AMD Radeon R5 M255 vs NVIDIA GeForce 940MX Comparison

The Verdict

The benchmark data splits this pair almost perfectly down the middle. In Geekbench OpenCL, the NVIDIA GeForce 940MX scores 4939 against the AMD Radeon R5 M255’s 4650, a 6.2% advantage. In Geekbench Vulkan, the AMD Radeon R5 M255 reverses the result with 4925 versus 4749, a 3.6% lead for AMD. Each GPU wins one test, and the average benchmark scores reflect that near-parity: the 940MX sits at 4844, while the R5 M255 sits at 4788. Both cards land in the 28th percentile of all GPUs, meaning they occupy the same performance tier.

For a buyer choosing strictly from this data, the decision hinges on workload. If the target applications rely on OpenCL — common in older compute tasks and some content-creation pipelines — the NVIDIA GeForce 940MX is the pick. Its 6.2% margin is modest but consistent. If the workload uses Vulkan — increasingly relevant for modern games and emulators — the AMD Radeon R5 M255 takes the edge, though its 3.6% advantage is smaller than NVIDIA’s OpenCL win. There is no dominant overall winner. The data shows a tie in head-to-head wins at one apiece. Given the near-identical average scores and percentile ranking, neither GPU offers a compelling universal advantage. The choice should be dictated by the specific API used in the primary applications.

Architecture Differences

The two GPUs come from different architectural lineages. The NVIDIA GeForce 940MX uses the GM107 chip built on the Maxwell architecture, part of the GeForce 900M generation. The AMD Radeon R5 M255 uses the Topaz chip built on GCN 3.0, belonging to the Gem System (R5 M200) generation. Both are fabricated by TSMC on the same 28 nm process node, which explains their similar transistor densities: 12.6M per mm² for NVIDIA and 12.4M per mm² for AMD.

The chip-level differences are substantial. NVIDIA’s GM107 packs 1,870 million transistors on a 148 mm² die, while AMD’s Topaz packs 1,550 million transistors on a 125 mm² die. Despite the smaller transistor count, AMD’s chip runs at higher clocks: the base clock is 925 MHz versus 795 MHz, and the boost clock is 940 MHz versus 861 MHz. However, NVIDIA compensates with more execution resources. The 940MX has 512 shading units, 32 texture mapping units, and 8 ROPs. The R5 M255 has 384 shading units, 24 TMUs, and 8 ROPs.

Memory architecture differs fundamentally. The 940MX uses 2 GB of GDDR5 on a 64-bit bus, yielding a bandwidth of 40.10 GB/s. The R5 M255 uses 2 GB of DDR3 on a 128-bit bus, yielding 32.00 GB/s. NVIDIA’s memory clock is 1253 MHz (5 Gbps effective), while AMD’s is 1000 MHz (2 Gbps effective). The wider bus on AMD’s side does not overcome the slower memory type. API support also diverges: NVIDIA lists DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4, while AMD lists DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. Both use the PCIe 3.0 x8 bus interface.

Head-to-Head Benchmarks

The Geekbench OpenCL result is NVIDIA’s clearest victory. The 940MX scores 4939, beating the R5 M255’s 4650 by 6.2%. This margin is meaningful in the context of their nearest rivals. The 940MX’s average score of 4844 places it just 0.2% behind the NVIDIA GeForce GTX 560M (4855) and 1% behind the NVIDIA GeForce GTS 450 (4893). The R5 M255’s average score of 4788 places it 0.8% ahead of the AMD Radeon R5 M335 (4752) and 1.3% ahead of the AMD Radeon R8 M445DX (4727). In OpenCL, the 940MX’s higher shading unit count and faster GDDR5 memory likely drive its advantage.

The Geekbench Vulkan result flips the script. The R5 M255 scores 4925, beating the 940MX’s 4749 by 3.6%. This is a notable reversal given the architectural differences. The R5 M255’s Vulkan score is actually higher than its OpenCL score (4925 versus 4650), while the 940MX’s Vulkan score is lower than its OpenCL score (4749 versus 4939). This suggests the AMD GPU handles Vulkan workloads with greater efficiency relative to its OpenCL performance. The deltaPct values in the head-to-head data confirm the split: +6.2% for NVIDIA in OpenCL, -3.6% for NVIDIA in Vulkan. The wins are evenly distributed at one apiece.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce 940MX has an average benchmark score of 4844, while the AMD Radeon R5 M255 has 4788. The difference is 56 points, roughly 1.2%.

Q: Does either GPU win in both benchmark tests?

A: No. The NVIDIA GeForce 940MX wins Geekbench OpenCL (4939 versus 4650), and the AMD Radeon R5 M255 wins Geekbench Vulkan (4925 versus 4749). Each has one win.

Q: How do these GPUs compare to the NVIDIA GeForce RTX 3080 12 GB?

A: Both GPUs are listed as nearest rivals to the RTX 3080 12 GB. The 940MX is 1.1% ahead of it in average score, and the R5 M255 is 0.1% behind it. This indicates the RTX 3080 12 GB sits in the same performance neighborhood in this benchmark database, despite its different market position.

Q: What memory configurations do they use?

A: The NVIDIA GeForce 940MX uses 2 GB of GDDR5 on a 64-bit bus with 40.10 GB/s bandwidth. The AMD Radeon R5 M255 uses 2 GB of DDR3 on a 128-bit bus with 32.00 GB/s bandwidth.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce 940MX has 512 shading units, compared to 384 on the AMD Radeon R5 M255. The 940MX also has more TMUs (32 versus 24), while both have 8 ROPs.

Q: What is the production status of both GPUs?

A: Both are listed as end-of-life products. The NVIDIA GeForce 940MX was released on 2016-06-27, and the AMD Radeon R5 M255 was released on 2014-10-11.

Where Each One Wins

The NVIDIA GeForce 940MX wins in OpenCL compute workloads. Its score of 4939 in Geekbench OpenCL is 6.2% higher than AMD’s. This advantage is consistent with its higher shading unit count (512 versus 384), higher texture rate (27.55 GTexel/s versus 22.56 GTexel/s), and higher FP32 throughput (881.7 GFLOPS versus 721.9 GFLOPS). The GDDR5 memory also provides higher bandwidth (40.10 GB/s versus 32.00 GB/s), which can benefit memory-intensive compute tasks. Applications that rely on OpenCL — scientific computing, video encoding, some rendering workloads — would favor the 940MX.

The AMD Radeon R5 M255 wins in Vulkan workloads. Its score of 4925 in Geekbench Vulkan is 3.6% higher than NVIDIA’s. This is notable because AMD’s hardware is otherwise less powerful on paper — fewer shading units, lower FP32, and slower memory bandwidth. The Vulkan win suggests the GCN 3.0 architecture handles this API more efficiently. Vulkan-based games, emulators, and modern graphics applications would see better performance on the R5 M255. The higher base clock (925 MHz versus 795 MHz) and boost clock (940 MHz versus 861 MHz) may contribute to this advantage, as Vulkan tends to scale with clock speed in certain draw-call scenarios.

For mixed workloads that use both OpenCL and Vulkan, the data does not favor either GPU decisively. The average scores are close (4844 versus 4788), and the percentile rankings are identical at 28. Users who prioritize OpenCL should choose the 940MX, while users who prioritize Vulkan should choose the R5 M255.

Specification Differences

The two GPUs differ across nearly every specification field. The process node is identical (28 nm, TSMC for both), but the chips themselves are distinct: GM107 for NVIDIA versus Topaz for AMD. Transistor counts differ: 1,870 million versus 1,550 million. Die sizes differ: 148 mm² versus 125 mm². Transistor density is nearly the same at 12.6M per mm² versus 12.4M per mm².

Clock speeds favor AMD. The R5 M255 has a base clock of 925 MHz and a boost clock of 940 MHz, while the 940MX has a base clock of 795 MHz and a boost clock of 861 MHz. Memory clocks also differ: NVIDIA runs at 1253 MHz (5 Gbps effective), AMD at 1000 MHz (2 Gbps effective). Memory type and bus width differ: GDDR5 on a 64-bit bus for NVIDIA, DDR3 on a 128-bit bus for AMD. Bandwidth favors NVIDIA at 40.10 GB/s versus 32.00 GB/s.

Compute resources favor NVIDIA. Shading units are 512 versus 384, TMUs are 32 versus 24, and ROPs are equal at 8. Pixel rate slightly favors AMD at 7.520 GPixel/s versus 6.888 GPixel/s. Texture rate favors NVIDIA at 27.55 GTexel/s versus 22.56 GTexel/s. FP32 favors NVIDIA at 881.7 GFLOPS versus 721.9 GFLOPS. AMD lists FP16 at 721.9 GFLOPS (1:1), while NVIDIA lists no FP16 value.

Power and physical specifications differ. The 940MX has a TDP of 23 W and uses an MXM Module slot width with no power connectors. The R5 M255 has no listed TDP, slot width, or power connector information. Both use PCIe 3.0 x8. Display outputs are listed as portable device dependent for NVIDIA, and null for AMD. API support differs in DirectX version (12_11_0 for NVIDIA versus 12_12_0 for AMD) and Vulkan version (1.4 versus 1.2.170). Release dates differ: 2016-06-27 for NVIDIA, 2014-10-11 for AMD. Neither has a launch MSRP listed.