AMD Radeon R5 Graphics vs NVIDIA GeForce GT 735M Comparison

AMD Radeon R5 Graphics and NVIDIA GeForce GT 735M are both end-of-life mobile-class graphics solutions, but benchmark results place them in distinctly different performance tiers. The data shows a clear overall winner in the single available head-to-head benchmark, with the AMD part achieving a 43.3% higher score in Geekbench OpenCL (5183 vs 3616). This places the Radeon R5 Graphics in the 23rd percentile of all GPUs, while the GeForce GT 735M sits slightly lower at the 21st percentile, underscoring that despite the large relative gap, both are entry-level parts in the broader market.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench OpenCL test, and it produces a decisive outcome. AMD Radeon R5 Graphics scores 5183, while NVIDIA GeForce GT 735M scores 3616. The deltaPct of 43.3% is substantial, meaning the AMD part is over two-fifths faster in this compute-oriented workload. This is not a marginal victory; it is a generational-style gap that suggests the AMD IGP can handle OpenCL tasks with noticeably more headroom than the discrete NVIDIA chip.

Looking at the average benchmark scores, the pattern holds. AMD Radeon R5 Graphics has an average score of 3883, which is 267 points higher than the GeForce GT 735M’s 3616. This 7.4% advantage in the average metric is smaller than the OpenCL delta, but it still confirms the AMD part’s overall superiority. The average score for the AMD part is pulled down by its Vulkan result of 2582, which is significantly lower than its OpenCL score, while the NVIDIA part only has an OpenCL result listed. For the NVIDIA chip, the average equals its sole benchmark score, indicating no other data points are available.

The nearest rival data provides additional context for each part’s standing. The AMD Radeon R5 Graphics’ average score of 3883 places it just 0.4% behind the NVIDIA Quadro 2000 (3898) and 0.9% behind the Quadro K2000D (3919). It is 1.3% ahead of the GeForce MX110 (3834). The NVIDIA GeForce GT 735M’s average of 3616 puts it 0.3% behind the GeForce GTX 1050 (3629) and 0.9% behind the Radeon HD 6770 (3649), while it leads the RTX 5000 Mobile Ada Generation (3596) by 0.6%. These deltas are all within roughly a single percentage point, meaning each part is tightly clustered with its nearest competitors, but the AMD part’s cluster sits at a higher absolute score level.

Architecture Differences

The two GPUs come from different architectural families and foundries, which explains their divergent performance characteristics. AMD Radeon R5 Graphics uses the Spectre SL chip based on GCN 2.0 architecture, built on a 28 nm process at GlobalFoundries. NVIDIA GeForce GT 735M uses the GK208 chip based on Kepler 2.0 architecture, also on a 28 nm process but manufactured by TSMC. Both use the same process node, but the transistor counts differ dramatically: AMD packs 2,410 million transistors on a 245 mm² die, while NVIDIA uses 1,020 million transistors on an 87 mm² die. This results in a transistor density of 9.8M per mm² for AMD and 11.7M per mm² for NVIDIA, meaning the NVIDIA chip is more densely packed but far smaller overall.

The compute resources are configured very differently. AMD Radeon R5 Graphics has 256 shading units, 16 texture mapping units (TMUs), and only 4 raster operation units (ROPs). NVIDIA GeForce GT 735M has more of each: 384 shading units, 32 TMUs, and 8 ROPs. Despite having fewer cores, the AMD part achieves a higher OpenCL score, which indicates that GCN 2.0’s architecture is more efficient per shader in compute workloads, or that the NVIDIA part is more heavily limited by its memory subsystem. The AMD part’s pixel rate is 3.032 GPixel/s and texture rate is 12.13 GTexel/s, while the NVIDIA part reaches 5.024 GPixel/s and 20.10 GTexel/s, showing that NVIDIA has a clear advantage in raw rasterization throughput.

Memory architecture is a critical differentiator. AMD Radeon R5 Graphics uses system-shared memory, with the size, type, and bus width all listed as "System Shared" and bandwidth described as "System Dependent." This means its performance is tied to the host system’s RAM configuration. NVIDIA GeForce GT 735M has dedicated 2 GB of DDR3 memory on a 64-bit bus, with a fixed bandwidth of 14.40 GB/s. The NVIDIA part’s memory runs at 900 MHz (1800 Mbps effective), while the AMD part’s memory clock is also listed as "System Shared." This difference means the NVIDIA chip has predictable, dedicated memory bandwidth, whereas the AMD IGP’s performance can vary based on the laptop’s memory setup.

Where Each One Wins

AMD Radeon R5 Graphics wins decisively in compute-oriented workloads, as evidenced by its 43.3% lead in Geekbench OpenCL. This makes it the stronger choice for applications that leverage OpenCL for general-purpose GPU computing, such as video encoding, physics simulations, or data-parallel tasks. The AMD part’s higher average benchmark score (3883 vs 3616) reinforces this, suggesting it maintains a lead across multiple test scenarios. Its GCN 2.0 architecture, which is known for strong compute throughput, appears to deliver better raw number-crunching performance despite having fewer shading units, TMUs, and ROPs than the NVIDIA part.

NVIDIA GeForce GT 735M has no benchmark wins in this dataset, but the specification sheet suggests it would excel in traditional graphics workloads. Its higher pixel rate (5.024 GPixel/s vs 3.032 GPixel/s) and texture rate (20.10 GTexel/s vs 12.13 GTexel/s) indicate it can fill pixels and sample textures faster, which is beneficial for gaming at lower resolutions and older DirectX titles. The dedicated 2 GB DDR3 memory with 14.40 GB/s bandwidth provides consistent performance independent of system RAM, avoiding the variability of the AMD part’s system-shared memory. For users running games that are bottlenecked by fill rate or texture throughput, the NVIDIA part would likely deliver smoother frame rates despite its lower compute scores.

It is also worth noting the API support differences. AMD Radeon R5 Graphics supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. NVIDIA GeForce GT 735M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The AMD part has a higher DirectX feature level (12_0 vs 11_0), which may enable newer rendering features in games that require them, while the NVIDIA part has a slightly newer Vulkan version (1.2.175 vs 1.2.170), offering marginal API compatibility improvements.

Specification Differences

The two parts differ across nearly every major specification category. The most significant differences are in memory configuration: AMD uses system-shared memory with no dedicated size, type, or bus width, while NVIDIA has 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth. The AMD part’s bandwidth is "System Dependent," whereas NVIDIA has a fixed figure. Clock speeds also differ: NVIDIA has a base clock of 575 MHz and a boost clock of 628 MHz, while AMD lists no base or boost clock, only "System Shared" for memory clock. The AMD part’s memory clock is similarly unspecified.

Compute resource counts differ substantially. AMD has 256 shading units, 16 TMUs, and 4 ROPs, while NVIDIA has 384 shading units, 32 TMUs, and 8 ROPs. This gives NVIDIA a 50% advantage in shading units and a 100% advantage in both TMUs and ROPs. However, AMD’s pixel rate (3.032 GPixel/s) and texture rate (12.13 GTexel/s) are lower than NVIDIA’s 5.024 GPixel/s and 20.10 GTexel/s, respectively. Floating-point performance (FP32) is 388.1 GFLOPS for AMD and 482.3 GFLOPS for NVIDIA, a 24.3% advantage for the NVIDIA part. Thermal design power (TDP) is another major divider: AMD is rated at 15 W, while NVIDIA is rated at 33 W, meaning the AMD IGP is far more power-efficient on paper.

The chips themselves are built on different architectures and foundries. AMD uses Spectre SL with GCN 2.0, fabricated at GlobalFoundries, while NVIDIA uses GK208 with Kepler 2.0, fabricated at TSMC. Transistor counts are 2,410 million for AMD and 1,020 million for NVIDIA, with die sizes of 245 mm² and 87 mm², respectively. Bus interface differs as well: AMD uses IGP (integrated graphics processor), while NVIDIA uses PCIe 3.0 x8. Power connectors are "None" for NVIDIA, and the AMD part has no listed power connectors. Display outputs are "Motherboard Dependent" for AMD and "Portable Device Dependent" for NVIDIA.

FAQ

Q: Which GPU is faster in OpenCL benchmarks?

A: AMD Radeon R5 Graphics is significantly faster, scoring 5183 in Geekbench OpenCL compared to the NVIDIA GeForce GT 735M’s 3616, a 43.3% advantage.

Q: Why does the NVIDIA part have more shading units but lower benchmark scores?

A: The NVIDIA GeForce GT 735M has 384 shading units versus 256 on the AMD Radeon R5 Graphics, but the AMD part’s GCN 2.0 architecture achieves higher compute efficiency, resulting in a higher OpenCL score.

Q: What type of memory does each GPU use?

A: AMD Radeon R5 Graphics uses system-shared memory with bandwidth dependent on the host system, while NVIDIA GeForce GT 735M has dedicated 2 GB of DDR3 memory on a 64-bit bus with 14.40 GB/s bandwidth.

Q: Which GPU has a lower power draw?

A: AMD Radeon R5 Graphics has a TDP of 15 W, while NVIDIA GeForce GT 735M has a TDP of 33 W, making the AMD part more power-efficient.

Q: What are the DirectX feature level differences?

A: AMD Radeon R5 Graphics supports DirectX 12 (12_0), while NVIDIA GeForce GT 735M supports DirectX 12 (11_0), giving the AMD part a higher feature level.

Q: How do their overall market positions compare?

A: AMD Radeon R5 Graphics sits in the 23rd percentile of all GPUs with an average benchmark score of 3883, while NVIDIA GeForce GT 735M is in the 21st percentile with an average score of 3616.