AMD Radeon R9 M375 vs NVIDIA GeForce GTX 870M Comparison

The AMD Radeon R9 M375 and NVIDIA GeForce GTX 870M are both end-of-life mobile graphics solutions from the 2014-2015 era, targeting similar performance tiers in the laptop space. The data shows a clear single benchmark comparison, with the NVIDIA part taking the only head-to-head win, yet the broader average scores indicate a much closer overall standing between the two.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test, and the result is decisive in favor of the NVIDIA GeForce GTX 870M. The GTX 870M scores 12,630 points, while the AMD Radeon R9 M375 manages 10,457 points. This represents a 17.2% deficit for the AMD part, which is a substantial margin in raw compute performance under this particular workload. The OpenCL test is particularly relevant for general-purpose GPU compute tasks, content creation acceleration, and any application that leverages the GPU for non-rendering workloads.

When looking at the average benchmark scores across all available tests, the picture becomes more nuanced. The R9 M375 posts an average score of 10,070, while the GTX 870M averages 9,959. This flips the narrative slightly, showing the AMD card holding a 1.1% advantage in the aggregate. This discrepancy between the single OpenCL result and the average scores suggests that the AMD card may perform relatively better in other unnamed tests, or that the OpenCL test is particularly favorable to the NVIDIA architecture. The deltaPct figures from the nearest rivals confirm this tight grouping: the R9 M375 sits 1.1% ahead of the GTX 870M, while the GTX 870M sits 1.1% behind the R9 M375, placing them nearly neck-and-neck in overall standing.

Both GPUs occupy the 48th percentile among all GPUs tracked, which places them squarely in the mid-range of mobile graphics performance for their generation. The AMD Radeon Pro 5300M and NVIDIA Quadro K5100M flank both cards within a 0.3% to 0.8% margin, illustrating just how crowded this performance tier is. The GTX 870M also shows a 1.1% lead over the NVIDIA Quadro 6000, while the R9 M375 trails the NVIDIA GeForce GTX 950A by 2% — the largest gap in either card's nearest rival list.

The Verdict

From the data, the NVIDIA GeForce GTX 870M is the stronger choice if your primary concern is raw OpenCL compute performance. The 17.2% advantage in that single benchmark is too large to ignore for users who run GPU-accelerated applications that rely heavily on OpenCL. The GTX 870M also brings a substantially larger memory bandwidth figure, which we will examine in the specification section, making it more suitable for texture-heavy workloads.

However, the AMD Radeon R9 M375 is not without merit. Its average benchmark score is 1.1% higher than the GTX 870M, indicating that across a broader suite of tests it holds a slight edge. If your workload mix includes tasks beyond pure OpenCL compute, the AMD part may deliver more consistent overall performance. The R9 M375 also supports DirectX 12 (11_1) compared to the GTX 870M's DirectX 12 (11_0), which could matter for newer titles that leverage the higher feature level.

For the practical builder, the choice hinges on workload specificity. If you need maximum OpenCL throughput, the GTX 870M is the pick. If you want a more balanced performer that edges out in aggregate benchmarks, the R9 M375 is the safer bet. The 48th percentile ranking for both cards means neither will excel at modern AAA gaming, but both remain viable for older titles and productivity tasks. Given the 1.1% aggregate difference and the 17.2% OpenCL gap, the GTX 870M's single-test dominance gives it the edge for compute-focused users, while the R9 M375's average score makes it the more versatile option.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M375 averages 10,070 points, which is 1.1% higher than the NVIDIA GeForce GTX 870M's 9,959 points.

Q: How much faster is the GTX 870M in the OpenCL benchmark?

A: The GTX 870M scores 12,630 in Geekbench OpenCL, compared to the R9 M375's 10,457, representing a 17.2% advantage for the NVIDIA card.

Q: Do both GPUs rank at the same percentile among all GPUs?

A: Yes, both the AMD Radeon R9 M375 and the NVIDIA GeForce GTX 870M sit at the 48th percentile when compared against all GPUs in the database.

Q: What is the memory bandwidth difference between the two cards?

A: The GTX 870M has 120.0 GB/s of bandwidth, while the R9 M375 has 28.80 GB/s, making the NVIDIA card approximately four times faster in memory throughput.

Q: Which GPU supports a higher DirectX feature level?

A: The AMD Radeon R9 M375 supports DirectX 12 (11_1), while the NVIDIA GeForce GTX 870M supports DirectX 12 (11_0), giving the AMD card a higher feature level.

Q: What are the transistor counts for each GPU?

A: The GTX 870M has 3,540 million transistors, while the R9 M375 has 1,500 million transistors, meaning the NVIDIA chip has over twice as many transistors.

Specification Differences

The two GPUs differ significantly in nearly every core specification category. The NVIDIA GeForce GTX 870M uses a 192-bit memory bus with 3 GB of GDDR5 memory, delivering 120.0 GB/s of bandwidth. The AMD Radeon R9 M375, by contrast, uses a 128-bit bus with 2 GB of DDR3 memory, yielding just 28.80 GB/s. This memory subsystem disparity is the largest single specification gap, with the NVIDIA card holding a 4.17x bandwidth advantage.

In terms of compute units, the GTX 870M has 1,344 shading units, 112 texture mapping units, and 24 ROPs. The R9 M375 has 640 shading units, 40 TMUs, and 16 ROPs. The NVIDIA card also leads in pixel rate at 27.08 GPixel/s versus 16.24 GPixel/s, and texture rate at 108.3 GTexel/s versus 40.60 GTexel/s. The FP32 compute performance shows 2.599 TFLOPS for the GTX 870M and 1,299.2 GFLOPS for the R9 M375.

Clock speeds are relatively close, with the R9 M375 boosting to 1015 MHz and the GTX 870M boosting to 967 MHz. The AMD card has a slightly higher base clock at 1000 MHz versus 941 MHz, but this does not compensate for the NVIDIA part's massive advantage in shader count and memory bandwidth. The TDP is listed at 100 W for the GTX 870M, while no TDP is provided for the R9 M375. The GTX 870M uses an MXM-B (3.0) bus interface, while the R9 M375 uses PCIe 3.0 x16.

Architecture Differences

The architectural divide between these two GPUs is stark. The AMD Radeon R9 M375 is built on GCN 1.0 architecture using the Tropo chip, manufactured on a 28 nm process at TSMC. It contains 1,500 million transistors on a 123 mm² die. The NVIDIA GeForce GTX 870M uses Kepler architecture with the GK104 chip, also on TSMC's 28 nm process, but packs 3,540 million transistors onto a 294 mm² die. The transistor density is nearly identical at 12.2M per mm² for AMD and 12.0M per mm² for NVIDIA, showing that both use similar design density at the same process node.

The GTX 870M belongs to the GeForce 800M generation, succeeding the GeForce 700M series and preceding the GeForce 900M. The R9 M375 comes from the Gem System (R9 M300) generation, with the Solar System as its predecessor and Polaris Mobile as its successor. In terms of API support, the R9 M375 supports Vulkan 1.2.170, while the GTX 870M supports Vulkan 1.2.175, a slightly newer revision. Both support OpenGL 4.6.

The memory architecture differences stem from the underlying design choices. The GTX 870M's GK104 chip was designed as a high-end desktop GPU adapted for mobile, while the Tropo chip in the R9 M375 is a smaller, lower-power design. This explains the 2.36x transistor count difference and the resulting disparity in memory bus width and bandwidth. The R9 M375 has no listed power connectors and no TDP, while the GTX 870M is explicitly rated at 100 W with an MXM Module slot width.

Where Each One Wins

The NVIDIA GeForce GTX 870M wins decisively in OpenCL compute, with a 17.2% advantage in the head-to-head benchmark. This makes it the superior choice for GPU-accelerated applications that leverage OpenCL, such as video encoding, scientific simulations, and certain rendering tasks. The GTX 870M also wins in memory bandwidth by a factor of 4.17x, which will benefit texture-heavy games and applications that require large data transfers. Its higher pixel rate (27.08 GPixel/s vs 16.24 GPixel/s) and texture rate (108.3 GTexel/s vs 40.60 GTexel/s) make it the better performer for fill-rate-bound workloads.

The AMD Radeon R9 M375 wins in the aggregate average benchmark score, holding a 1.1% lead over the GTX 870M. This suggests it performs better across a broader range of tests beyond the single OpenCL benchmark. The AMD card also has a higher boost clock at 1015 MHz versus 967 MHz, and it supports a higher DirectX feature level (11_1 vs 11_0), which could provide better compatibility with certain modern games. The R9 M375's smaller die size (123 mm² vs 294 mm²) and lower transistor count (1,500 million vs 3,540 million) imply lower power consumption and heat output, though no TDP is listed for the AMD card.

For use cases, the GTX 870M is the clear pick for anyone running OpenCL-heavy workloads or games that are bandwidth-sensitive. The R9 M375 is better suited for users who want a more balanced part with slightly better aggregate performance and lower power draw. Neither GPU is competitive with modern parts, but within this vintage tier, the GTX 870M's raw compute and memory advantages make it the stronger choice for performance-oriented builds, while the R9 M375 offers a more efficient alternative with a small aggregate performance edge.