AMD Radeon R9 M275X vs NVIDIA GeForce GTX 960 Comparison

Head-to-Head Benchmarks

The recorded data shows a clear split between the two contenders, with each taking one benchmark victory in their shared tests. In the Geekbench OpenCL workload, the NVIDIA GeForce GTX 960 delivers a commanding performance, scoring 18,925 against the AMD Radeon R9 M275X's 11,200. That represents a 40.8% advantage for the NVIDIA part, a substantial margin that underscores its raw compute throughput in this specific API test. The AMD card simply cannot match that level of OpenCL output, and the delta is among the largest seen in this comparison.

However, the story flips entirely in the Geekbench Vulkan test. Here, the AMD Radeon R9 M275X takes the win with a score of 9,964, edging past the GeForce GTX 960's 9,231. The margin is 7.9%, a modest but meaningful lead. This suggests that while the NVIDIA card has superior raw compute in certain legacy APIs, the AMD architecture holds its own, and even surpasses its rival, in a modern, low-level graphics API like Vulkan. The database records one win for each card in these head-to-head tests, making the overall comparison a tie on paper.

Looking at the broader benchmark averages, the AMD Radeon R9 M275X posts an average score of 10,582 across all recorded tests, placing it at the 49th percentile of all GPUs. The NVIDIA GeForce GTX 960, despite its massive OpenCL win, averages 9,273, which puts it at the 45th percentile. This is a curious inversion: the NVIDIA card wins the single most lopsided test, but its average is dragged down by the Vulkan result and its Metal score of 8,773. The AMD card's consistent showing in both OpenCL and Vulkan gives it a higher overall average, despite losing the OpenCL test by a wide margin.

The nearest rival data further contextualizes these numbers. The AMD Radeon R9 M275X sits within a tight cluster of comparable GPUs: it trails the AMD Radeon RX 6600S by just 0.4%, leads the AMD Radeon RX 550X by 1%, trails the NVIDIA GeForce GTX 560 Ti by 1%, and trails the NVIDIA Quadro K2200 by 1.7%. These are all single-digit percentage differences, indicating that the R9 M275X is positioned in a very competitive performance band. The NVIDIA GeForce GTX 960, in contrast, is clustered with the NVIDIA GeForce GTX 465 (0.2% behind), the NVIDIA GeForce GTX 850M (0.3% behind), the AMD Radeon R7 M380 (0.4% behind), and leads the AMD Radeon Vega 8 by 0.6%. The GTX 960's average score is thus surrounded by very different hardware, including mobile parts and older desktop cards, all landing within a narrow range.

Where Each One Wins

The use-case split is defined by the API and workload type. The NVIDIA GeForce GTX 960 is the clear winner in OpenCL compute tasks. Its 40.8% lead over the AMD card in that test is decisive, and this is the kind of workload that benefits from the NVIDIA card's higher shader count and texture throughput. If the task at hand leverages OpenCL, the GTX 960 is the obvious choice based on the recorded data.

The AMD Radeon R9 M275X wins in Vulkan workloads. Its 7.9% advantage in the Geekbench Vulkan test indicates that the GCN 1.0 architecture, despite being older, handles this API more efficiently than the Maxwell 2.0 design in the GTX 960. Vulkan is a low-overhead API that relies on the driver and hardware scheduling, and the AMD part appears to have an edge here. For gaming or compute applications that use Vulkan, the R9 M275X is the better performer.

The average benchmark score also favors the AMD card. With an average of 10,582 versus 9,273, the R9 M275X is 14.1% ahead in overall recorded performance across all tests. This suggests that, on a day-to-day basis, the AMD card delivers a more balanced performance profile. It does not have the extreme peaks of the GTX 960, but it also does not have the valleys. The NVIDIA card's average is pulled down by its Vulkan result and its Metal score of 8,773, which is notably lower than its OpenCL score. For users who run a mix of workloads, the AMD card's consistency is a strength.

Architecture Differences

The two GPUs are built on fundamentally different architectures, though they share the same manufacturing process. The AMD Radeon R9 M275X uses the Venus chip, based on the GCN 1.0 architecture, and belongs to the Gem System (R9 M200) generation. The NVIDIA GeForce GTX 960 uses the GM206 chip, based on Maxwell 2.0, and belongs to the GeForce 900 generation. Both are fabricated by TSMC on a 28 nm process, but the similarity ends there.

The transistor counts differ substantially. The AMD chip packs 1,500 million transistors on a die size of 123 mm², yielding a transistor density of 12.2 million per mm². The NVIDIA chip has 2,940 million transistors on a 228 mm² die, for a density of 12.9 million per mm². The GTX 960 has nearly double the transistor count, which explains its higher raw compute capabilities in certain tests.

The shader and texture resources also favor the NVIDIA card. The GTX 960 has 1,024 shading units, 64 texture mapping units, and 32 ROPs. The R9 M275X has 640 shading units, 40 TMUs, and 16 ROPs. This translates directly into higher fill rates: the GTX 960 delivers 37.70 GPixel/s pixel rate and 75.39 GTexel/s texture rate, while the AMD card manages 14.80 GPixel/s and 37.00 GTexel/s. The NVIDIA card is more than double the AMD part in pixel throughput and more than double in texture throughput.

Clock speeds tell a similar story. The GTX 960 runs at a base clock of 1127 MHz and a boost clock of 1178 MHz. The R9 M275X runs at 900 MHz base and 925 MHz boost. The memory clocks also differ: the GTX 960 runs its GDDR5 memory at 1753 MHz (7 Gbps effective), while the R9 M275X runs at 1125 MHz (4.5 Gbps effective). Memory bandwidth follows: the GTX 960 has 112.2 GB/s, the AMD card has 72.00 GB/s. Both use a 128-bit bus and 2 GB of GDDR5.

The API support is another differentiator. The GTX 960 supports DirectX 12 (12_1) and Vulkan 1.4, while the R9 M275X supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6. The higher DirectX feature level and newer Vulkan version on the NVIDIA card could explain its strong OpenCL showing, though the AMD card's Vulkan performance suggests its driver implementation is effective despite the older API version.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M275X, with an average score of 10,582, compared to the NVIDIA GeForce GTX 960's 9,273.

Q: How much faster is the NVIDIA GeForce GTX 960 in OpenCL?

A: The GTX 960 scores 18,925 in Geekbench OpenCL, which is 40.8% higher than the R9 M275X's 11,200.

Q: Does the AMD Radeon R9 M275X win any benchmark?

A: Yes, it wins the Geekbench Vulkan test, scoring 9,964 against the GTX 960's 9,231, a 7.9% lead.

Q: What is the memory bandwidth difference?

A: The NVIDIA GeForce GTX 960 has 112.2 GB/s, while the AMD Radeon R9 M275X has 72.00 GB/s.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce GTX 960 has 1,024 shading units, while the AMD Radeon R9 M275X has 640.

Q: What is the transistor count for each chip?

A: The NVIDIA GM206 chip has 2,940 million transistors, and the AMD Venus chip has 1,500 million.

Specification Differences

| Specification | AMD Radeon R9 M275X | NVIDIA GeForce GTX 960 |

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

| Chip | Venus | GM206 |

| Architecture | GCN 1.0 | Maxwell 2.0 |

| Generation | Gem System (R9 M200) | GeForce 900 |

| Transistors | 1,500 million | 2,940 million |

| Die Size | 123 mm² | 228 mm² |

| Transistor Density | 12.2M / mm² | 12.9M / mm² |

| Base Clock | 900 MHz | 1127 MHz |

| Boost Clock | 925 MHz | 1178 MHz |

| Memory Clock | 1125 MHz (4.5 Gbps effective) | 1753 MHz (7 Gbps effective) |

| Memory Bandwidth | 72.00 GB/s | 112.2 GB/s |

| Shading Units | 640 | 1024 |

| TMUs | 40 | 64 |

| ROPs | 16 | 32 |

| Pixel Rate | 14.80 GPixel/s | 37.70 GPixel/s |

| Texture Rate | 37.00 GTexel/s | 75.39 GTexel/s |

| FP32 | 1,184.0 GFLOPS | 2.413 TFLOPS |

| TDP | Not recorded | 120 W |

| Slot Width | Not recorded | Dual-slot |

| Power Connectors | Not recorded | 1x 6-pin |

| Suggested PSU | Not recorded | 300 W |

| Display Outputs | Not recorded | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 |

| DirectX | 12 (11_1) | 12 (12_1) |

| Vulkan | 1.2.170 | 1.4 |

| Length | Not recorded | 241 mm (9.5 inches) |

| Release Date | 2014-01-27 | 2015-01-21 |

| Predecessor | Solar System | GeForce 700 |

| Successor | Polaris Mobile | GeForce 10 |

| Launch MSRP | None recorded | 199 USD |

The Verdict

The data paints a nuanced picture. The NVIDIA GeForce GTX 960 is the superior raw compute performer in OpenCL, with a 40.8% lead over the AMD Radeon R9 M275X. It also has substantially higher pixel and texture rates, more shading units, and nearly double the memory bandwidth. For any workload that is heavily dependent on OpenCL or traditional fill-rate-bound rendering, the GTX 960 is the clear choice.

However, the AMD Radeon R9 M275X holds a 7.9% advantage in Vulkan, and its overall average benchmark score is 14.1% higher than the GTX 960's. This indicates that for modern Vulkan-based applications, the AMD card is not just competitive but actually faster. The GTX 960's average is dragged down by its Vulkan and Metal scores, suggesting that its architecture does not scale as well to these newer APIs.

The choice depends on the target workload. If the priority is OpenCL compute or maximum fill rates, the GeForce GTX 960 is the stronger option. If the priority is Vulkan performance or a balanced overall score across multiple APIs, the Radeon R9 M275X is the better pick. The data does not declare a single winner; it declares a workload-dependent split. The GTX 960 has the higher peak, the R9 M275X has the higher average. Users should align their choice with the specific applications they intend to run.