AMD Radeon RX 580 vs NVIDIA GeForce GTX 965M Comparison

FAQ

Q: How does the NVIDIA GeForce GTX 965M compare to the AMD Radeon RX 580 in synthetic benchmarks?

A: The database shows the GTX 965M scores 14,509 in Geekbench OpenCL and 14,299 in Geekbench Vulkan. The RX 580 scores 37,453 in OpenCL and 45,173 in Vulkan. The RX 580 wins both recorded head-to-head tests, with deltas of 61.3% and 68.3% respectively.

Q: Which GPU has the higher average benchmark score?

A: The GTX 965M has an average benchmark score of 14,404, while the RX 580 has 12,928. Despite losing the head-to-head matchups, the GTX 965M holds a higher average score because it has fewer recorded tests, while the RX 580 includes lower DirectX and compute results that pull its average down.

Q: What are the architectural differences between these two GPUs?

A: The GTX 965M uses NVIDIA's Maxwell 2.0 architecture on a 28 nm process at TSMC, with 5,200 million transistors on a 398 mm² die. The RX 580 uses AMD's GCN 4.0 on a 14 nm process at GlobalFoundries, with 5,700 million transistors on a 232 mm² die. The RX 580 has a much higher transistor density at 24.6M per mm² versus 13.1M per mm².

Q: How do the memory subsystems differ?

A: The GTX 965M has 2 GB of GDDR5 on a 128-bit bus with 80.19 GB/s bandwidth. The RX 580 has 8 GB of GDDR5 on a 256-bit bus with 256.0 GB/s bandwidth. The RX 580 offers four times the capacity and over three times the bandwidth.

Q: What is the production status and release timeline for each?

A: Both are end-of-life products. The GTX 965M was released on January 8, 2015, and the RX 580 on April 17, 2017. The GTX 965M's predecessor is GeForce 800M and its successor is GeForce 10 Mobile. The RX 580's predecessor is Arctic Islands and its successor is Vega.

Q: How do their API support levels compare?

A: The GTX 965M supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RX 580 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The GTX 965M has a higher DirectX feature level and a newer Vulkan version.

Architecture Differences

The GTX 965M is built on NVIDIA's Maxwell 2.0 architecture using the GM204 chip, fabricated by TSMC on a 28 nm process. The die measures 398 mm² and contains 5,200 million transistors, yielding a transistor density of 13.1M per mm². This is a mobile-oriented GPU presented as an MXM Module with no power connectors and portable-device-dependent display outputs.

The RX 580 uses AMD's GCN 4.0 architecture with the Polaris 20 chip, fabricated by GlobalFoundries on a 14 nm process. The die is significantly smaller at 232 mm² but packs more transistors at 5,700 million, giving a density of 24.6M per mm². This is a desktop dual-slot card with a 1x 8-pin power connector and a 450 W suggested power supply.

The compute resource allocation differs substantially. The GTX 965M has 1,024 shading units, 64 texture mapping units, and 32 ROPs. The RX 580 has 2,304 shading units, 144 TMUs, and 32 ROPs. This means the RX 580 has more than double the shading units and more than double the texture units, though both have identical ROP counts.

Clock speeds favor the RX 580. The GTX 965M runs at a base of 924 MHz and boost of 950 MHz, while the RX 580 runs at 1,257 MHz base and 1,340 MHz boost. Memory clocks also differ: the GTX 965M uses 1,253 MHz (5 Gbps effective), while the RX 580 uses 2,000 MHz (8 Gbps effective).

The memory architecture is a major differentiator. The GTX 965M has 2 GB GDDR5 on a 128-bit bus, providing 80.19 GB/s bandwidth. The RX 580 has 8 GB GDDR5 on a 256-bit bus, providing 256.0 GB/s. This quadruples capacity and more than triples bandwidth.

Pixel and texture rates reflect the hardware differences. The GTX 965M achieves 30.40 GPixel/s and 60.80 GTexel/s, while the RX 580 achieves 42.88 GPixel/s and 193.0 GTexel/s. The FP32 compute is 1.946 TFLOPS for the GTX 965M versus 6.175 TFLOPS for the RX 580, a ratio of roughly 3.2 to 1. The RX 580 also lists FP16 at 6.175 TFLOPS (1:1), while the GTX 965M has no recorded FP16 value.

The GTX 965M uses an MXM-B (3.0) bus interface, whereas the RX 580 uses PCIe 3.0 x16. Display outputs on the RX 580 include 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the GTX 965M's outputs are portable-device dependent. The RX 580 has a TDP of 185 W, while the GTX 965M has no TDP recorded.

Head-to-Head Benchmarks

The database records two direct head-to-head benchmark comparisons between these GPUs. Both are clear wins for the AMD Radeon RX 580.

In Geekbench OpenCL, the GTX 965M scores 14,509, while the RX 580 scores 37,453. The RX 580 wins this test by a delta of 61.3%. This is a substantial margin, indicating the RX 580 delivers massively higher raw compute throughput in OpenCL workloads. The RX 580's advantage in shading units and clock speed is directly reflected in this result.

In Geekbench Vulkan, the gap widens further. The GTX 965M scores 14,299, while the RX 580 scores 45,173. The RX 580 wins by a delta of 68.3%. Vulkan performance favors the RX 580 even more strongly than OpenCL, suggesting that the GCN 4.0 architecture scales particularly well with this API, or that the memory bandwidth advantage becomes more pronounced in Vulkan workloads.

The recorded data shows the GTX 965M loses both head-to-head tests, with zero wins and two wins for the RX 580. The deltas of 61.3% and 68.3% are both in the same direction, meaning there is no benchmark category in which the GTX 965M comes out ahead.

However, the average benchmark score picture is more nuanced. The GTX 965M's average across its two recorded tests is 14,404, which places it at the 56th percentile among all GPUs. The RX 580's average across its eleven recorded tests is 12,928, placing it at the 53rd percentile. This discrepancy arises because the RX 580's benchmark suite includes several DirectX tests with low scores, such as Passmark DirectX 9 at 124, DirectX 10 at 46, DirectX 11 at 60, and DirectX 12 at 43, plus a G2D score of 769. These lower scores drag down the RX 580's average, even though its high-end scores in OpenCL, Vulkan, and Metal are far above anything the GTX 965M records.

The RX 580 also has a Geekbench Metal score of 45,235 and a Passmark G3D score of 8,813, both of which are strong results that the GTX 965M cannot match, as it has no comparable recorded tests.

The Verdict

The head-to-head data is unambiguous: the AMD Radeon RX 580 dominates the NVIDIA GeForce GTX 965M in the two benchmark tests where both are recorded. The RX 580 leads by 61.3% in OpenCL and 68.3% in Vulkan. These are not marginal differences; they represent a generational and architectural gap.

The GTX 965M's higher average benchmark score of 14,404 versus 12,928 is misleading. It reflects the limited test set for the GTX 965M (only two tests) against a much broader suite for the RX 580. The RX 580's average is pulled down by legacy DirectX tests that are not representative of modern workloads. In the tests that matter for compute and modern graphics APIs, the RX 580 is decisively faster.

For users choosing between these two, the RX 580 is the clear pick for anyone who needs raw performance, higher memory capacity, or broader API support in terms of benchmark coverage. The RX 580's 8 GB memory and 256-bit bus provide substantial headroom for modern game textures and compute workloads that would exhaust the GTX 965M's 2 GB capacity.

The GTX 965M may still be relevant in specific mobile contexts where its MXM form factor and lower power requirements (no TDP recorded, no power connectors) are advantages. Its higher Vulkan version (1.4 versus 1.3) and DirectX feature level (12_1 versus 12_0) offer slight API compliance advantages. But in pure performance terms, the data shows no contest.

The GTX 965M sits at the 56th percentile versus the RX 580's 53rd percentile among all GPUs, but this ranking is an artifact of the test suite composition. The RX 580's nearest rivals include the NVIDIA GeForce RTX 3050 Ti Mobile (average score 12,940, delta of 0.1% against the RX 580) and the NVIDIA GeForce GTX 1660 SUPER (12,986, delta of 0.4%). The GTX 965M's nearest rivals include the AMD Radeon RX Vega 11 (14,385, delta of 0.1%) and the NVIDIA GeForce GTX TITAN (14,373, delta of 0.2%). These comparisons confirm that the RX 580 competes with a higher performance tier despite its lower average score.

The verdict from the recorded data: the RX 580 is the stronger GPU for compute and modern graphics workloads. The GTX 965M should only be considered where its mobile form factor and lower power footprint are essential requirements.

Specification Differences

| Field | NVIDIA GeForce GTX 965M | AMD Radeon RX 580 |

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

| Manufacturer | NVIDIA | AMD |

| Chip | GM204 | Polaris 20 |

| Architecture | Maxwell 2.0 | GCN 4.0 |

| Generation | GeForce 900M | Polaris (RX 500) |

| Process Node | 28 nm | 14 nm |

| Foundry | TSMC | GlobalFoundries |

| Transistors | 5,200 million | 5,700 million |

| Die Size | 398 mm² | 232 mm² |

| Transistor Density | 13.1M / mm² | 24.6M / mm² |

| Base Clock | 924 MHz | 1257 MHz |

| Boost Clock | 950 MHz | 1340 MHz |

| Memory Clock | 1253 MHz (5 Gbps effective) | 2000 MHz (8 Gbps effective) |

| Memory Size | 2 GB | 8 GB |

| Memory Type | GDDR5 | GDDR5 |

| Memory Bus Width | 128 bit | 256 bit |

| Memory Bandwidth | 80.19 GB/s | 256.0 GB/s |

| Shading Units | 1024 | 2304 |

| TMUs | 64 | 144 |

| ROPs | 32 | 32 |

| Pixel Rate | 30.40 GPixel/s | 42.88 GPixel/s |

| Texture Rate | 60.80 GTexel/s | 193.0 GTexel/s |

| FP32 | 1.946 TFLOPS | 6.175 TFLOPS |

| FP16 | null | 6.175 TFLOPS (1:1) |

| TDP | null | 185 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 1x 8-pin |

| Suggested PSU | null | 450 W |

| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.0b, 3x DisplayPort 1.4a |

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

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.3 |

| Length | null | 241 mm (9.5 inches) |

| Release Date | 2015-01-08 | 2017-04-17 |

| Predecessor | GeForce 800M | Arctic Islands |

| Successor | GeForce 10 Mobile | Vega |

| Launch MSRP | null | 229 USD |