AMD Radeon R5 M420 vs NVIDIA GeForce GTX 650 Comparison

The AMD Radeon R5 M420 and NVIDIA GeForce GTX 650 represent two very different approaches to graphics hardware, separated by nearly three years of release timing and targeting distinct market segments. The data shows a clear performance hierarchy, but the architectural and specification gaps reveal a more nuanced story about what each part was designed to accomplish.

Head-to-Head Benchmarks

The only direct benchmark comparison available in the data is the Geekbench OpenCL test, and it delivers a decisive verdict. The NVIDIA GeForce GTX 650 scores 4545 points, while the AMD Radeon R5 M420 manages 3956 points. That translates to a 13% delta in favor of the GTX 650, which is the sole head-to-head win recorded between the two parts. The AMD card trails by roughly 589 points, a margin that places it firmly behind in raw compute workloads.

Looking at the broader context, the GTX 650’s OpenCL result is not an isolated spike. Its average benchmark score across all tested workloads sits at 3823, which includes additional Metal and Vulkan scores of 2400 and 4524 respectively. The R5 M420, by contrast, has only a single OpenCL result, making its average score identical to that single run at 3956. This means the GTX 650’s OpenCL advantage is even more pronounced when considering its Vulkan score of 4524, which nearly matches its OpenCL performance. The AMD part has no Vulkan or Metal scores in the data, so its capabilities in those APIs remain unquantified.

The percentile rankings tell a similar story. The R5 M420 sits at the 23rd percentile of all GPUs, while the GTX 650 is at the 22nd percentile. Despite the GTX 650 winning the head-to-head, both parts occupy nearly the same position in the global performance distribution, which suggests that the 13% gap in OpenCL does not translate into a dramatically different standing among all graphics cards. The R5 M420’s nearest rivals include the NVIDIA GeForce 830M with a nearly identical average score of 3957 (0% delta), the GeForce GT 745M at 3953 (0.1% delta), and the Quadro K2000 at 3964 (-0.2% delta). The GTX 650’s closest competition includes the GeForce MX110 at 3834 (-0.3% delta), Intel UHD Graphics 710 at 3792 (0.8% delta), and the Radeon R5 Graphics at 3883 (-1.5% delta).

The performance gap between the two parts is consistent with their hardware configurations. The GTX 650’s FP32 throughput of 812.5 GFLOPS exceeds the R5 M420’s 544.0 GFLOPS by roughly 49%, and its texture rate of 33.86 GTexel/s is nearly double the AMD part’s 17.00 GTexel/s. Pixel rates follow the same pattern, with the GTX 650 delivering 8.464 GPixel/s versus 6.800 GPixel/s for the R5 M420. These raw throughput advantages explain why the GTX 650 wins the OpenCL test despite both parts being end-of-life products.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 650 scores 4545 points in Geekbench OpenCL, which is 13% higher than the AMD Radeon R5 M420’s score of 3956 points.

Q: How do these two cards compare in terms of global GPU percentile ranking?

A: The AMD Radeon R5 M420 ranks at the 23rd percentile of all GPUs, while the NVIDIA GeForce GTX 650 ranks at the 22nd percentile. Despite the GTX 650 winning the head-to-head benchmark, their overall standings are nearly identical.

Q: What memory configurations do the two cards use?

A: The AMD Radeon R5 M420 has 4 GB of DDR3 memory on a 64-bit bus with 16.00 GB/s bandwidth. The NVIDIA GeForce GTX 650 has 1024 MB of GDDR5 memory on a 128-bit bus with 80.00 GB/s bandwidth.

Q: Do both cards support the same API levels?

A: Both support DirectX 12 and OpenGL 4.6, but there are differences in the specific DirectX feature levels. The AMD card supports DirectX 12 (11_1), while the NVIDIA card supports DirectX 12 (11_0). The GTX 650 has a newer Vulkan version at 1.2.175 compared to the R5 M420’s 1.2.170.

Q: What are the transistor counts for each chip?

A: The AMD Radeon R5 M420 uses the Jet chip with 690 million transistors on a 56 mm² die. The NVIDIA GeForce GTX 650 uses the GK106 chip with 2,540 million transistors on a 221 mm² die.

Q: Which card has more shading units and texture mapping units?

A: The NVIDIA GeForce GTX 650 has 384 shading units and 32 TMUs, while the AMD Radeon R5 M420 has 320 shading units and 20 TMUs. The GTX 650 also has 16 ROPs compared to 8 on the AMD part.

Architecture Differences

The two GPUs come from fundamentally different architectural families. The AMD Radeon R5 M420 is built on Graphics Core Next 1.0 (GCN 1.0) using the Jet chip, while the NVIDIA GeForce GTX 650 uses the Kepler architecture with the GK106 chip. Both are fabricated on a 28 nm process at TSMC, but that is where the manufacturing similarities end.

The transistor counts reveal a massive difference in complexity. The GTX 650’s GK106 packs 2,540 million transistors onto a 221 mm² die, while the R5 M420’s Jet chip contains just 690 million transistors on a 56 mm² die. This translates to a transistor density of 11.5M per mm² for the NVIDIA part and 12.3M per mm² for the AMD part. The GTX 650’s die is nearly four times larger, which explains its substantially higher compute throughput across every measured metric.

Memory architecture diverges sharply as well. The R5 M420 uses 4 GB of DDR3 memory with a 64-bit bus, yielding 16.00 GB/s of bandwidth. The GTX 650 uses 1024 MB of GDDR5 memory on a 128-bit bus, delivering 80.00 GB/s — exactly five times the bandwidth of the AMD part. The effective memory clock differs accordingly: the AMD card runs at 2 Gbps effective while the NVIDIA card runs at 5 Gbps effective. The GTX 650’s memory advantage is arguably its most significant architectural edge, since the R5 M420’s narrow bus and slower DDR3 memory create a severe bandwidth bottleneck.

The shading resources also favor the GTX 650. It has 384 shading units and 32 TMUs, compared to 320 shading units and 20 TMUs on the R5 M420. The ROP count doubles from 8 on the AMD part to 16 on the NVIDIA part. These differences directly feed into the pixel rate (8.464 GPixel/s vs 6.800 GPixel/s) and texture rate (33.86 GTexel/s vs 17.00 GTexel/s) figures. The FP32 compute capability of 812.5 GFLOPS on the GTX 650 versus 544.0 GFLOPS on the R5 M420 rounds out the compute picture.

The bus interfaces differ as well. The R5 M420 connects via PCIe 3.0 x8, while the GTX 650 uses PCIe 3.0 x16. This gives the NVIDIA card twice the PCIe bandwidth for data transfers, though the practical impact depends on the workload. The R5 M420 is classified as an IGP (integrated graphics processor) with portable device-dependent display outputs, while the GTX 650 is a single-slot discrete card measuring 147 mm in length with 1x DVI and 2x DisplayPort 1.2 outputs.

Power requirements highlight the positioning of each card. The R5 M420 has no listed TDP, no power connectors, and no suggested PSU rating, consistent with its integrated nature. The GTX 650 carries a 65 W TDP, requires a single 6-pin power connector, and has a suggested PSU rating of 250 W. The NVIDIA card is clearly designed as a drop-in discrete solution for desktop systems, while the AMD part targets mobile or compact platforms where power delivery is not a user concern.

The Verdict

The data points to a straightforward conclusion: the NVIDIA GeForce GTX 650 is the faster GPU in direct compute workloads, winning the only head-to-head benchmark with a 13% margin. Its advantages in shading units, TMUs, ROPs, memory bandwidth, and FP32 throughput are consistent across every specification category. The GTX 650’s FP32 output of 812.5 GFLOPS versus 544.0 GFLOPS on the R5 M420, combined with 80.00 GB/s versus 16.00 GB/s of memory bandwidth, makes it the clear choice for anyone prioritizing raw performance.

However, the R5 M420 is not without its own merits. Its 4 GB memory capacity doubles the GTX 650’s 1024 MB, which could be relevant for workloads that favor capacity over bandwidth. The AMD part also carries a newer DirectX feature level (11_1 versus 11_0) and a lower transistor count that suggests greater power efficiency per unit of silicon, though no TDP is listed to confirm this. Its IGP classification means it requires no additional power connectors and can slot into systems where discrete cards are not an option.

For users building or upgrading a desktop system with a standard PCIe slot, the GTX 650 is the data-backed pick. Its higher benchmark score, superior texture and pixel rates, and 128-bit GDDR5 memory interface make it the more capable graphics solution. The R5 M420 appeals to a narrower use case: portable or integrated systems where its 4 GB DDR3 memory and lower resource footprint may be acceptable trade-offs for the convenience of an IGP. The percentile rankings — 23rd for the AMD part and 22nd for the NVIDIA part — indicate that neither card is a high-performer by modern standards, but within this specific pairing, the GTX 650 consistently delivers more performance where it counts.

Specification Differences

The table below highlights only the fields where the two GPUs differ, based on the available data.

| Specification | AMD Radeon R5 M420 | NVIDIA GeForce GTX 650 |

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

| Architecture | GCN 1.0 | Kepler |

| Generation | Gem System (R5 M400) | GeForce 600 |

| Chip | Jet | GK106 |

| Transistors | 690 million | 2,540 million |

| Die Size | 56 mm² | 221 mm² |

| Transistor Density | 12.3M / mm² | 11.5M / mm² |

| Memory Clock | 2 Gbps effective | 5 Gbps effective |

| Memory Size | 4 GB | 1024 MB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 64 bit | 128 bit |

| Memory Bandwidth | 16.00 GB/s | 80.00 GB/s |

| Shading Units | 320 | 384 |

| TMUs | 20 | 32 |

| ROPs | 8 | 16 |

| Pixel Rate | 6.800 GPixel/s | 8.464 GPixel/s |

| Texture Rate | 17.00 GTexel/s | 33.86 GTexel/s |

| FP32 Performance | 544.0 GFLOPS | 812.5 GFLOPS |

| TDP | Not listed | 65 W |

| Slot Width | IGP | Single-slot |

| Power Connectors | None | 1x 6-pin |

| Suggested PSU | Not listed | 250 W |

| Bus Interface | PCIe 3.0 x8 | PCIe 3.0 x16 |

| Display Outputs | Portable Device Dependent | 1x DVI, 2x DisplayPort 1.2 |

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

| Vulkan Support | 1.2.170 | 1.2.175 |

| Dimensions | Not listed | 147 mm (5.8 inches) |

| Release Date | 2016-05-14 | 2013-11-26 |

| Predecessor | Solar System | GeForce 500 |

| Successor | Polaris Mobile | GeForce 700 |

| Geekbench OpenCL Score | 3956 | 4545 |

| Average Benchmark Score | 3956 | 3823 |

| Percentile vs All GPUs | 23 | 22 |