexel/s | 185.6 GTexel/s |

| FP32 | 3.200 TFLOPS | 5.939 TFLOPS |

| FP16 | 6.400 TFLOPS (2:1) | 5.939 TFLOPS (1:1) |

| TDP | 85 W | 15 W |

| DirectX | 12 (12_1) | 12 Ultimate (12_2) |

| Production Status | End-of-life | Active |

| Release Date | 2019-11-12 | 2024-07-14 |

The Verdict

The data unequivocally favors the AMD Radeon 890M for virtually all workloads. It wins 8 of 9 head-to-head benchmarks, with leads ranging from 17.5% to 49.3% across DirectX, OpenCL, Vulkan, and compute tests. The 890M’s 5.939 TFLOPS FP32 output nearly doubles the Pro 5300M’s 3.200 TFLOPS, and its 16 RT cores provide capabilities the older card lacks entirely. The 890M also achieves this with an 85 W lower TDP (15 W vs 85 W), making it not just faster but dramatically more efficient.

The Pro 5300M’s only win comes in PassMark DirectX 10 with a 9.1% margin (36 vs 33), a legacy API test with little relevance to modern applications. Its dedicated 4 GB GDDR6 memory with 192.0 GB/s bandwidth provides a theoretical advantage over system-shared memory, but benchmark results show this does not translate into real-world performance gains. The Pro 5300M’s higher pixel rate (40.00 vs 92.80 GPixel/s) is also theoretically inferior, and its lower texture rate (100.0 vs 185.6 GTexel/s) confirms the 890M’s dominance.

For users choosing between these two, the 890M is the rational pick for everything except workloads specifically optimized for legacy DirectX 10 pipelines or requiring dedicated VRAM isolation. The 890M’s active production status and 2024 release date also ensure ongoing driver support, while the Pro 5300M is end-of-life.

Where Each One Wins

AMD Radeon 890M: This is the clear winner for modern gaming, 3D rendering, and compute workloads. It dominates in Geekbench Vulkan (40,808 vs 27,912, +31.6%), Geekbench OpenCL (37,254 vs 29,252, +21.5%), and PassMark G3D (8,076 vs 5,918, +26.7%). Its DirectX 11 performance is nearly double the Pro 5300M (73 vs 37, +49.3%), making it superior for DirectX 11 games. The 890M’s 16 RT cores enable hardware ray tracing, a feature completely absent on the Pro 5300M. Its lower TDP of 15 W makes it suitable for thin-and-light laptops without discrete cooling solutions. The 890M also wins in GPU compute (4,157 vs 2,658, +36.1%), 2D performance (979 vs 582, +40.6%), DirectX 12 (37 vs 25, +32.4%), and DirectX 9 (97 vs 80, +17.5%).

AMD Radeon Pro 5300M: The only area where this card wins is PassMark DirectX 10, scoring 36 versus 33 for the 890M, a 9.1% margin. This makes it marginally better for legacy DirectX 10 applications. The Pro 5300M also offers dedicated 4 GB GDDR6 memory with 192.0 GB/s bandwidth, which could be preferable in scenarios where system memory bandwidth is constrained or where memory isolation is required for stability. Its 1280 shading units outnumber the 890M’s 1024, though the 890M’s higher clocks more than compensate. For users running older software that predates DirectX 11 and relies on DirectX 10 paths, the Pro 5300M holds a slight edge. Otherwise, the 890M is the superior choice across every meaningful performance metric.