AMD Radeon R5 M330 vs NVIDIA GeForce 920MX Comparison

Head-to-Head Benchmarks

The recorded data shows a clear pair of victories for the AMD Radeon R5 M330 in the two head-to-head tests available. In the Geekbench OpenCL benchmark, the AMD part scores 4302 against the NVIDIA GeForce 920MX’s 4068, a lead of 5.8%. This is a modest but consistent advantage in a compute-oriented workload. The Vulkan test tells a more dramatic story, with the R5 M330 posting 4037 points versus the 920MX’s 2987, a delta of 35.2%. That is a substantial gap, and it suggests the AMD architecture handles the Vulkan API’s low-level execution model with considerably more efficiency in this configuration.

The average benchmark score across all recorded tests reinforces the pattern. The R5 M330 averages 4170 points, placing it in the 25th percentile of all GPUs in the database. The 920MX averages 3528 points, sitting in the 21st percentile. The difference in averages is 642 points, which is roughly an 18% gap. Looking at the nearest rivals for each card provides additional context. The R5 M330’s closest competitors include the NVIDIA Quadro K2100M at 4151 (only 0.4% behind), the GeForce GTX 1050 Ti at 4193 (0.5% ahead), the Quadro K3000M at 4241 (1.7% ahead), and the AMD Radeon RX 9060 XT 8 GB at 4093 (1.9% behind). This clustering indicates the R5 M330 sits within a tight performance band where small percentage shifts change the ranking order.

For the 920MX, its nearest rivals include the GeForce GT 545 at 3594 (1.8% ahead), the RTX 5000 Mobile Ada Generation at 3596 (1.9% ahead), the GeForce GT 735M at 3616 (2.4% ahead), and the Quadro 2000M at 3434 (2.7% behind). The 920MX trails most of its immediate peers in the database, with only the Quadro 2000M below it. This places the NVIDIA part in a lower overall standing relative to its own competitive set, while the AMD card holds a position that is roughly neutral against its nearest rivals, with deltas ranging from -1.7% to +1.9%.

The win count is unambiguous: the R5 M330 takes both tests, with 2 wins and 0 for the 920MX. No benchmark in the database shows the NVIDIA part outperforming the AMD part. This is not a case of split results where each card excels in different scenarios; the data points in one direction across both OpenCL and Vulkan.

Where Each One Wins

The use-case split follows directly from the benchmark results. The AMD Radeon R5 M330 wins in compute-heavy tasks that leverage OpenCL, as shown by its 4302 score. This is the kind of workload found in general-purpose GPU computing, video encoding, and certain physics simulations. The 5.8% lead over the 920MX in this area is real but not overwhelming; it means the AMD card will complete these tasks somewhat faster, but not to a degree that would transform the user experience.

The Vulkan result is where the R5 M330 truly separates itself. A 35.2% advantage in this API is significant. Vulkan is increasingly used in modern game engines and professional visualization tools that require fine-grained control over GPU resources. The higher score suggests the GCN 1.0 architecture in the AMD part handles the command buffer and draw call overhead more effectively than the Maxwell-based NVIDIA chip in this specific test. For any application that relies on Vulkan, the R5 M330 is the clear choice based on the recorded measurements.

For the NVIDIA GeForce 920MX, there is no benchmark win to point to. The closest it comes is the OpenCL test, where it is only 5.8% behind. In Vulkan, the deficit is too large to ignore. The 920MX does have a slightly higher texture rate on paper, 23.83 GTexel/s versus 20.60 GTexel/s, and a higher base clock, 965 MHz versus 955 MHz. However, these specification advantages do not translate into a single benchmark victory. The data indicates that the 920MX would be the weaker option in both general compute and Vulkan-specific scenarios covered by the database.

The percentile rankings reinforce this split. The R5 M330 at the 25th percentile is in the lower quarter of all GPUs, but it is four percentage points higher than the 920MX at the 21st percentile. In a pool of hundreds of GPUs, this difference represents a meaningful number of cards that the AMD part outranks. The average score of 4170 for the R5 M330 versus 3528 for the 920MX confirms that, across the full set of recorded tests, the AMD card delivers more performance per unit of work.

Architecture Differences

The two GPUs come from different architectural lineages. The AMD Radeon R5 M330 uses the GCN 1.0 architecture, built on a chip codenamed Exo. The NVIDIA GeForce 920MX uses the Maxwell architecture, built on the GM108S chip. Both are manufactured by TSMC on a 28 nm process node, so the underlying fabrication technology is identical. The transistor counts differ substantially: the AMD chip packs 690 million transistors on a 56 mm² die, while the NVIDIA chip has 1,020 million transistors on a 77 mm² die. The transistor density is 12.3M per mm² for AMD and 13.2M per mm² for NVIDIA, indicating the NVIDIA chip is slightly denser.

The compute core configurations diverge. The R5 M330 has 320 shading units, 20 texture mapping units, and 8 ROPs. The 920MX has 256 shading units, 24 texture mapping units, and 8 ROPs. This means the AMD card has more shader processors but fewer texture units. The pixel rate for the R5 M330 is 8.240 GPixel/s versus 7.944 GPixel/s for the 920MX, a small but real advantage for AMD. The texture rate is reversed, with the NVIDIA part achieving 23.83 GTexel/s against AMD’s 20.60 GTexel/s. The FP32 throughput follows the shader count: the R5 M330 delivers 659.2 GFLOPS, while the 920MX delivers 508.4 GFLOPS. Neither card has dedicated RT cores or tensor cores, and neither lists FP16 performance.

Memory configurations are identical on paper. Both use 2 GB of DDR3 with a 64-bit bus and 14.40 GB/s of bandwidth. The memory clock is the same at 900 MHz with 1800 Mbps effective data rate. Clock speeds are close, with the R5 M330 at 955 MHz base and 1030 MHz boost, versus the 920MX at 965 MHz base and 993 MHz boost. The AMD part has a higher boost clock, which likely contributes to its compute edge. The TDP is 18 W for AMD and 16 W for NVIDIA, a difference of 2 W that is minor for mobile parts. The slot width is listed as IGP for AMD and MXM Module for NVIDIA, indicating different physical integration methods.

API support shows subtle differences. The R5 M330 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The 920MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The Vulkan version difference is notable, as the NVIDIA card supports a newer specification, yet it still scores significantly lower in the Vulkan benchmark. The bus interface is PCIe 3.0 x8 for both, and display outputs are portable-device dependent for both.

The Verdict

The database points to a clear winner in the AMD Radeon R5 M330. It wins both head-to-head benchmarks, with a 5.8% advantage in OpenCL and a 35.2% advantage in Vulkan. Its average benchmark score of 4170 is 18% higher than the 920MX’s 3528, and its 25th percentile ranking is four points above the NVIDIA part’s 21st percentile. For anyone choosing between these two for a system that will run Vulkan-based games or compute workloads, the R5 M330 is the evidence-backed option.

The 920MX is not without merit. Its texture rate is higher, and its power draw is 2 W lower. For a system where texture-heavy but shader-light workloads dominate, and where power efficiency is paramount, the NVIDIA part could be the better fit. However, the recorded benchmarks do not show a single test where the 920MX wins. The closest it comes is OpenCL, where it trails by a small margin. The Vulkan gap is too large to overcome through any speculative use case.

The R5 M330’s nearest rival cluster shows it is competitive with a range of other GPUs. It sits within 2 percentage points of the Quadro K2100M, GTX 1050 Ti, Quadro K3000M, and RX 9060 XT 8 GB in the database. This suggests the AMD card is not an outlier but rather a solid mid-to-low tier performer. The 920MX, by contrast, trails most of its nearest rivals, with only the Quadro 2000M below it. The data implies that the 920MX is a weaker entry in its own class.

For a user with an existing system that has a 920MX, upgrading to the R5 M330 would provide a measurable performance uplift in compute and Vulkan tasks. For a user building a new system, the R5 M330 is the better choice unless the 2 W lower TDP of the 920MX is a critical constraint. The production status for both is end-of-life, so neither is a future-proof option, but among the two, the AMD part leads in every recorded test.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R5 M330 has an average benchmark score of 4170, while the NVIDIA GeForce 920MX has an average of 3528.

Q: How big is the Vulkan performance gap between the two?

A: The R5 M330 scores 4037 in Geekbench Vulkan, while the 920MX scores 2987, a 35.2% advantage for the AMD part.

Q: Do both cards have the same memory configuration?

A: Yes, both have 2 GB of DDR3, a 64-bit bus width, and 14.40 GB/s of bandwidth.

Q: What is the power draw difference?

A: The R5 M330 has a TDP of 18 W, while the 920MX has a TDP of 16 W.

Q: Which GPU has more shading units?

A: The AMD Radeon R5 M330 has 320 shading units, while the NVIDIA GeForce 920MX has 256.

Q: What is the release date difference?

A: The R5 M330 was released on 2015-05-04, and the 920MX was released on 2016-03-24.

Specification Differences

| Specification | AMD Radeon R5 M330 | NVIDIA GeForce 920MX |

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

| Chip | Exo | GM108S |

| Architecture | GCN 1.0 | Maxwell |

| Generation | Gem System (R5 M300) | GeForce 900M |

| Transistors | 690 million | 1,020 million |

| Die Size | 56 mm² | 77 mm² |

| Transistor Density | 12.3M / mm² | 13.2M / mm² |

| Base Clock | 955 MHz | 965 MHz |

| Boost Clock | 1030 MHz | 993 MHz |

| Shading Units | 320 | 256 |

| TMUs | 20 | 24 |

| Pixel Rate | 8.240 GPixel/s | 7.944 GPixel/s |

| Texture Rate | 20.60 GTexel/s | 23.83 GTexel/s |

| FP32 | 659.2 GFLOPS | 508.4 GFLOPS |

| TDP | 18 W | 16 W |

| Slot Width | IGP | MXM Module |

| DirectX | 12 (11_1) | 12 (11_0) |

| Vulkan | 1.2.170 | 1.4 |

| Release Date | 2015-05-04 | 2016-03-24 |

| Predecessor | Solar System | GeForce 800M |

| Successor | Polaris Mobile | GeForce 10 Mobile |

| Benchmark Average | 4170 | 3528 |

| Percentile | 25 | 21 |

| OpenCL Score | 4302 | 4068 |

| Vulkan Score | 4037 | 2987 |