AMD Radeon R5 M420 vs NVIDIA GeForce 940MX Comparison

Head-to-Head Benchmarks

The database records a single direct comparison between these two mobile graphics processors: the Geekbench OpenCL test. In that measurement, the NVIDIA GeForce 940MX scores 4939, while the AMD Radeon R5 M420 scores 3956. The delta is 19.9 percent, meaning NVIDIA wins this head-to-head by a substantial margin. To put it plainly, the 940MX delivers roughly one-fifth more compute throughput in this OpenCL workload.

Looking beyond the direct matchup, the average benchmark scores reinforce the same hierarchy. The 940MX holds an average score of 4844 across all recorded tests, while the R5 M420 averages 3956. That is a gap of 888 points, or about 22.4 percent. The R5 M420's nearest rivals in the database are all NVIDIA parts or older AMD cards: the GeForce 830M sits at 3957, the GeForce GT 745M at 3953, and the Quadro K2000 at 3964. The R5 M420 essentially trades blows with these, landing within a range of 0.5 percent in either direction. Its percentile ranking among all GPUs is 23, placing it in the lower quarter of the database.

The 940MX, by contrast, aligns with a noticeably faster group. Its nearest rivals include the GeForce GTX 560M at 4855, the AMD Radeon R6 M255DX at 4867, and the GeForce GTS 450 at 4893. The 940MX's average score of 4844 is within 1 percent of all three. Interestingly, the database also lists the GeForce RTX 3080 12 GB as a nearest rival with an average score of 4791, which is 1.1 percent below the 940MX. That result is an outlier relative to the other entries, but it reflects the recorded data: the 940MX outperforms that high-end desktop card in this particular aggregated metric. The 940MX also has a Vulkan score of 4749, which is lower than its OpenCL score but still far above the R5 M420's only recorded result.

The wins tally is decisive: one win for the 940MX, zero for the R5 M420. No benchmark in the database shows the AMD part ahead.

Architecture Differences

The two chips come from different architectural generations and different design philosophies. The AMD Radeon R5 M420 uses the Jet chip built on GCN 1.0, while the NVIDIA GeForce 940MX uses the GM107 chip built on Maxwell. Both are manufactured by TSMC on a 28 nm process node, so the fabrication process is identical. The transistor counts, however, differ enormously. The NVIDIA chip packs 1,870 million transistors on a 148 mm² die, whereas the AMD chip has just 690 million transistors on a 56 mm² die. Transistor density is nearly the same, 12.6M per mm² for NVIDIA versus 12.3M per mm² for AMD, which makes sense given the shared process node. The 940MX simply uses a much larger die to house more compute resources.

The execution resources tell the story. The 940MX has 512 shading units, 32 texture mapping units, and 8 raster operation units. The R5 M420 has 320 shading units, 20 TMUs, and 8 ROPs. So the NVIDIA part has 60 percent more shaders and 60 percent more TMUs, while the ROP count is identical. These differences translate directly into theoretical throughput. The 940MX reaches 881.7 GFLOPS of FP32 compute, compared to 544.0 GFLOPS for the R5 M420. Texture fill rate is 27.55 GTexel/s versus 17.00 GTexel/s. Pixel rates are nearly identical, 6.888 GPixel/s for NVIDIA and 6.800 GPixel/s for AMD, because both have 8 ROPs and similar clock speeds.

Memory is another major divergence. The R5 M420 comes with 4 GB of DDR3 on a 64-bit bus, yielding 16.00 GB/s of bandwidth. The 940MX has 2 GB of GDDR5 on the same 64-bit bus, but its memory clock runs at 1253 MHz with 5 Gbps effective speed, producing 40.10 GB/s of bandwidth. That is 2.5 times the memory bandwidth of the AMD part, a critical advantage for texture-heavy workloads. The AMD card's memory runs at 1000 MHz with 2 Gbps effective speed.

Clock speeds are close. The R5 M420 has a base clock of 780 MHz and a boost of 850 MHz. The 940MX has a base of 795 MHz and a boost of 861 MHz. The NVIDIA chip runs slightly higher in both states, though the difference is small. The 940MX carries a TDP of 23 W, while the R5 M420 has no recorded TDP in the database. The 940MX is listed as an MXM Module, while the R5 M420 is an IGP, indicating the AMD part is typically soldered into a motherboard rather than socketed as a discrete module.

API support differs at the margins. Both support DirectX 12 and OpenGL 4.6. The AMD part supports DirectX 12 (11_1) and Vulkan 1.2.170, while the NVIDIA part supports DirectX 12 (11_0) and Vulkan 1.4. The R5 M420's GCN 1.0 architecture is older in design lineage, while Maxwell is a later NVIDIA microarchitecture. Both are end-of-life products, with the AMD part released on May 14, 2016, and the NVIDIA part on June 27, 2016.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce 940MX, with an average score of 4844 across all recorded tests, compared to 3956 for the AMD Radeon R5 M420.

Q: How much faster is the 940MX in the direct OpenCL comparison?

A: The 940MX scores 4939 versus 3956 for the R5 M420, a delta of 19.9 percent.

Q: Do both GPUs use the same manufacturing process?

A: Yes, both are built by TSMC on a 28 nm process node, and their transistor densities are nearly identical at 12.6M per mm² for NVIDIA and 12.3M per mm² for AMD.

Q: What is the memory bandwidth difference?

A: The 940MX has 40.10 GB/s of bandwidth using 2 GB of GDDR5 on a 64-bit bus. The R5 M420 has 16.00 GB/s using 4 GB of DDR3 on the same 64-bit bus.

Q: Which GPU has more shading units?

A: The 940MX has 512 shading units, while the R5 M420 has 320. The NVIDIA part also has 32 TMUs versus 20 for AMD.

Q: What is the release date gap between the two?

A: The R5 M420 was released on May 14, 2016, and the 940MX followed on June 27, 2016, a gap of about six weeks.

The Verdict

The recorded data points to a clear winner: the NVIDIA GeForce 940MX. It wins the only head-to-head benchmark, holds a higher average score, and outperforms the R5 M420 across every architectural metric that matters for compute throughput. The 940MX delivers 19.9 percent more OpenCL performance in the direct comparison, and its average score advantage is even larger at 22.4 percent. Its shading unit count is 60 percent higher, its texture rate is 62 percent higher, and its memory bandwidth is 2.5 times higher.

The R5 M420 does have one advantage in capacity: it offers 4 GB of memory versus 2 GB on the 940MX. For workloads that need more frame buffer capacity rather than bandwidth, the AMD part could hold more data locally. However, the memory type difference matters. DDR3 at 16.00 GB/s is a severe bottleneck, and the lower bandwidth will limit how effectively that 4 GB can be used. The R5 M420 also has a lower transistor count and a smaller die, which suggests lower power draw, but the database does not record a TDP for the AMD part, so this cannot be quantified.

The 940MX's nearest rival group includes the GTX 560M and R6 M255DX, both within 0.5 percent of its average score. That places it in a performance tier that is roughly comparable to mid-range GPUs from the 2011-2014 era. The R5 M420, by contrast, sits alongside the GeForce 830M and GT 745M, which are entry-level parts from similar generations. The percentile rankings reflect this: 28 for the 940MX versus 23 for the R5 M420.

For a buyer choosing between these two in a used or legacy laptop, the data supports the 940MX without qualification. It is faster in compute, faster in memory throughput, and has more execution resources. The only scenario where the R5 M420 might be preferable is if a specific application requires more than 2 GB of video memory and can tolerate the much lower bandwidth. That is a narrow use case, and the benchmark data does not include a test that would validate it.

Specification Differences

The two GPUs differ in nearly every specification category except process node, foundry, bus interface, ROP count, and display outputs. Both use TSMC's 28 nm process and PCIe 3.0 x8. Both have 8 ROPs and portable device dependent display outputs.

The transistor count is 1,870 million for NVIDIA versus 690 million for AMD. Die size is 148 mm² versus 56 mm². The 940MX has 512 shading units, 32 TMUs, and a base clock of 795 MHz with a boost of 861 MHz. The R5 M420 has 320 shading units, 20 TMUs, and a base clock of 780 MHz with a boost of 850 MHz. Memory configuration: 940MX uses 2 GB GDDR5 at 1253 MHz with 5 Gbps effective speed and 40.10 GB/s bandwidth. The R5 M420 uses 4 GB DDR3 at 1000 MHz with 2 Gbps effective speed and 16.00 GB/s bandwidth.

Theoretical rates: 940MX reaches 881.7 GFLOPS FP32, 27.55 GTexel/s, and 6.888 GPixel/s. The R5 M420 reaches 544.0 GFLOPS, 17.00 GTexel/s, and 6.800 GPixel/s. The 940MX has a TDP of 23 W and is an MXM Module with no power connectors. The R5 M420 is an IGP with no recorded TDP. API support: both have OpenGL 4.6, but the 940MX lists DirectX 12 (11_0) and Vulkan 1.4, while the R5 M420 lists DirectX 12 (11_1) and Vulkan 1.2.170. Release dates differ by about six weeks in 2016, with NVIDIA launching later.

Where Each One Wins

The NVIDIA GeForce 940MX wins in every benchmark category recorded in the database. It has the higher OpenCL score (4939 versus 3956), the higher average score (4844 versus 3956), and the only Vulkan score in the comparison (4749). Its FP32 throughput is 62 percent higher, its texture rate is 62 percent higher, and its memory bandwidth is 150 percent higher. Any workload that stresses compute shaders, texture fetches, or memory throughput will favor the 940MX by a wide margin.

The AMD Radeon R5 M420 wins in exactly one measurable specification: memory capacity. It offers 4 GB versus 2 GB. For applications that allocate large textures or datasets that fit within 4 GB but not 2 GB, the AMD part might avoid spillover to system memory. However, the DDR3 interface at 16.00 GB/s will likely negate this advantage in practice, as the lower bandwidth will throttle data movement before capacity becomes the limiting factor.

The 940MX also holds the edge in architecture maturity. Maxwell is a newer design than GCN 1.0, and the database shows this in the Vulkan score of 4749, which is only 3.8 percent below its own OpenCL score. The R5 M420 has no Vulkan score recorded, so its Vulkan performance cannot be compared directly. The 940MX's DX12 support at feature level 11_0 is slightly older than the R5 M420's 11_1, but this is a minor API-level difference that does not show up in the benchmark results.

For gaming, the 940MX is the stronger choice based on the data. Higher shader counts, more texture units, and vastly higher memory bandwidth all contribute to frame rate in typical game workloads. The R5 M420 could be acceptable for very light 2D workloads or older titles with low texture demands, but its 23rd percentile ranking among all GPUs indicates it sits near the bottom of the performance distribution. The 940MX's 28th percentile is also low in absolute terms, but relative to the R5 M420, it is clearly the superior part.

In summary, the database records no scenario where the R5 M420 outperforms the 940MX. The NVIDIA part wins the head-to-head, wins the average score comparison, and wins on every throughput metric. The AMD part's only consolation is its larger memory pool, which is a capacity advantage that the bandwidth bottleneck severely limits. A system builder or buyer choosing between these two should select the 940MX based on the recorded measurements.