AMD Radeon R9 M375X vs NVIDIA GeForce GTX 960 Comparison

The Verdict

The data positions the NVIDIA GeForce GTX 960 as the clear performance leader between these two mobile and desktop offerings. The GTX 960 wins both recorded head-to-head benchmarks, with a 128.8% advantage in Geekbench OpenCL and a 10.2% lead in Geekbench Vulkan. Its average benchmark score of 9273 places it in the 45th percentile of all GPUs, while the AMD Radeon R9 M375X averages 8325, sitting at the 43rd percentile.

For users choosing strictly on recorded performance, the GTX 960 is the obvious pick. It delivers roughly double the OpenCL compute throughput of the R9 M375X, which matters for general-purpose workloads and any application leveraging GPU compute. The Vulkan gap is narrower but still decisive, indicating that even in modern API scenarios, the GTX 960 holds a measurable edge.

The R9 M375X, however, is not without context. Its nearest rivals include the NVIDIA Quadro K1200 (0.7% ahead), the GeForce GTX 675MX (1.2% behind), the AMD Radeon 880M (1.3% behind), and the GeForce MX330 (1.6% behind). This clustering suggests the R9 M375X occupies a specific performance tier appropriate for lighter workloads or systems where power and thermal constraints favor a smaller die. The GTX 960, by contrast, sits among rivals like the GTX 465 (0.2% behind), GTX 850M (0.3% behind), R7 M380 (0.4% behind), and Vega 8 (0.6% ahead), all within a narrow band that defines its mid-range standing.

The verdict is straightforward: the GTX 960 is the superior performer in every measured category. The R9 M375X is a viable option only when the specific trade-offs of a smaller, lower-power mobile chip outweigh raw benchmark scores. The data does not support choosing the R9 M375X for performance-critical tasks.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The NVIDIA GeForce GTX 960 uses the GM206 chip built on the Maxwell 2.0 architecture, part of the GeForce 900 generation. It is fabricated on a 28 nm process at TSMC, with 2,940 million transistors on a 228 mm² die, yielding a transistor density of 12.9 million per square millimeter.

The AMD Radeon R9 M375X uses the Tropo chip based on GCN 1.0 architecture, belonging to the Gem System (R9 M300) generation. It also uses a 28 nm TSMC process but packs only 1,500 million transistors on a 123 mm² die, resulting in a slightly lower density of 12.2 million per square millimeter. The smaller die and lower transistor count reflect a more modest design intended for mobile integration.

Core configuration differs substantially. The GTX 960 has 1024 shading units, 64 texture mapping units, and 32 render output units. The R9 M375X has 640 shading units, 40 TMUs, and only 16 ROPs. These differences directly explain the pixel rate gap: 37.70 GPixel/s for the GTX 960 versus 16.24 GPixel/s for the R9 M375X. Texture rate follows the same pattern, with the GTX 960 at 75.39 GTexel/s and the R9 M375X at 40.60 GTexel/s. Floating-point performance is equally lopsided: 2.413 TFLOPS versus 1,299.2 GFLOPS.

Clock speeds also favor the GTX 960. It runs at a base of 1127 MHz with a boost of 1178 MHz, while the R9 M375X operates at 925 MHz base and 1015 MHz boost. Memory configurations are similar in size and type, both using 2 GB of GDDR5 on a 128-bit bus, but the GTX 960's memory runs at 1753 MHz (7 Gbps effective) delivering 112.2 GB/s of bandwidth, versus 1125 MHz (4.5 Gbps effective) and 72.00 GB/s for the AMD part.

API support differs meaningfully. The GTX 960 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R9 M375X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The higher DirectX feature level and newer Vulkan version on the NVIDIA side could matter for compatibility with newer titles.

The GTX 960 is a dual-slot desktop card with a 120 W TDP, a single 6-pin power connector, a 300 W suggested PSU, and PCIe 3.0 x16 interface. It measures 241 mm (9.5 inches) in length and offers display outputs of 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The R9 M375X has no recorded TDP, slot width, power connector, or dimension data, indicating it is primarily a mobile GPU. Both products are end-of-life, with the GTX 960 released on January 21, 2015, and the R9 M375X on May 4, 2015.

Head-to-Head Benchmarks

The head-to-head data contains two benchmark comparisons, and the NVIDIA GeForce GTX 960 wins both. The most dramatic result is in Geekbench OpenCL, where the GTX 960 scores 18925 against the R9 M375X's 8273. That is a delta of 128.8%, meaning the NVIDIA part delivers more than double the OpenCL compute performance. This aligns with the raw specification differences: the GTX 960 has 1024 shading units versus 640, a higher boost clock of 1178 MHz versus 1015 MHz, and nearly double the memory bandwidth at 112.2 GB/s versus 72.00 GB/s.

The second benchmark, Geekbench Vulkan, shows a narrower margin. The GTX 960 scores 9231, while the R9 M375X reaches 8377, a 10.2% difference. This smaller gap suggests that Vulkan workloads may be less sensitive to raw shading unit count or memory bandwidth, or that the R9 M375X's GCN architecture handles certain Vulkan operations more efficiently relative to its specifications. Still, the GTX 960 comes out ahead.

The wins tally is 2 for the GTX 960 and 0 for the R9 M375X. No benchmark in the database shows the AMD part winning. For context, the GTX 960's average benchmark score of 9273 is 11.4% higher than the R9 M375X's 8325. This overall average is pulled up by the GTX 960's additional benchmark results: it also records a 3DMark Steel Nomad DX12 score of 162 and a Geekbench Metal score of 8773, neither of which has a corresponding R9 M375X result.

The percentile ranks reinforce the gap. The GTX 960 sits at the 45th percentile of all GPUs, while the R9 M375X is at the 43rd. While both are mid-pack, the GTX 960 edges out a meaningful portion of the field that the R9 M375X does not reach.

FAQ

Q: Which GPU is faster in OpenCL compute workloads?

A: The NVIDIA GeForce GTX 960 is decisively faster. It scores 18925 in Geekbench OpenCL versus 8273 for the AMD Radeon R9 M375X, a 128.8% advantage.

Q: How do the two compare in Vulkan performance?

A: The GTX 960 leads again, scoring 9231 in Geekbench Vulkan against 8377 for the R9 M375X, a 10.2% difference. The margin is much smaller than in OpenCL, but the NVIDIA card still wins.

Q: What are the key architectural differences?

A: The GTX 960 uses Maxwell 2.0 architecture with 1024 shading units, 64 TMUs, and 32 ROPs on a 228 mm² die with 2,940 million transistors. The R9 M375X uses GCN 1.0 with 640 shading units, 40 TMUs, and 16 ROPs on a 123 mm² die with 1,500 million transistors. Both use a 28 nm TSMC process.

Q: Do both GPUs support the same DirectX and Vulkan versions?

A: No. The GTX 960 supports DirectX 12 (12_1) and Vulkan 1.4. The R9 M375X supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6.

Q: How does memory bandwidth differ?

A: Both have 2 GB of GDDR5 on a 128-bit bus, but the GTX 960 runs memory at 1753 MHz (7 Gbps effective) for 112.2 GB/s, while the R9 M375X runs at 1125 MHz (4.5 Gbps effective) for 72.00 GB/s.

Q: What is the GTX 960's launch MSRP?

A: The GTX 960 had a launch MSRP of 199 USD. The R9 M375X has no recorded launch MSRP in the database.

Where Each One Wins

The NVIDIA GeForce GTX 960 wins in every recorded benchmark category, but the magnitude of its wins varies significantly by workload type. The largest advantage comes in OpenCL compute, where its 128.8% lead indicates a fundamental throughput advantage driven by more shading units, higher clocks, and nearly double the memory bandwidth. This makes the GTX 960 the clear choice for any application that offloads parallel computation to the GPU, such as video encoding, physics simulations, or data processing that uses OpenCL.

In Vulkan rendering, the GTX 960 still wins but by a much smaller margin of 10.2%. This suggests that for modern game engines or graphics applications using Vulkan, the R9 M375X is comparatively more competitive than its raw specifications would imply. The GCN architecture may handle certain draw calls or pipeline stages more efficiently, narrowing the gap. Still, the GTX 960 holds the advantage.

The R9 M375X has no benchmark wins in the database. However, its smaller die size (123 mm² versus 228 mm²) and lower transistor count (1,500 million versus 2,940 million) suggest it may be suited for thermally constrained environments where the GTX 960's 120 W TDP and dual-slot cooling requirements are prohibitive. The R9 M375X has no recorded TDP or slot width, which aligns with its likely mobile deployment.

For users prioritizing raw performance, the choice is unambiguous: the GTX 960. For systems where the GTX 960 cannot physically fit or where power delivery is limited, the R9 M375X remains a functional alternative, especially given its Vulkan score is within 10% of the NVIDIA part. The GTX 960's additional benchmarks (3DMark Steel Nomad DX12 at 162 and Geekbench Metal at 8773) further broaden its utility, covering DX12 and Apple ecosystem workloads that the R9 M375X cannot match. The data does not identify any scenario where the R9 M375X outperforms the GTX 960.