AMD Radeon R5 M230 vs NVIDIA GeForce GTX 460M Comparison

The AMD Radeon R5 M230 and NVIDIA GeForce GTX 460M represent two distinct generations of mobile graphics, separated by over three years of architectural evolution. The data shows the Radeon R5 M230 holds a 6.9% advantage in the sole head-to-head OpenCL benchmark, scoring 4577 against the GTX 460M’s 4282. This places the AMD part at the 27th percentile of all GPUs, while the NVIDIA part sits at the 25th percentile—a narrow gap that underscores how process node improvements and memory technology shifts have reshaped the competitive landscape for entry-level mobile parts.

FAQ

Q: Which GPU is faster in the benchmark data?

A: The AMD Radeon R5 M230 wins the Geekbench OpenCL test with a score of 4577, compared to 4282 for the NVIDIA GeForce GTX 460M. This represents a 6.9% performance advantage for the AMD part.

Q: How do these GPUs compare to their nearest rivals?

A: The Radeon R5 M230 is 0.2% ahead of the AMD Radeon RX 560 (4569) and 0.4% ahead of the Intel HD Graphics P530 (4560). The GTX 460M is 0.3% behind the AMD Radeon Vega 3 (4268) but 1.0% ahead of the NVIDIA Quadro K3000M (4241).

Q: What are the memory specifications for each GPU?

A: The Radeon R5 M230 uses 2 GB of DDR3 memory on a 64-bit bus, delivering 16.00 GB/s bandwidth. The GTX 460M uses 1536 MB of GDDR5 memory on a 192-bit bus, delivering 60.00 GB/s bandwidth—a substantial 3.75x advantage in raw memory throughput.

Q: Which GPU has a higher transistor count?

A: The NVIDIA GTX 460M features 1,170 million transistors on a 238 mm² die, while the AMD Radeon R5 M230 has only 690 million transistors on a 56 mm² die. The NVIDIA part has roughly 70% more transistors, though the AMD part achieves a much higher transistor density of 12.3M / mm² versus 4.9M / mm².

Q: What are the API support differences?

A: Both support DirectX 12, but the Radeon R5 M230 implements the 11_1 feature level while the GTX 460M implements the 11_0 feature level. Both support OpenGL 4.6, but only the AMD part supports Vulkan (version 1.2.170); the NVIDIA part has no Vulkan support listed.

Q: Which GPU has a higher pixel fill rate?

A: The NVIDIA GTX 460M achieves 5.400 GPixel/s, which is 10.7% higher than the Radeon R5 M230’s 4.880 GPixel/s. However, the AMD part still wins the overall benchmark due to other architectural factors.

Architecture Differences

The two GPUs are built on fundamentally different architectures. The AMD Radeon R5 M230 uses the GCN 1.0 architecture on a 28 nm process node from TSMC, while the NVIDIA GeForce GTX 460M uses the Fermi architecture on a 40 nm process node, also from TSMC. The manufacturing process difference is significant: the 28 nm node allows for a much smaller die size of 56 mm², whereas the 40 nm Fermi chip occupies 238 mm². Despite having fewer transistors (690 million versus 1,170 million), the AMD part achieves a transistor density of 12.3M / mm²—roughly 2.5x higher than the NVIDIA part’s 4.9M / mm².

The shader configuration differs substantially in structure. The Radeon R5 M230 has 320 shading units, 20 TMUs, and 8 ROPs. The GTX 460M has 192 shading units, 32 TMUs, and 24 ROPs. This means the AMD part relies on a larger number of parallel shaders, while the NVIDIA part has more texture mapping units and raster output units. The GTX 460M’s higher ROP count directly contributes to its higher pixel rate of 5.400 GPixel/s, while its TMU count drives a texture rate of 21.60 GTexel/s. The Radeon R5 M230 achieves only 12.20 GTexel/s and 4.880 GPixel/s, showing a clear deficit in these fixed-function units.

Memory architecture is another major divergence. The Radeon R5 M230 pairs 2 GB of DDR3 memory with a 64-bit bus, yielding 16.00 GB/s bandwidth. The GTX 460M uses 1536 MB of GDDR5 memory on a 192-bit bus, delivering 60.00 GB/s—a 3.75x bandwidth advantage. This is a critical difference, as the GTX 460M’s memory subsystem is far more capable of feeding its compute units with data. The bus interface also differs: the AMD part uses PCIe 3.0 x8, while the NVIDIA part uses PCIe 2.0 x16.

The Radeon R5 M230 is designated as an IGP (integrated graphics processor) with a slot width of "IGP," whereas the GTX 460M is an MXM Module. This reflects their intended deployment: the AMD part is designed for integration into a system-on-chip or low-power platform, while the NVIDIA part is a discrete mobile module. The GTX 460M has a listed TDP of 50 W and uses no power connectors, while the Radeon R5 M230 has no TDP listed in the data.

Head-to-Head Benchmarks

The only head-to-head benchmark available is Geekbench OpenCL, and the results show the AMD Radeon R5 M230 winning by a 6.9% margin. The AMD part scores 4577, while the NVIDIA GTX 460M scores 4282. This is a decisive win for the newer architecture, though the margin is modest in absolute terms—a difference of 295 points.

The performance delta is interesting when viewed through the lens of each GPU’s nearest rivals. The Radeon R5 M230’s score of 4577 places it just 0.2% above the AMD Radeon RX 560 (4569) and 0.4% above the Intel HD Graphics P530 (4560). It trails the NVIDIA Quadro M3000M (4621) by 0.9% and the NVIDIA GeForce GTX 970M (4628) by 1.1%. This indicates that the R5 M230 is performing in a tight cluster of mid-range parts, despite being an entry-level IGP.

The GTX 460M’s score of 4282 places it 0.3% behind the AMD Radeon Vega 3 (4268) and 0.3% behind the AMD FirePro W2100 (4295), while being 1.0% ahead of the NVIDIA Quadro K3000M (4241). Notably, it is 1.2% behind the NVIDIA GeForce RTX 4070 GDDR6 (4335)—a strange comparison that highlights the wide variance in OpenCL scores across vastly different hardware generations.

The 6.9% win for the Radeon R5 M230 is not explained by raw compute throughput. The GTX 460M has higher FP32 performance at 518.4 GFLOPS versus 390.4 GFLOPS for the AMD part—a 32.8% advantage. The NVIDIA part also has higher texture and pixel rates. Yet the AMD part still wins the benchmark, suggesting that its GCN architecture is more efficient at executing the OpenCL workload, or that the GDDR5 memory advantage of the GTX 460M does not translate into better benchmark results in this specific test.

Specification Differences

The specification tables reveal several key differences between the two GPUs. The process node differs: the Radeon R5 M230 is built on 28 nm, while the GTX 460M uses 40 nm. Transistor counts are 690 million and 1,170 million, respectively. Die sizes are 56 mm² and 238 mm². The Radeon R5 M230 has a transistor density of 12.3M / mm², while the GTX 460M has 4.9M / mm².

Memory specifications diverge sharply. The Radeon R5 M230 has 2 GB of DDR3 with a 64-bit bus and 16.00 GB/s bandwidth. The GTX 460M has 1536 MB of GDDR5 with a 192-bit bus and 60.00 GB/s bandwidth. Memory clock speeds are listed as 1000 MHz (2 Gbps effective) for the AMD part and 625 MHz (2.5 Gbps effective) for the NVIDIA part.

Compute unit counts differ: the Radeon R5 M230 has 320 shading units, 20 TMUs, and 8 ROPs, while the GTX 460M has 192 shading units, 32 TMUs, and 24 ROPs. Pixel rates are 4.880 GPixel/s versus 5.400 GPixel/s, and texture rates are 12.20 GTexel/s versus 21.60 GTexel/s. FP32 performance is 390.4 GFLOPS for the AMD part and 518.4 GFLOPS for the NVIDIA part.

The GTX 460M has a listed TDP of 50 W, while the Radeon R5 M230 has no TDP listed. Slot widths differ: IGP for the AMD part and MXM Module for the NVIDIA part. Power connectors are listed as "None" for the GTX 460M and absent for the Radeon R5 M230. Bus interfaces are PCIe 3.0 x8 for the AMD part and PCIe 2.0 x16 for the NVIDIA part.

API support differs in DirectX feature level and Vulkan: the Radeon R5 M230 supports DirectX 12 (11_1) and Vulkan 1.2.170, while the GTX 460M supports DirectX 12 (11_0) and no Vulkan. Both support OpenGL 4.6. Release dates are 2014-01-06 for the AMD part and 2010-09-02 for the NVIDIA part. The AMD part’s generation is "Gem System (R5 M200)" with predecessor "Solar System" and successor "Polaris Mobile." The NVIDIA part’s generation is "GeForce 400M" with predecessor "GeForce 300M" and successor "GeForce 500M."

The Verdict

The benchmark data clearly favors the AMD Radeon R5 M230. It wins the only head-to-head test by 6.9%, despite having substantially lower theoretical compute throughput (390.4 GFLOPS versus 518.4 GFLOPS) and far less memory bandwidth (16.00 GB/s versus 60.00 GB/s). This indicates that the GCN 1.0 architecture on 28 nm is significantly more efficient per FLOP than the Fermi architecture on 40 nm. The Radeon R5 M230 also supports Vulkan, a modern API that the GTX 460M lacks entirely, making it the more future-proof option for applications that leverage Vulkan.

The NVIDIA GeForce GTX 460M retains advantages in specific areas. Its memory subsystem is far superior, with GDDR5 memory on a 192-bit bus delivering 60.00 GB/s—a 3.75x bandwidth advantage over the Radeon R5 M230. It also has higher pixel and texture rates, with 5.400 GPixel/s and 21.60 GTexel/s respectively. For workloads that are heavily dependent on texture fetching or raster operations, the GTX 460M may perform better, even though the overall OpenCL score does not reflect this.

For users prioritizing raw compute performance in OpenCL applications, the Radeon R5 M230 is the clear choice based on the benchmark data. Its higher percentile ranking (27th versus 25th) and its position among rivals—sitting within 1.1% of the GTX 970M and Quadro M3000M—demonstrate that it punches above its weight class. The GTX 460M, by contrast, sits in a lower performance tier, closer to the Radeon Vega 3 and FirePro W2100.

The decision ultimately hinges on the target workload. For modern API support and better OpenCL performance, the Radeon R5 M230 is the superior part. For legacy applications that may benefit from higher memory bandwidth and texture throughput, the GTX 460M offers specific strengths, though its lack of Vulkan support and older architecture make it a less versatile option. The data shows a narrow but decisive win for the AMD part in the benchmark that matters.