AMD Radeon R7 M460 vs NVIDIA GeForce 945M Comparison

Head-to-Head Benchmarks

The only overlapping benchmark recorded in the database is Geekbench OpenCL, and the result is decisive. The NVIDIA GeForce 945M scores 8099 points, while the AMD Radeon R7 M460 scores 6612 points. That gives the GeForce 945M a 22.5% lead in raw compute performance. This is not a marginal gap; it is a full performance tier of separation. The R7 M460 would need a substantial clockspeed or architecture advantage to close that kind of deficit, and the data shows it does not have one.

Context from the nearest rivals makes the 945M's position clearer. The GeForce 945M sits between the NVIDIA GRID K2 (8080 points, 0.2% behind) and the AMD Radeon R9 M360 (8129 points, 0.4% ahead). It trades blows with the desktop-class GeForce GTX 650 Ti Boost (8067 points, 0.4% behind) and the GeForce GTX 950M (8135 points, 0.4% ahead). Essentially, the 945M is bracketed by much larger discrete GPUs, and it holds its own within 0.4% of all four nearest rivals. That is a tight cluster, and the 945M sits right in the middle of it.

The R7 M460, by contrast, lands in a lower performance neighborhood. Its nearest rival is the NVIDIA GeForce GTX 670M (6513 points), which the R7 M460 beats by 1.5%. It also edges out the AMD Radeon HD 7730M (6581 points, 0.5% ahead) and the Intel UHD Graphics P750 (6554 points, 0.9% ahead). The only rival that beats it is the NVIDIA GeForce GT 1010 (6698 points, 1.3% ahead). These are all older or lower-end parts, and the R7 M460 is competitive within that group. But the gap between the two GPUs being compared here is the headline: 22.5% in favor of the GeForce 945M.

Looking at the win tally, the GeForce 945M takes the single recorded head-to-head benchmark, and the R7 M460 has zero wins. The percentile data reinforces the same story. The GeForce 945M sits at the 42nd percentile of all GPUs in the database, while the R7 M460 sits at the 38th percentile. That four-percentile gap is modest, but it aligns with the benchmark delta. The 945M is not a high-end part by any means, but it is clearly a step above the R7 M460 in absolute compute throughput.

Architecture Differences

The two GPUs come from different architectural generations and different design philosophies. The GeForce 945M uses the GM107 chip, built on NVIDIA's Maxwell architecture. It is manufactured by TSMC on a 28 nm process, with 1,870 million transistors on a 148 mm² die. That works out to a transistor density of 12.6 million transistors per square millimeter. The R7 M460 uses the Meso chip, built on AMD's GCN 3.0 architecture. It is also manufactured by TSMC on 28 nm, but with 1,550 million transistors on a 125 mm² die, giving a density of 12.4 million transistors per square millimeter. The die sizes and transistor counts are similar, but the 945M packs roughly 20% more transistors into a 23 mm² larger die.

The compute resources differ significantly. The GeForce 945M has 640 shading units, 40 texture mapping units, and 16 raster operation pipelines. The R7 M460 has 384 shading units, 24 TMUs, and only 8 ROPs. That is a 66% advantage in shader count for the 945M, a 66% advantage in TMUs, and double the ROP count. These structural differences show up directly in the fillrate and throughput numbers. The 945M delivers 16.32 GPixel/s of pixel rate and 40.80 GTexel/s of texture rate. The R7 M460 manages 8.192 GPixel/s and 24.58 GTexel/s, which is roughly half the pixel throughput and about 60% of the texture throughput.

Clock speeds tell a more nuanced story. The GeForce 945M has a base clock of 928 MHz and a boost clock of 1020 MHz. The R7 M460 has a lower base clock of 730 MHz but a slightly higher boost clock of 1024 MHz. The R7 M460's boost advantage is only 4 MHz, which is negligible in real-world terms. The 945M's higher base clock is far more relevant, because sustained loads rarely hold maximum boost on thin-and-light laptop cooling. In practice, the 945M spends more time at higher clocks.

FP32 compute performance reflects the combined effect of shader count and clocks. The 945M delivers 1,305.6 GFLOPS, while the R7 M460 delivers 786.4 GFLOPS. That is a 66% advantage for the 945M. The R7 M460 does have FP16 capability at a 1:1 ratio (786.4 GFLOPS), but the 945M lists no FP16 figure in the database. For gaming and general compute workloads, FP32 is the relevant metric, and the 945M wins by a wide margin.

Memory architecture is another major point of divergence. The GeForce 945M pairs 2 GB of DDR3 on a 128-bit bus, yielding 28.80 GB/s of bandwidth. The R7 M460 pairs 2 GB of GDDR5 on a 64-bit bus, yielding 36.00 GB/s of bandwidth. Despite the narrower bus, the R7 M460 actually has 25% more memory bandwidth because GDDR5 operates at a much higher effective data rate. The 945M's memory runs at 900 MHz (1800 Mbps effective), while the R7 M460's memory runs at 1125 MHz (4.5 Gbps effective). For bandwidth-sensitive workloads, the R7 M460 has a real advantage, even though its compute throughput is far lower.

API support differs in one notable way. The GeForce 945M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The R7 M460 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The R7 M460 has a more complete DirectX 12 feature set with the 12_0 profile, while the 945M is limited to the 11_0 feature level. The 945M has a newer Vulkan version (1.4 vs 1.2.170). For modern titles that lean on DX12 features, the R7 M460 is better positioned; for Vulkan-based engines, the 945M has the newer runtime.

Where Each One Wins

The GeForce 945M wins in raw compute, pixel throughput, and texture throughput. Its 22.5% OpenCL advantage means it is the better choice for GPU-accelerated applications that scale with shader count and FP32 performance. The 1,305.6 GFLOPS of FP32 throughput, the 40.80 GTexel/s texture rate, and the 16.32 GPixel/s pixel rate all point in the same direction: the 945M is the stronger all-around performer for gaming at typical laptop resolutions. Its 640 shading units and 40 TMUs give it a structural advantage that clockspeed alone cannot overcome.

The R7 M460 wins in memory bandwidth and DirectX 12 feature level. Its 36.00 GB/s of bandwidth is 25% higher than the 945M's 28.80 GB/s, which matters for texture-heavy scenes and higher resolution work. Its DirectX 12 (12_0) support is more complete than the 945M's DirectX 12 (11_0). On paper, the R7 M460 is better equipped for titles that use the full DX12 feature set. The 1:1 FP16 ratio (786.4 GFLOPS) is also notable for compute workloads that can use half-precision math.

However, the benchmark data does not show any scenario where the R7 M460 beats the 945M. The only recorded head-to-head test, Geekbench OpenCL, goes to the 945M by 22.5%. The R7 M460's advantages are real but situational. The bandwidth edge helps in specific workloads, but the 945M's compute lead is so large that it likely dominates in most real applications.

FAQ

Q: Which GPU has the higher benchmark score?

A: The NVIDIA GeForce 945M scores 8099 in Geekbench OpenCL, while the AMD Radeon R7 M460 scores 6612. The 945M leads by 22.5%.

Q: How does the R7 M460 compare to its nearest rivals?

A: The R7 M460 beats the AMD Radeon HD 7730M (6581 points) by 0.5%, the Intel UHD Graphics P750 (6554 points) by 0.9%, and the NVIDIA GeForce GTX 670M (6513 points) by 1.5%. It trails the NVIDIA GeForce GT 1010 (6698 points) by 1.3%.

Q: Which GPU has more memory bandwidth?

A: The AMD Radeon R7 M460 has 36.00 GB/s of bandwidth from 2 GB of GDDR5 on a 64-bit bus. The NVIDIA GeForce 945M has 28.80 GB/s from 2 GB of DDR3 on a 128-bit bus.

Q: What are the shader counts for these GPUs?

A: The GeForce 945M has 640 shading units, while the R7 M460 has 384 shading units. The 945M also has 40 TMUs and 16 ROPs, compared to 24 TMUs and 8 ROPs on the R7 M460.

Q: How does the DirectX support differ?

A: The R7 M460 supports DirectX 12 (12_0), while the 945M supports DirectX 12 (11_0). The 945M has the newer Vulkan version at 1.4, compared to Vulkan 1.2.170 on the R7 M460.

Q: What is the performance percentile of each GPU?

A: The GeForce 945M sits at the 42nd percentile of all GPUs in the database. The R7 M460 sits at the 38th percentile.

The Verdict

The data points to a clear winner. The NVIDIA GeForce 945M outperforms the AMD Radeon R7 M460 by 22.5% in Geekbench OpenCL, holds a 42nd percentile ranking versus 38th, and wins the only recorded head-to-head benchmark. It has 66% more shading units, 66% more TMUs, double the ROPs, and nearly 66% more FP32 throughput. For anyone choosing between these two for gaming or general compute work, the 945M is the stronger part.

The R7 M460 is not without merit. Its GDDR5 memory delivers 36.00 GB/s of bandwidth, 25% more than the 945M's DDR3, and its DirectX 12 (12_0) support is more complete for modern titles. But the benchmark data shows no scenario where those advantages translate into a win. The 945M's compute lead is simply too large.

For users who prioritize raw performance, the GeForce 945M is the pick. For users who need the newer DX12 feature set or rely on memory-bandwidth-sensitive workloads, the R7 M460 has a narrow niche. But based strictly on the recorded measurements, the 945M is the faster GPU in nearly every meaningful way.

Specification Differences

| Specification | NVIDIA GeForce 945M | AMD Radeon R7 M460 |

|---|---|---|

| Architecture | Maxwell | GCN 3.0 |

| Process Node | 28 nm | 28 nm |

| Transistors | 1,870 million | 1,550 million |

| Die Size | 148 mm² | 125 mm² |

| Transistor Density | 12.6M / mm² | 12.4M / mm² |

| Base Clock | 928 MHz | 730 MHz |

| Boost Clock | 1020 MHz | 1024 MHz |

| Memory Size | 2 GB | 2 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 64 bit |

| Memory Bandwidth | 28.80 GB/s | 36.00 GB/s |

| Shading Units | 640 | 384 |

| TMUs | 40 | 24 |

| ROPs | 16 | 8 |

| Pixel Rate | 16.32 GPixel/s | 8.192 GPixel/s |

| Texture Rate | 40.80 GTexel/s | 24.58 GTexel/s |

| FP32 | 1,305.6 GFLOPS | 786.4 GFLOPS |

| FP16 | N/A | 786.4 GFLOPS (1:1) |

| TDP | 75 W | N/A |

| Bus Interface | MXM-B (3.0) | PCIe 3.0 x8 |

| DirectX | 12 (11_0) | 12 (12_0) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.2.170 |

| Release Date | 2015-10-26 | 2016-05-14 |

| Production Status | End-of-life | End-of-life |

| Predecessor | GeForce 800M | Solar System |

| Successor | GeForce 10 Mobile | Polaris Mobile |