AMD Radeon R9 M375 vs NVIDIA GeForce GTX 960M Comparison

The AMD Radeon R9 M375 and NVIDIA GeForce GTX 960M are two end-of-life mobile GPUs from 2015, targeting different priorities within the same generation of laptops. The data shows a split decision: the GTX 960M leads in OpenCL compute workloads, while the R9 M375 takes a decisive victory in Vulkan performance. Their average benchmark scores are close — 10070 for the AMD part against 9645 for the NVIDIA — but the underlying architectures and memory configurations tell a more nuanced story for buyers choosing between used or legacy systems.

Head-to-Head Benchmarks

The two GPUs split their two benchmark tests exactly, with each claiming one win. In the Geekbench OpenCL test, the NVIDIA GeForce GTX 960M scores 11045 against the AMD Radeon R9 M375’s 10457, a margin of 5.3%. This is not a trivial gap; it reflects the GTX 960M’s higher clock speeds and faster memory subsystem in compute-heavy tasks that scale with bandwidth. The AMD part’s 28.80 GB/s of memory bandwidth is a severe bottleneck here, while the GTX 960M’s 80.19 GB/s provides nearly three times the throughput.

The Vulkan test flips the script dramatically. The R9 M375 scores 9682, while the GTX 960M manages only 8245 — a 17.4% advantage for the AMD card. This is a substantial win, suggesting that the GCN 1.0 architecture’s driver overhead and scheduling behavior are better suited to Vulkan’s low-level API, despite the NVIDIA part having faster raw hardware. The delta between the two tests is striking: the GTX 960M loses nearly 25% of its OpenCL score when moving to Vulkan (11045 to 8245), whereas the R9 M375 only drops about 7% (10457 to 9682). This consistency makes the AMD card more predictable across different API workloads.

Looking at the broader context, the R9 M375’s average score of 10070 places it at the 48th percentile of all GPUs, just ahead of its nearest rival, the NVIDIA Quadro K5100M, by 0.3%. The GTX 960M’s 9645 average sits at the 46th percentile, with its closest competitor, the NVIDIA Quadro K5000, trailing by only 0.1% — a statistical tie. The R9 M375 also edges out the AMD Radeon Pro 5300M by 0.6% and the GTX 870M by 1.1%, while the GTX 950A leads it by 2%. For the GTX 960M, the margins to its rivals are razor-thin: it is 0.1% ahead of the Quadro K5000, 0.1% behind the Radeon Pro WX 2100, 0.2% behind the Quadro P4000, and 0.7% behind the Tesla C2070. Neither card dominates its peer group; both sit in a crowded mid-range pack.

FAQ

Q: Which GPU has the higher overall average benchmark score?

A: The AMD Radeon R9 M375 leads with an average benchmark score of 10070, compared to the NVIDIA GeForce GTX 960M’s 9645. That is a 425-point gap, roughly a 4.2% advantage for the AMD part.

Q: How do the two GPUs compare in Vulkan performance?

A: The R9 M375 scores 9682 in Geekbench Vulkan, while the GTX 960M scores 8245. The AMD card is 17.4% faster, which is the largest single-test margin between the two.

Q: What is the memory configuration difference?

A: The GTX 960M has 4 GB of GDDR5 memory on a 128-bit bus, delivering 80.19 GB/s bandwidth. The R9 M375 has 2 GB of DDR3 on the same 128-bit bus, yielding only 28.80 GB/s. The GTX 960M offers double the capacity and nearly three times the bandwidth.

Q: Which GPU has a higher pixel fill rate?

A: The GTX 960M achieves 18.82 GPixel/s, while the R9 M375 manages 16.24 GPixel/s. The NVIDIA part is about 16% faster in this metric, which matters for fill-rate-bound scenarios at high resolutions.

Q: Do both GPUs support DirectX 12?

A: Yes, but with different feature levels. The R9 M375 supports DirectX 12 (11_1), while the GTX 960M supports DirectX 12 (11_0). The AMD card has a slightly higher feature-level support.

Q: What are the transistor counts for each chip?

A: The GTX 960M’s GM107 chip contains 1,870 million transistors on a 148 mm² die. The R9 M375’s Tropo chip has 1,500 million transistors on a 123 mm² die. The NVIDIA chip is larger in both transistor count and die size.

Architecture Differences

The two GPUs are built on fundamentally different architectures, though both use a 28 nm process at TSMC. The AMD Radeon R9 M375 uses the Tropo chip based on GCN 1.0, while the NVIDIA GeForce GTX 960M uses GM107 based on Maxwell. Both have identical core counts — 640 shading units, 40 texture mapping units, and 16 ROPs — but the similarities end there.

Clock speeds favor NVIDIA. The GTX 960M runs at a base clock of 1097 MHz and boosts to 1176 MHz, while the R9 M375 operates at 1000 MHz base and 1015 MHz boost. This translates into higher throughput for the NVIDIA part: 1.505 TFLOPS of FP32 compute versus 1,299.2 GFLOPS, and a texture rate of 47.04 GTexel/s against 40.60 GTexel/s. The pixel rate also favors NVIDIA at 18.82 GPixel/s versus 16.24 GPixel/s.

Memory is where the gap becomes cavernous. The GTX 960M ships with 4 GB of GDDR5 running at 1253 MHz (5 Gbps effective) on a 128-bit bus, providing 80.19 GB/s of bandwidth. The R9 M375 has 2 GB of DDR3 at 900 MHz (1800 Mbps effective) on the same 128-bit bus, yielding just 28.80 GB/s. This is a 2.8x difference in memory bandwidth, which heavily influences the OpenCL results. The GTX 960M’s TDP is listed at 75 W with an MXM Module slot width and no power connectors, while the R9 M375’s power figures are not provided in the data.

API support differs subtly. The R9 M375 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The GTX 960M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The AMD card has a higher DirectX feature level, but the NVIDIA card has a newer Vulkan version. The bus interfaces also differ: the R9 M375 uses PCIe 3.0 x16, while the GTX 960M uses MXM-B (3.0), which is a module standard rather than a slot interface.

The Verdict

The data points to a clear trade-off rather than a single winner. If Vulkan performance is the priority, the AMD Radeon R9 M375 is the better choice — its 17.4% lead in that test is decisive, and its average score is higher overall. The R9 M375 also holds a higher percentile ranking (48th versus 46th) and beats the GTX 960M in average benchmark score by 425 points. It also supports DirectX 12 (11_1), which is a slightly higher feature level than the GTX 960M’s 11_0.

However, the NVIDIA GeForce GTX 960M wins in OpenCL by 5.3%, and its memory configuration is vastly superior: 4 GB of GDDR5 versus 2 GB of DDR3, with 80.19 GB/s against 28.80 GB/s. This makes the GTX 960M the better option for workloads that are bandwidth-sensitive or require larger frame buffers, such as higher-resolution textures or multi-tasking with multiple displays. The GTX 960M also has higher clock speeds, more FP32 throughput, and a faster pixel rate.

For a gamer or user running a mix of modern and legacy titles, the R9 M375’s Vulkan advantage is the more future-proof metric, especially since Vulkan is increasingly used in newer game engines. For compute tasks or older DirectX 11 titles that rely on raw bandwidth, the GTX 960M is the safer bet. The choice hinges on whether the workload leans toward Vulkan (pick AMD) or OpenCL and memory-heavy tasks (pick NVIDIA).

Specification Differences

| Specification | AMD Radeon R9 M375 | NVIDIA GeForce GTX 960M |

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

| Chip | Tropo | GM107 |

| Architecture | GCN 1.0 | Maxwell |

| Process Node | 28 nm | 28 nm |

| Foundry | TSMC | TSMC |

| Transistors | 1,500 million | 1,870 million |

| Die Size | 123 mm² | 148 mm² |

| Transistor Density | 12.2M / mm² | 12.6M / mm² |

| Base Clock | 1000 MHz | 1097 MHz |

| Boost Clock | 1015 MHz | 1176 MHz |

| Memory Clock | 900 MHz (1800 Mbps effective) | 1253 MHz (5 Gbps effective) |

| Memory Size | 2 GB | 4 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 128 bit |

| Memory Bandwidth | 28.80 GB/s | 80.19 GB/s |

| Shading Units | 640 | 640 |

| TMUs | 40 | 40 |

| ROPs | 16 | 16 |

| Pixel Rate | 16.24 GPixel/s | 18.82 GPixel/s |

| Texture Rate | 40.60 GTexel/s | 47.04 GTexel/s |

| FP32 | 1,299.2 GFLOPS | 1.505 TFLOPS |

| TDP | Not provided | 75 W |

| Slot Width | Not provided | MXM Module |

| Power Connectors | Not provided | None |

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

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

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.2.170 | 1.4 |

| Production Status | End-of-life | End-of-life |

| Release Date | 2015-05-04 | 2015-03-12 |

| Predecessor | Solar System | GeForce 800M |

| Successor | Polaris Mobile | GeForce 10 Mobile |

Where Each One Wins

The AMD Radeon R9 M375 wins in Vulkan-based applications and modern API scenarios. Its 9682 Vulkan score is 17.4% higher than the GTX 960M’s, and this advantage is amplified by the fact that the NVIDIA card loses about a quarter of its OpenCL performance when switching to Vulkan. The R9 M375 also wins on average benchmark score (10070 vs 9645) and percentile ranking (48th vs 46th). For users running Vulkan-capable games or using Vulkan-based compute, the AMD card is the clear pick.

The NVIDIA GeForce GTX 960M wins in OpenCL compute and memory-heavy tasks. Its 11045 OpenCL score beats the R9 M375 by 5.3%, and its 80.19 GB/s of memory bandwidth is a massive advantage for workloads that stream large datasets. The 4 GB frame buffer also allows for higher-resolution textures and more demanding visual settings without running out of memory. The GTX 960M’s higher clocks (1097 MHz base, 1176 MHz boost) and greater FP32 throughput (1.505 TFLOPS) make it the better choice for general-purpose compute and older DirectX 11 games that do not leverage Vulkan. Its 75 W TDP, while not compared directly to the R9 M375 (whose TDP is unlisted), suggests a more power-conscious design for thin laptops.