AMD Radeon R9 M375X vs NVIDIA GeForce GTX 960M Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 960M leads with an average benchmark score of 9645, while the AMD Radeon R9 M375X scores 8325. That puts the GTX 960M at the 46th percentile of all GPUs, versus the 43rd percentile for the R9 M375X.

Q: How do the two cards compare in OpenCL performance?

A: The GTX 960M is substantially ahead in Geekbench OpenCL, scoring 11045 against 8273 for the R9 M375X, a 33.5% advantage. This is the largest performance gap between the two in any recorded test.

Q: Does the AMD card win any benchmark?

A: Yes, the Radeon R9 M375X wins the Geekbench Vulkan test, scoring 8377 versus 8245 for the GTX 960M, a 1.6% edge. It is a narrow victory, but it shows the AMD card holds its own in Vulkan workloads.

Q: What are the memory configurations of each GPU?

A: The GTX 960M comes with 4 GB of GDDR5 on a 128-bit bus, delivering 80.19 GB/s of bandwidth. The R9 M375X has 2 GB of GDDR5 on a 128-bit bus, with 72.00 GB/s of bandwidth. The NVIDIA card offers double the capacity and roughly 11% more bandwidth.

Q: Which GPU has higher clock speeds?

A: The GTX 960M runs at a base clock of 1097 MHz and a boost clock of 1176 MHz. The R9 M375X operates at 925 MHz base and 1015 MHz boost. The NVIDIA card has higher clocks at both the base and boost levels.

Q: Are both GPUs still in production?

A: No, both are end-of-life products. The GTX 960M was released in March 2015, and the R9 M375X followed in May 2015.

Architecture Differences

The two mobile GPUs come from different architectural lineages. The NVIDIA GeForce GTX 960M uses the GM107 chip built on the Maxwell architecture, while the AMD Radeon R9 M375X uses the Tropo chip based on GCN 1.0. Both are manufactured by TSMC on a 28 nm process, but the underlying designs diverge significantly.

The transistor counts tell part of the story. The GTX 960M packs 1,870 million transistors on a 148 mm² die, giving a transistor density of 12.6M per mm². The R9 M375X contains 1,500 million transistors on a 123 mm² die, with a density of 12.2M per mm². The NVIDIA chip is both larger and denser, which contributes to its higher compute throughput.

Both GPUs have identical core counts in several respects: 640 shading units, 40 texture mapping units, and 16 raster output units. Despite the same counts, the execution rates differ due to clock speeds and architectural efficiency. The GTX 960M achieves a pixel rate of 18.82 GPixel/s and a texture rate of 47.04 GTexel/s. The R9 M375X delivers 16.24 GPixel/s and 40.60 GTexel/s. The NVIDIA card is roughly 16% faster in both pixel and texture throughput.

Floating-point performance follows the same pattern. The GTX 960M reaches 1.505 TFLOPS of FP32 compute, while the R9 M375X produces 1,299.2 GFLOPS. That is a clear advantage for NVIDIA in raw compute density per clock.

API support also differs. The GTX 960M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The R9 M375X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The AMD card has a slightly higher DirectX feature level, while NVIDIA offers a newer Vulkan version.

The bus interfaces reflect their intended platforms. The GTX 960M uses MXM-B (3.0) and comes as an MXM Module, while the R9 M375X connects via PCIe 3.0 x16. Display outputs on the NVIDIA card are listed as portable device dependent, and the AMD card has no listed display outputs, both being mobile parts.

Power characteristics also differ. The GTX 960M has a TDP of 75 W and requires no power connectors. The R9 M375X has no TDP listed and no power connector data. The NVIDIA card is documented as a fixed 75 W part, which is typical for a mid-range mobile solution.

Head-to-Head Benchmarks

The benchmark data shows a split decision between these two GPUs. The GTX 960M dominates in OpenCL, while the R9 M375X edges out a win in Vulkan. The overall average favors NVIDIA by a wide margin.

In Geekbench OpenCL, the GTX 960M scores 11045 against 8273 for the R9 M375X. That is a 33.5% difference, the largest gap in any comparison between the two. This result aligns with the compute specifications: the NVIDIA card has higher clocks, higher pixel and texture rates, and more FP32 throughput. The 4 GB memory buffer also gives it more headroom for large workloads compared to the 2 GB on the AMD card.

In Geekbench Vulkan, the tables turn slightly. The R9 M375X scores 8377, while the GTX 960M scores 8245. The AMD card wins by 1.6%, a modest margin but a real one. Vulkan performance does not track raw OpenCL compute linearly, and the GCN architecture handles this workload well enough to overcome the clock and bandwidth disadvantages.

The average benchmark scores reflect the overall balance. The GTX 960M averages 9645 across its recorded tests, placing it among rivals like the NVIDIA Quadro K5000 (9637, 0.1% lower), the AMD Radeon Pro WX 2100 (9653, 0.1% higher), and the NVIDIA Quadro P4000 (9665, 0.2% higher). It sits just below the NVIDIA Tesla C2070 (9716, 0.7% higher). The R9 M375X averages 8325, near the NVIDIA Quadro K1200 (8265, 0.7% lower), the NVIDIA GeForce GTX 675MX (8427, 1.2% higher), the AMD Radeon 880M (8436, 1.3% higher), and the NVIDIA GeForce MX330 (8458, 1.6% higher).

The percentile ranks summarize the competitive positioning. The GTX 960M sits at the 46th percentile of all GPUs, while the R9 M375X sits at the 43rd. The three-point gap is small but consistent with the 13.7% difference in average scores.

Specification Differences

The two GPUs differ across nearly every major specification category.

The process node is the same (28 nm, TSMC), but the chips themselves are distinct: GM107 for NVIDIA versus Tropo for AMD. The GTX 960M has 1,870 million transistors on a 148 mm² die; the R9 M375X has 1,500 million on 123 mm². Transistor density is similar at 12.6M/mm² versus 12.2M/mm².

Clock speeds favor NVIDIA. The GTX 960M runs at 1097 MHz base and 1176 MHz boost. The R9 M375X runs at 925 MHz base and 1015 MHz boost. Memory clocks also differ: 1253 MHz (5 Gbps effective) for the GTX 960M versus 1125 MHz (4.5 Gbps effective) for the R9 M375X.

Memory capacity is a major differentiator. The GTX 960M has 4 GB of GDDR5, while the R9 M375X has 2 GB. Both use a 128-bit bus, but bandwidth differs: 80.19 GB/s for NVIDIA versus 72.00 GB/s for AMD.

Shader, TMU, and ROP counts are identical at 640, 40, and 16 respectively. However, the resulting throughput rates favor NVIDIA. Pixel rate is 18.82 GPixel/s versus 16.24 GPixel/s, and texture rate is 47.04 GTexel/s versus 40.60 GTexel/s. FP32 compute is 1.505 TFLOPS versus 1,299.2 GFLOPS.

API support shows minor differences. Both support OpenGL 4.6. The GTX 960M supports DirectX 12 (11_0) and Vulkan 1.4; the R9 M375X supports DirectX 12 (11_1) and Vulkan 1.2.170.

Form factor and interface differ. The GTX 960M is an MXM Module with MXM-B (3.0) interface. The R9 M375X uses PCIe 3.0 x16. The NVIDIA card lists a 75 W TDP and no power connectors; the AMD card has no TDP, power connector, or slot width data.

Release timing is close: the GTX 960M launched in March 2015, and the R9 M375X in May 2015. Both are end-of-life. The NVIDIA card's predecessor is GeForce 800M and its successor is GeForce 10 Mobile. The AMD card's predecessor is Solar System and its successor is Polaris Mobile.

The Verdict

The data points clearly toward the NVIDIA GeForce GTX 960M as the stronger overall GPU. Its average benchmark score of 9645 is 13.7% higher than the R9 M375X's 8325, and it holds a 46th percentile rank versus 43rd. The OpenCL result is decisive: 11045 versus 8273, a 33.5% lead that dwarfs the AMD card's 1.6% Vulkan advantage.

For users prioritizing compute-heavy tasks, OpenCL workloads, or applications that benefit from larger memory buffers, the GTX 960M is the logical choice. It doubles the VRAM (4 GB versus 2 GB), offers higher bandwidth (80.19 GB/s versus 72.00 GB/s), and delivers superior pixel, texture, and FP32 rates. Its higher clock speeds across base, boost, and memory reinforce the performance gap.

The R9 M375X is not without merit. It wins the Vulkan benchmark and supports a slightly higher DirectX feature level (12 (11_1) versus 12 (11_0)). Its smaller die (123 mm² versus 148 mm²) and lower transistor count (1,500 million versus 1,870 million) may appeal in power-constrained designs, though no TDP is listed for the AMD part. For Vulkan-specific workloads, the R9 M375X is competitive, but the margin is thin.

The overall recommendation from the recorded data is straightforward: the GTX 960M is the better all-around mobile GPU. The R9 M375X only makes sense when Vulkan performance is the primary criterion or when the slightly higher DirectX feature level matters. Otherwise, the NVIDIA card wins on compute, memory, and average performance.

Where Each One Wins

The GTX 960M wins in OpenCL compute performance by a significant margin. Its 33.5% lead in Geekbench OpenCL makes it the clear choice for applications that leverage OpenCL acceleration, such as video encoding, image processing, and general-purpose GPU compute. The 4 GB memory buffer provides additional capacity for larger datasets, and the higher bandwidth (80.19 GB/s versus 72.00 GB/s) supports faster data movement.

The GTX 960M also wins on raw throughput metrics. It has higher pixel rate (18.82 GPixel/s versus 16.24 GPixel/s), higher texture rate (47.04 GTexel/s versus 40.60 GTexel/s), and higher FP32 compute (1.505 TFLOPS versus 1,299.2 GFLOPS). These advantages apply across most rendering and compute workloads.

The R9 M375X wins in the Vulkan benchmark, scoring 8377 versus 8245, a 1.6% edge. This suggests the AMD card has a slight advantage in Vulkan-based games and applications, despite its lower raw specs. The GCN architecture appears to handle Vulkan workloads efficiently relative to its clock and bandwidth limitations.

The R9 M375X also offers a marginally higher DirectX feature level (12 (11_1) versus 12 (11_0)). For software that specifically utilizes this feature level, the AMD card may have a compatibility or feature advantage, though the practical impact is limited given the small version difference.

In terms of overall average score, the GTX 960M wins decisively at 9645 versus 8325. The NVIDIA card also sits closer to a tighter cluster of rivals, with its nearest competitors within 0.7% of its score. The R9 M375X faces rivals up to 1.6% higher, indicating it sits slightly lower in the competitive hierarchy.

The use-case split is therefore clear. Choose the GTX 960M for general performance, OpenCL workloads, and memory-intensive tasks. Choose the R9 M375X for Vulkan-specific applications or when the DirectX feature level difference matters. For everything else, the NVIDIA card is the stronger pick.