AMD Radeon 890M vs NVIDIA GeForce GTX 950M Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive sweep for the AMD Radeon 890M in the two directly comparable benchmark tests. In Geekbench OpenCL, the Radeon 890M scores 37,254 against the GeForce GTX 950M's 9,745, a lead of 282.3%. The Vulkan result is even more lopsided: 40,808 versus 6,525, which translates to a 525.4% advantage for the AMD part. These are not marginal wins; they represent generational-class gaps in raw compute throughput and API-specific efficiency.

Context from the broader database reinforces this outcome. The Radeon 890M posts an average benchmark score of 9,210 across all recorded tests, placing it in the 45th percentile of all GPUs. The GeForce GTX 950M averages 8,135 and sits in the 42nd percentile. While the percentile difference is modest, the average score gap of 1,075 points (roughly 13.2% higher for the AMD part) reflects the fact that the 890M's OpenCL and Vulkan results are supplemented by a wider suite of DirectX and compute tests. The GTX 950M, by contrast, has only two recorded benchmarks, both of which it loses heavily.

Looking at the nearest rivals, the Radeon 890M's average score of 9,210 places it essentially level with the AMD Radeon Vega 8 (9,221, delta -0.1%), the NVIDIA GeForce GTX 960 (9,273, delta -0.7%), and the NVIDIA GeForce GTX 465 (9,294, delta -0.9%). It trails the GeForce GTX 850M by just 1%. This clustering suggests the 890M competes in the same performance tier as those older discrete parts, despite being an integrated graphics processor. The GTX 950M's average of 8,135 puts it in a slightly lower band, with its closest rival being the AMD Radeon R9 M360 (8,129, delta 0.1%), followed by the NVIDIA GeForce GTX 980 (8,167, delta -0.4%), the GeForce 945M (8,099, delta 0.4%), and the NVIDIA GRID K2 (8,080, delta 0.7%).

The individual benchmark breakdown for the 890M shows strong DirectX 9 performance with a Passmark score of 97, while DirectX 11 and DirectX 12 scores drop to 73 and 37 respectively. The GPU compute score is 4,157, and the G3D score reaches 8,076. These figures, combined with the dominant OpenCL and Vulkan results, indicate that the 890M's architecture is particularly well suited to modern, compute-heavy workloads rather than legacy rasterization paths.

Architecture Differences

The two GPUs come from entirely different design eras and philosophies. The AMD Radeon 890M is built on TSMC's 4 nm process, packing 34,000 million transistors into a 233 mm² die, yielding a transistor density of 145.9 million per square millimeter. It uses the RDNA 3.5 architecture with the Strix Point chip, part of the Navi III IGP generation. The NVIDIA GeForce GTX 950M, in contrast, uses the Maxwell architecture with the GM107 chip, fabricated on a 28 nm process at TSMC. It contains 1,870 million transistors on a 148 mm² die, giving a density of 12.6 million per square millimeter. The density difference is stark: the AMD part packs over eleven times more transistors per unit area.

Clock behavior differs significantly. The 890M has a base clock of 400 MHz and a boost clock of 2,900 MHz, a 2,500 MHz range that reflects its power-efficient mobile design. The GTX 950M runs at a base of 993 MHz with a boost of 1,124 MHz, a much narrower envelope. Memory configurations are fundamentally different: the 890M uses system-shared memory with system-dependent bandwidth, while the GTX 950M has 4 GB of dedicated DDR3 on a 128-bit bus, delivering 28.80 GB/s. The shared-memory approach of the 890M means its effective bandwidth scales with the host system's memory, whereas the GTX 950M has a fixed, dedicated allocation.

Compute resources are heavily skewed toward the AMD part. The 890M has 1,024 shading units, 64 texture mapping units, 32 render output units, and 16 ray tracing cores. The GTX 950M has 640 shading units, 40 TMUs, and 16 ROPs, with no ray tracing cores. The pixel rate of the 890M is 92.80 GPixel/s versus 17.98 GPixel/s for the GTX 950M. Texture rate is 185.6 GTexel/s versus 44.96 GTexel/s. FP32 throughput is 5.939 TFLOPS for the AMD part versus 1,438.7 GFLOPS (approximately 1.44 TFLOPS) for the NVIDIA part, a roughly 4.1x advantage. The 890M also supports FP16 at a 1:1 ratio with the same 5.939 TFLOPS figure, while the GTX 950M has no recorded FP16 capability.

API support further separates the two. The 890M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The GTX 950M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The DirectX feature level difference, 12_2 versus 11_0, is significant for modern game compatibility and advanced rendering features. The 890M also carries a PCIe 4.0 x8 interface, while the GTX 950M uses PCIe 3.0 x8.

Power and production status also diverge. The 890M has a TDP of 15 W and is listed as active in production, with a release date of July 14, 2024. The GTX 950M has a TDP of 75 W and is marked end-of-life, released on March 12, 2015. The GTX 950M's predecessor is the GeForce 800M and its successor is GeForce 10 Mobile, while the 890M's predecessor is Navi II IGP with no successor recorded.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The AMD Radeon 890M scores 37,254 versus 9,745 for the NVIDIA GeForce GTX 950M, a 282.3% advantage.

Q: How much faster is the AMD Radeon 890M in Vulkan?

A: The 890M records 40,808 in Geekbench Vulkan against 6,525 for the GTX 950M, which is 525.4% higher.

Q: What are the average benchmark scores for each GPU?

A: The AMD Radeon 890M has an average benchmark score of 9,210, while the NVIDIA GeForce GTX 950M averages 8,135. The 890M ranks in the 45th percentile of all GPUs, and the GTX 950M ranks in the 42nd percentile.

Q: Does the GTX 950M have ray tracing cores?

A: No, the GTX 950M has no ray tracing cores. The AMD Radeon 890M includes 16 ray tracing cores.

Q: What is the TDP difference between the two?

A: The AMD Radeon 890M has a TDP of 15 W, while the NVIDIA GeForce GTX 950M has a TDP of 75 W.

Q: What DirectX versions do they support?

A: The AMD Radeon 890M supports DirectX 12 Ultimate (12_2), while the NVIDIA GeForce GTX 950M supports DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4.

The Verdict

The data points to a clear conclusion: the AMD Radeon 890M is the stronger performer in every recorded head-to-head metric. Its OpenCL and Vulkan scores dwarf those of the GTX 950M, and its average benchmark score is higher despite the GTX 950M having only two recorded tests. The 890M also carries modern architectural features, including 16 ray tracing cores, a 4 nm process, and DirectX 12 Ultimate support, none of which the GTX 950M offers.

For users prioritizing raw compute performance, modern API support, or energy efficiency, the 890M is the obvious choice. Its 15 W TDP compared to 75 W for the GTX 950M means it delivers dramatically higher performance per watt. The GTX 950M, being end-of-life with a 2015 release date, offers no advantage in the recorded benchmarks or feature set. The only scenario where the GTX 950M might be preferable is if a system requires dedicated VRAM, as it has 4 GB of DDR3, whereas the 890M relies on system-shared memory with system-dependent bandwidth.

The percentile rankings, 45th versus 42nd, are close, but the head-to-head deltas are overwhelming. The 890M is not just faster; it is in a different performance class for compute and modern graphics workloads. The GTX 950M remains viable only for legacy DirectX 11-era applications, where its 28 nm Maxwell architecture still functions, but the measured data gives no reason to prefer it over the 890M in any recorded test.

Specification Differences

| Specification | AMD Radeon 890M | NVIDIA GeForce GTX 950M |

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

| Architecture | RDNA 3.5 | Maxwell |

| Process Node | 4 nm | 28 nm |

| Transistors | 34,000 million | 1,870 million |

| Die Size | 233 mm² | 148 mm² |

| Transistor Density | 145.9M / mm² | 12.6M / mm² |

| Base Clock | 400 MHz | 993 MHz |

| Boost Clock | 2,900 MHz | 1,124 MHz |

| Shading Units | 1,024 | 640 |

| TMUs | 64 | 40 |

| ROPs | 32 | 16 |

| Ray Tracing Cores | 16 | None |

| Pixel Rate | 92.80 GPixel/s | 17.98 GPixel/s |

| Texture Rate | 185.6 GTexel/s | 44.96 GTexel/s |

| FP32 | 5.939 TFLOPS | 1,438.7 GFLOPS |

| FP16 | 5.939 TFLOPS (1:1) | None |

| TDP | 15 W | 75 W |

| Memory | System Shared | 4 GB DDR3, 128 bit, 28.80 GB/s |

| Bus Interface | PCIe 4.0 x8 | PCIe 3.0 x8 |

| DirectX | 12 Ultimate (12_2) | 12 (11_0) |

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

| Release Date | 2024-07-14 | 2015-03-12 |

| Predecessor | Navi II IGP | GeForce 800M |

| Successor | None | GeForce 10 Mobile |