GPU Comparison

The AMD Radeon R5 Graphics and NVIDIA GeForce 920MX are both end-of-life mobile graphics solutions from different architectural eras, and benchmark data reveals a split decision. In the Geekbench OpenCL test, the AMD Radeon R5 Graphics scores 5183, while the NVIDIA GeForce 920MX scores 4068, giving AMD a 27.4% advantage. Conversely, in the Geekbench Vulkan test, the NVIDIA GeForce 920MX scores 2987, outmatching the AMD Radeon R5 Graphics’ 2582 by 13.6%. Each GPU claims one benchmark win, making the choice highly dependent on the workload and API in question.

Head-to-Head Benchmarks

The Geekbench OpenCL results show a decisive victory for the AMD Radeon R5 Graphics. With a score of 5183 versus the GeForce 920MX’s 4068, the AMD part leads by 27.4%. This is a substantial margin, indicating that in OpenCL compute workloads, which often leverage general-purpose GPU processing, the Radeon R5 Graphics holds a clear edge. The data places the AMD GPU at the 23rd percentile of all GPUs, with an average benchmark score of 3883, whereas the NVIDIA GPU sits at the 21st percentile with an average of 3528. Despite the lower percentile ranking, the AMD part’s peak OpenCL performance is notably higher.

The Vulkan results flip the script. Here, the NVIDIA GeForce 920MX scores 2987, beating the AMD Radeon R5 Graphics’ 2582 by 13.6%. This suggests that in Vulkan-based applications, which are more common in modern gaming and graphics-heavy tasks, the NVIDIA architecture provides better driver optimization or hardware scheduling. The delta is smaller than AMD’s OpenCL win, but it is still significant. Looking at the nearest rivals for each GPU, the AMD Radeon R5 Graphics sits close to the NVIDIA Quadro 2000 (average score 3898, delta -0.4%) and the NVIDIA Quadro K2000D (average score 3919, delta -0.9%), while the GeForce 920MX is near the NVIDIA GeForce GT 545 (average score 3594, delta -1.8%) and the NVIDIA RTX 5000 Mobile Ada Generation (average score 3596, delta -1.9%). These proximity figures reinforce that both GPUs are in a similar performance tier overall, but their strengths diverge sharply by API.

The head-to-head tally is one win apiece. AMD wins OpenCL with a 27.4% margin; NVIDIA wins Vulkan with a 13.6% margin. This balance means neither GPU is universally superior, the choice hinges on which API the user’s applications prioritize. For compute-heavy OpenCL tasks, the AMD Radeon R5 Graphics is the stronger performer. For Vulkan-based rendering, the NVIDIA GeForce 920MX takes the lead.

Architecture Differences

The architectural gulf between these two GPUs explains their divergent benchmark behavior. The AMD Radeon R5 Graphics is built on GCN 2.0 architecture, specifically the Spectre SL chip, and belongs to the Kaveri IGP generation. It is fabricated on a 28 nm process by GlobalFoundries, with a transistor count of 2,410 million spread over a 245 mm² die size, yielding a transistor density of 9.8 million transistors per square millimeter. In contrast, the NVIDIA GeForce 920MX uses the Maxwell architecture with the GM108S chip, part of the GeForce 900M generation. It is also on a 28 nm process but fabricated by TSMC, with 1,020 million transistors on a much smaller 77 mm² die, achieving a higher transistor density of 13.2 million per square millimeter.

Memory configurations are fundamentally different. The AMD Radeon R5 Graphics uses system shared memory for size, type, bus width, and bandwidth, meaning it relies on the host system’s RAM and has no dedicated VRAM. Its memory bandwidth is listed as system dependent. The NVIDIA GeForce 920MX, however, has dedicated 2 GB of DDR3 memory on a 64-bit bus, delivering 14.40 GB/s of bandwidth. This dedicated memory gives the NVIDIA part a significant advantage in memory-intensive tasks, as it does not compete with the CPU for bandwidth. The NVIDIA GPU’s memory clock runs at 900 MHz with 1800 Mbps effective data rate, while the AMD part’s memory clock is system shared.

Core configurations show both similarities and differences. Both GPUs have 256 shading units, but the NVIDIA GeForce 920MX has 24 texture mapping units (TMUs) and 8 render output units (ROPs), compared to the AMD Radeon R5 Graphics’ 16 TMUs and 4 ROPs. This translates to a higher pixel rate for NVIDIA (7.944 GPixel/s versus 3.032 GPixel/s) and a higher texture rate (23.83 GTexel/s versus 12.13 GTexel/s). The NVIDIA GPU also achieves higher FP32 performance at 508.4 GFLOPS, versus AMD’s 388.1 GFLOPS. Clock speeds differ as well: the NVIDIA GeForce 920MX has a base clock of 965 MHz and a boost clock of 993 MHz, while the AMD Radeon R5 Graphics has no listed base or boost clocks.

Interface and power characteristics also diverge. The AMD Radeon R5 Graphics is an integrated GPU (IGP) with a 15 W TDP, using the system’s motherboard for display outputs. The NVIDIA GeForce 920MX is an MXM module with a 16 W TDP, requiring no power connectors, and uses a PCIe 3.0 x8 bus interface. For API support, AMD lists DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170, while NVIDIA lists DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The higher Vulkan version on the NVIDIA side may contribute to its better Vulkan benchmark performance.

Where Each One Wins

The AMD Radeon R5 Graphics wins in OpenCL compute scenarios. Its 27.4% lead over the GeForce 920MX in Geekbench OpenCL indicates superior raw compute throughput in that API, likely due to the GCN 2.0 architecture’s design for asynchronous compute and general-purpose tasks. For users running OpenCL-accelerated applications, such as certain video encoding, scientific simulations, or data processing workloads, the AMD part is the stronger choice. Its higher average benchmark score of 3883 (versus 3528 for NVIDIA) also suggests more consistent performance across the board, despite its lower percentile ranking.

The NVIDIA GeForce 920MX wins in Vulkan-based workloads, where it leads by 13.6%. This is particularly relevant for gaming and graphics rendering, as Vulkan is a low-level API used in many modern titles. The NVIDIA GPU’s dedicated 2 GB DDR3 memory with 14.40 GB/s bandwidth provides a clear advantage over the AMD part’s system-shared memory, which is dependent on the host system’s RAM speed and capacity. Additionally, the NVIDIA GPU’s higher pixel rate (7.944 GPixel/s versus 3.032 GPixel/s) and texture rate (23.83 GTexel/s versus 12.13 GTexel/s) make it more capable in fill-rate-bound scenarios, which are common in gaming. The NVIDIA part also has a higher FP32 performance (508.4 GFLOPS versus 388.1 GFLOPS), further supporting its graphics throughput.

For memory-bound tasks, the NVIDIA GeForce 920MX is clearly superior due to its dedicated VRAM. The AMD Radeon R5 Graphics must share system memory with the CPU, which can become a bottleneck in texture-heavy or high-resolution workloads. However, for compute tasks that are not memory-bandwidth-limited, the AMD part’s OpenCL performance suggests it can still deliver competitive results. The NVIDIA GPU’s higher transistor density (13.2M / mm² versus 9.8M / mm²) and smaller die size (77 mm² versus 245 mm²) also indicate a more efficient design, which may translate to better performance per watt, despite the similar TDP (16 W versus 15 W).

The Verdict

The data does not crown a single overall winner; instead, it reveals two specialized performers. The AMD Radeon R5 Graphics is the pick for OpenCL compute workloads, where its 27.4% advantage over the GeForce 920MX in Geekbench OpenCL is decisive. Its GCN 2.0 architecture and higher transistor count (2,410 million versus 1,020 million) suggest a design optimized for parallel compute, and its benchmark results confirm this strength. Users who prioritize OpenCL-accelerated applications, such as professional compute tasks or older software relying on that API, should favor the AMD part.

The NVIDIA GeForce 920MX is the better choice for Vulkan-based graphics and gaming. Its 13.6% lead in Geekbench Vulkan, combined with dedicated 2 GB GDDR3 memory and higher pixel/texture rates, makes it more suitable for modern rendering workloads. The NVIDIA GPU’s higher FP32 performance (508.4 GFLOPS) and faster clocks (boost up to 993 MHz) also support its graphics prowess. For users who play Vulkan-enabled games or use Vulkan-based rendering software, the GeForce 920MX delivers a smoother experience.

In terms of absolute performance, the AMD part’s average benchmark score of 3883 exceeds the NVIDIA part’s 3528, indicating that the AMD GPU is generally faster in mixed workloads. However, the NVIDIA GPU’s better Vulkan support and dedicated memory make it a more well-rounded option for gaming. Neither GPU is a clear recommendation over the other; the choice depends entirely on the user’s primary applications. If compute is the focus, choose AMD. If graphics and Vulkan support matter more, choose NVIDIA.

FAQ

Q: Which GPU has a higher Geekbench OpenCL score?

A: The AMD Radeon R5 Graphics scores 5183 in Geekbench OpenCL, which is 27.4% higher than the NVIDIA GeForce 920MX’s score of 4068.

Q: Does the NVIDIA GeForce 920MX perform better in Vulkan benchmarks?

A: Yes, the NVIDIA GeForce 920MX scores 2987 in Geekbench Vulkan, beating the AMD Radeon R5 Graphics’ 2582 by 13.6%.

Q: How much memory does the NVIDIA GeForce 920MX have?

A: The NVIDIA GeForce 920MX has 2 GB of dedicated DDR3 memory on a 64-bit bus, providing 14.40 GB/s of bandwidth. The AMD Radeon R5 Graphics uses system shared memory.

Q: What are the shading unit counts for both GPUs?

A: Both the AMD Radeon R5 Graphics and the NVIDIA GeForce 920MX have 256 shading units. However, the NVIDIA GPU has more TMUs (24 versus 16) and ROPs (8 versus 4).

Q: Which GPU has a higher transistor count?

A: The AMD Radeon R5 Graphics has 2,410 million transistors, while the NVIDIA GeForce 920MX has 1,020 million transistors, making the AMD chip larger in that regard.

Q: What is the TDP difference between the two GPUs?

A: The AMD Radeon R5 Graphics has a TDP of 15 W, while the NVIDIA GeForce 920MX has a TDP of 16 W, a difference of just 1 W.