AMD Radeon R5 M335 vs AMD Radeon R7 M360 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R7 M360 posts an average benchmark score of 4931, while the AMD Radeon R5 M335 scores 4752. This places the R7 M360 at the 29th percentile of all GPUs, one point above the R5 M335's 28th percentile.

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

A: The AMD Radeon R5 M335 wins the Geekbench OpenCL test with a score of 4745 versus the R7 M360's 4638, a 2.3% advantage for the R5 M335.

Q: Which GPU is stronger in Vulkan workloads?

A: The AMD Radeon R7 M360 takes the Geekbench Vulkan test decisively, scoring 5223 against the R5 M335's 4758. That is a 9.8% lead for the R7 M360.

Q: What are the core counts of each GPU?

A: The R7 M360 has 384 shading units, 24 texture mapping units, and 8 ROPs. The R5 M335 has 320 shading units, 20 texture mapping units, and also 8 ROPs.

Q: Do both cards use the same memory configuration?

A: Yes, both come with 2 GB of DDR3 memory on a 64-bit bus, yielding an identical 14.40 GB/s of bandwidth and the same 900 MHz memory clock (1800 Mbps effective).

Q: What is the architectural generation difference?

A: The R7 M360 is built on GCN 3.0 with the Meso chip, while the R5 M335 uses GCN 1.0 with the Exo chip. Both are fabricated on TSMC's 28 nm process.

Where Each One Wins

The benchmark split is clean: one card wins each of the two tests, and the margins tell a different story about where each GPU excels.

The AMD Radeon R7 M360 is the clear choice for Vulkan-based workloads. Its Geekbench Vulkan score of 5223 towers over the R5 M335's 4758, a 9.8% advantage. This is a substantial gap for two mobile GPUs from the same generation family, suggesting the newer GCN 3.0 architecture handles modern API overhead more efficiently. The R7 M360's higher shading unit count (384 versus 320) and texture unit count (24 versus 20) contribute to this lead, as does its superior texture rate of 27.00 GTexel/s versus 20.60 GTexel/s on the R5 M335.

Conversely, the AMD Radeon R5 M335 wins the OpenCL test, albeit by a thinner margin. Its score of 4745 beats the R7 M360's 4638 by 2.3%. This is a narrower victory, and it is notable because the R5 M335 has fewer shading units, fewer TMUs, and lower theoretical FP32 throughput (659.2 GFLOPS versus 864.0 GFLOPS). The fact that the smaller, older-architecture GPU wins an OpenCL compute test suggests that driver optimizations or workload characteristics favor the GCN 1.0 design in that specific API path.

In terms of pixel throughput, the R7 M360 also leads with 9.000 GPixel/s against the R5 M335's 8.240 GPixel/s, a 9.2% difference that mirrors its Vulkan win. Both cards tie on memory bandwidth at 14.40 GB/s, so neither gains an edge from memory subsystem performance.

The average benchmark scores reflect this mixed result: the R7 M360's 4931 average is 3.8% higher than the R5 M335's 4752. However, the R5 M335's nearest rival list includes the AMD Radeon R5 M255 at 4788 (0.7% ahead of the R5 M335) and the NVIDIA GeForce RTX 3080 12 GB at 4791 (0.8% ahead), which underscores how close these mobile parts cluster in overall performance. For the R7 M360, its nearest rival is the AMD Radeon R7 M265 at 4929, a virtual tie.

Architecture Differences

The two GPUs come from different generations of AMD's Graphics Core Next design, and that distinction drives most of their behavioral differences.

The AMD Radeon R7 M360 is built on GCN 3.0, implemented in the Meso chip. This is the newer architecture, and it supports DirectX 12 at feature level 12_0. The R7 M360 also includes FP16 support at a 1:1 ratio with FP32, meaning it can process half-precision floats at the same 864.0 GFLOPS rate as its single-precision throughput. This is a capability the R5 M335 lacks entirely, as its FP16 field is null.

The AMD Radeon R5 M335 uses GCN 1.0, the original GCN design, on the Exo chip. Its DirectX support is rated at 12 (11_1), which is functionally a lower feature level than the R7 M360's 12_0. Both cards support OpenGL 4.6 and Vulkan 1.2.170, so API compatibility beyond DirectX is identical.

The transistor counts reveal a significant design gap. The Meso chip in the R7 M360 packs 1,550 million transistors on a 125 mm² die, while the Exo chip in the R5 M335 has 690 million transistors on a 56 mm² die. The transistor density is nearly identical — 12.4M per mm² for the R7 M360 versus 12.3M per mm² for the R5 M335 — indicating that the larger chip is simply scaled up with more compute resources rather than using denser logic.

Both GPUs are manufactured by TSMC on a 28 nm process, and both are classified as end-of-life products. Their generation lineage is the same: both list "Solar System" as predecessor and "Polaris Mobile" as successor, confirming they are part of the same product family evolution. The R7 M360 carries the "Gem System (R7 M300)" generation label, while the R5 M335 is in the "Gem System (R5 M300)" tier.

Specification Differences

The two cards differ across several key specification fields, and these differences align with their benchmark outcomes.

The shading unit count is the most prominent gap: 384 on the R7 M360 versus 320 on the R5 M335, a 20% difference. Texture mapping units follow the same ratio at 24 versus 20, also a 20% delta. Both GPUs have 8 ROPs, so pixel output capability is closer in hardware design, though the R7 M360's higher clock still gives it a pixel rate advantage.

Clock speeds are another differentiator. The R7 M360 runs at a base clock of 1100 MHz with a boost clock of 1125 MHz. The R5 M335 has no base or boost clock listed in the data, which is notable — it means the R5 M335's performance is derived entirely from its memory clock and architectural efficiency rather than a specified core frequency. Both share the same memory clock of 900 MHz (1800 Mbps effective).

Theoretical throughput figures amplify the core count differences. The R7 M360 delivers 864.0 GFLOPS of FP32 compute, 27.00 GTexel/s of texture fill, and 9.000 GPixel/s of pixel fill. The R5 M335 delivers 659.2 GFLOPS, 20.60 GTexel/s, and 8.240 GPixel/s respectively. In every rate metric, the R7 M360 leads by roughly 20-31%, with the pixel rate gap being the narrowest at about 9%.

Physical specifications also differ in the power connector field. The R5 M335 lists "None" for power connectors and "Portable Device Dependent" for display outputs, reflecting its low-power mobile design. The R7 M360 does not specify these fields, but both cards use a PCIe 3.0 x8 bus interface.

Neither card has a launch MSRP listed, and both are end-of-life products. The R7 M360 was released on 2015-05-04, while the R5 M335 followed later on 2015-10-20.

Head-to-Head Benchmarks

The direct comparison between these two GPUs yields one win apiece, but the magnitude of those wins is asymmetric.

In Geekbench OpenCL, the AMD Radeon R5 M335 scores 4745 against the R7 M360's 4638. This 2.3% delta in favor of the R5 M335 is modest, and it is surprising given the R7 M360's hardware advantages. The R7 M360 has 20% more shading units and 23% higher theoretical FP32 throughput, yet it loses the OpenCL test. This suggests that the R5 M335's GCN 1.0 architecture, despite being older, may have more mature OpenCL driver paths or that the workload is not sufficiently parallel to utilize the R7 M360's extra execution resources.

In Geekbench Vulkan, the tables turn decisively. The AMD Radeon R7 M360 scores 5223, while the R5 M335 manages 4758. The 9.8% delta is the largest margin in either test and represents a substantial performance advantage for the R7 M360. This result aligns with the architectural differences: GCN 3.0's DirectX 12_0 feature level and modern scheduling likely translate better to Vulkan's explicit, low-overhead model. The R7 M360's higher texture rate (27.00 versus 20.60 GTexel/s) also contributes to geometry and fill-bound Vulkan workloads.

The average benchmark scores confirm the R7 M360's overall superiority: 4931 versus 4752, a 3.8% gap. The R7 M360's nearest rival is the AMD Radeon R7 M265 at 4929 (0% delta), while the R5 M335's closest competitor is the AMD Radeon R5 M255 at 4788 (0.7% faster than the R5 M335). The R5 M335 also sits within 1.5% of the NVIDIA Quadro P400 (4684) and within 0.8% of the NVIDIA GeForce RTX 3080 12 GB (4791), highlighting how clustered this performance tier is.

For the R7 M360, its nearest rival list includes the NVIDIA GeForce RTX 5060 Ti 8 GB at 4901 (0.6% behind) and the NVIDIA GeForce GTS 450 at 4893 (0.8% behind). These comparisons show that the R7 M360, despite being a mobile part, lands in a performance bracket that includes desktop GPUs from other eras. The R7 M360's single Vulkan win is enough to push its average score above that cluster, while the R5 M335's OpenCL win is too small to overcome its Vulkan deficit.