AMD Radeon R9 M360 vs NVIDIA GeForce GTX 870M Comparison

Head-to-Head Benchmarks

The head-to-head comparison between the NVIDIA GeForce GTX 870M and the AMD Radeon R9 M360 is decisively lopsided in favor of the NVIDIA part. In the only directly comparable benchmark recorded in the database, Geekbench OpenCL, the GTX 870M scores 12630 against the R9 M360's 8211. That represents a 53.8% advantage for the NVIDIA GPU, a massive gap that places these two mobile graphics processors in entirely different performance tiers.

To put that margin in perspective, the database's nearest rival data shows how close the competition is around each card. The GTX 870M's average benchmark score is 9959, while the R9 M360's average is 8129. The NVIDIA card sits at the 48th percentile of all GPUs, whereas the AMD card lands at the 42nd percentile. The GTX 870M is not merely ahead; it is ahead by a margin that rivals the difference between entire product stack levels.

The R9 M360's nearest rival, the NVIDIA GeForce GTX 950M, scores 8135, which is only 0.1% higher than the AMD part's 8129 average. That means the R9 M360 is essentially trading blows with the GTX 950M, a mainstream mobile GPU. Meanwhile, the GTX 870M's nearest rivals include the AMD Radeon Pro 5300M (10013, 0.5% higher) and the NVIDIA Quadro K5100M (10043, 0.8% higher), both of which are just barely ahead of the 870M's 9959 average. The GTX 870M is competing in a class roughly 22% above where the R9 M360 sits.

The single head-to-head benchmark result reinforces the overall average scores. The 53.8% delta in Geekbench OpenCL is not a marginal victory; it is a category-level separation. The GTX 870M's raw score of 12630 also exceeds its own average benchmark score of 9959 by a substantial amount, indicating that the OpenCL workload plays to its strengths. The R9 M360's 8211 OpenCL result is closer to its 8129 average, suggesting that this test is representative of its typical performance.

Examining the rival lists further clarifies the positioning. The GTX 870M's closest rival, the Quadro 6000, scores 9846 and trails by 1.1%, while the R9 M360's closest rival, the GeForce GTX 980, scores 8167 and leads by 0.5%. The GTX 980 is a desktop flagship from a previous generation, yet the R9 M360 is merely keeping pace with it in this database's scoring, while the GTX 870M is outpacing it by more than 20%. The data clearly shows that the GTX 870M occupies a higher performance stratum.

Where Each One Wins

The NVIDIA GeForce GTX 870M wins every benchmark category where both cards have recorded results. It holds a single head-to-head win out of one possible comparison. The R9 M360 has zero wins in direct comparisons.

More importantly, the GTX 870M wins across the board when considering the breadth of available data. Its average benchmark score of 9959 versus the R9 M360's 8129 means the NVIDIA card is roughly 22.5% faster on average across all recorded workloads. The GTX 870M also demonstrates a higher peak in OpenCL (12630) than the R9 M360 achieves in either of its recorded tests (8211 in OpenCL, 8047 in Vulkan).

The R9 M360 does have one distinction: it shows a Vulkan score of 8047, a test the GTX 870M does not have recorded in the database. This does not translate into a win, but it does indicate that the AMD card has been tested across a broader range of modern APIs. The GTX 870M's OpenCL score of 12630, however, is 53.8% higher than the R9 M360's OpenCL score, and even the R9 M360's best result (8211) falls 35% short of the GTX 870M's worst recorded benchmark (9959 average, though the individual OpenCL result is higher).

For workloads that rely on OpenCL compute, the GTX 870M is the clear choice. The 53.8% delta in that specific test is the largest single margin in this comparison. For users who need Vulkan support, the R9 M360 at least has a recorded score (8047), but that score is below the GTX 870M's average, implying that even in Vulkan the NVIDIA card would likely hold a lead had it been tested.

The percentile data reinforces the split. The GTX 870M's 48th percentile places it in the upper-middle range of all GPUs, while the R9 M360's 42nd percentile places it just below the midpoint. In practical terms, the GTX 870M is suited for demanding 1080p gaming and compute workloads, whereas the R9 M360 is more appropriate for lighter duties or as a fallback GPU in systems where power efficiency is prioritized over raw throughput.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 870M has an average benchmark score of 9959, while the AMD Radeon R9 M360 averages 8129. The GTX 870M is approximately 22.5% faster on average.

Q: What is the largest single benchmark margin between these two cards?

A: In the Geekbench OpenCL test, the GTX 870M scores 12630 versus the R9 M360's 8211, a 53.8% advantage for the NVIDIA card.

Q: Does the AMD Radeon R9 M360 outperform the GTX 870M in any recorded benchmark?

A: No. The R9 M360 has zero head-to-head wins. Its best recorded score is 8211 in OpenCL, while the GTX 870M's OpenCL score is 12630.

Q: How does each card compare to its nearest rivals?

A: The GTX 870M's closest rival is the AMD Radeon Pro 5300M, which scores 10013 and leads by 0.5%. The R9 M360's closest rival is the NVIDIA GeForce GTX 950M, scoring 8135, which leads by 0.1%.

Q: Which card has a higher percentile ranking among all GPUs?

A: The GTX 870M sits at the 48th percentile, while the R9 M360 sits at the 42nd percentile, indicating the NVIDIA card is ranked higher overall.

Q: What API scores are recorded for each card?

A: The GTX 870M has Geekbench Metal (7288) and Geekbench OpenCL (12630) scores. The R9 M360 has Geekbench OpenCL (8211) and Geekbench Vulkan (8047) scores.

Specification Differences

The two GPUs differ substantially across nearly every 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 M360 uses a narrower 128-bit bus with 4 GB of GDDR5 memory, yielding 72.00 GB/s. The GTX 870M's memory clock runs at 1250 MHz (5 Gbps effective), while the R9 M360's runs at 1125 MHz (4.5 Gbps effective).

Compute resources favor the NVIDIA card heavily. The GTX 870M has 1344 shading units, 112 texture mapping units (TMUs), and 24 raster operation units (ROPs). The R9 M360 has just 512 shading units, 32 TMUs, and 16 ROPs. The pixel rate of the GTX 870M is 27.08 GPixel/s versus 14.80 GPixel/s for the AMD card. Texture rate is 108.3 GTexel/s against 29.60 GTexel/s. Floating point performance (FP32) reaches 2.599 TFLOPS on the GTX 870M, while the R9 M360 manages 947.2 GFLOPS.

Clock speeds are relatively close, with the GTX 870M running at a 941 MHz base and 967 MHz boost, while the R9 M360 runs at 900 MHz base and 925 MHz boost. The power draw differs as well: the GTX 870M has a TDP of 100 W, while the R9 M360 has no TDP recorded in the database. The bus interface also differs: the GTX 870M uses MXM-B (3.0), while the R9 M360 uses PCIe 3.0 x16. The GTX 870M is an MXM module, whereas the R9 M360's slot width is not recorded.

Architecture Differences

The architectural gap between these two GPUs is significant. The NVIDIA GeForce GTX 870M is built on the Kepler architecture using the GK104 chip, fabricated on a 28 nm process at TSMC. It contains 3,540 million transistors on a 294 mm² die, resulting in a transistor density of 12.0 million per mm². The AMD Radeon R9 M360 uses the GCN 1.0 architecture with the Tropo chip, also on TSMC's 28 nm process, but with only 1,500 million transistors on a 123 mm² die, giving a density of 12.2 million per mm².

The GTX 870M belongs to the GeForce 800M generation and has a predecessor in the GeForce 700M series, with the GeForce 900M as its successor. The R9 M360 belongs to the Gem System (R9 M300) generation, with the Solar System as its predecessor and Polaris Mobile as its successor. The GTX 870M was released in March 2014, while the R9 M360 came in May 2015, a difference of over a year.

API support shows minor differences. Both support DirectX 12 and OpenGL 4.6, but the GTX 870M's DirectX version is 12 (11_0) while the R9 M360's is 12 (11_1). Vulkan versions are 1.2.175 for NVIDIA and 1.2.170 for AMD. The GTX 870M's display outputs are described as "Portable Device Dependent," while the R9 M360 has no display output data recorded. The R9 M360 has no power connector information, while the GTX 870M lists "None" for power connectors.

The die size difference is particularly notable: the GTX 870M's GK104 die is nearly 2.4 times larger than the R9 M360's Tropo die. This explains the transistor count disparity (3,540 million versus 1,500 million) and contributes to the performance gap. The smaller die on the AMD card also explains its lower transistor density, despite the same 28 nm process node, because the GK104 packs more logic into a larger area.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 870M is the superior GPU in this comparison. It wins the only direct head-to-head benchmark by 53.8%, holds a higher average benchmark score (9959 versus 8129), and ranks higher in the percentile distribution (48th versus 42nd). Every compute resource metric favors the NVIDIA card: shading units (1344 versus 512), TMUs (112 versus 32), ROPs (24 versus 16), pixel rate (27.08 versus 14.80 GPixel/s), texture rate (108.3 versus 29.60 GTexel/s), and FP32 throughput (2.599 TFLOPS versus 947.2 GFLOPS).

The GTX 870M also delivers substantially more memory bandwidth (120.0 GB/s versus 72.00 GB/s) despite having less total memory (3 GB versus 4 GB). The wider 192-bit bus versus 128-bit bus is the primary reason, and it matters more for sustained throughput than the extra gigabyte of capacity on the AMD card.

The R9 M360 does have a few points in its favor. It offers 4 GB of memory, which may help in texture-heavy workloads that exceed the GTX 870M's 3 GB capacity. It also has a recorded Vulkan score (8047), indicating modern API support that the GTX 870M lacks in the database. Its smaller die (123 mm² versus 294 mm²) and transistor count (1,500 million versus 3,540 million) suggest it could be more power-efficient, though no TDP is recorded for the AMD card to confirm this.

Who should pick which? Users seeking maximum performance for gaming or compute workloads should choose the GTX 870M without hesitation. Its 53.8% lead in OpenCL and 22.5% lead in average score make it the clear choice for demanding applications. Users who prioritize larger memory capacity or need Vulkan support in a lighter, smaller package might consider the R9 M360, but they should expect roughly half the compute throughput. The GTX 870M is the verdict for anyone who values raw performance, while the R9 M360 serves only as a fallback for specific use cases involving Vulkan or memory capacity beyond 3 GB.