AMD Radeon 760M vs NVIDIA GeForce GTX 460 SE Comparison

NVIDIA GeForce GTX 460 SE and AMD Radeon 760M represent two distant eras of GPU design, one a discrete add-in board from 2010 and the other a modern integrated processor. Their benchmark data shows a clear generational gap, but the older card still holds a narrow edge in overall percentile ranking despite being vastly outscored in raw compute tests.

Architecture Differences

The architectural divide between these two GPUs is enormous. The GTX 460 SE is built on NVIDIA’s Fermi architecture using the GF104 chip, manufactured on a 40 nm process at TSMC. It packs 1,950 million transistors into a 332 mm² die, yielding a transistor density of 5.9 million per square millimeter. The Radeon 760M, by contrast, uses AMD’s RDNA 3.0 architecture with the Phoenix chip, also fabricated by TSMC but on a 4 nm node. This modern process allows 25,390 million transistors in a much smaller 178 mm² die, achieving 142.6 million transistors per square millimeter — roughly 24 times the density of the older Fermi part.

Core configuration differs fundamentally as well. The GTX 460 SE contains 288 shading units, 48 texture mapping units, and 32 ROPs. The Radeon 760M has 512 shading units, 32 TMUs, and only 16 ROPs. Notably, the Radeon also includes 8 ray tracing cores, a feature entirely absent from the Fermi architecture. The NVIDIA card’s FP32 throughput is 748.8 GFLOPS, while the AMD part reaches 5.323 TFLOPS — a sevenfold advantage. The Radeon additionally supports FP16 at 5.323 TFLOPS with 1:1 ratio, whereas the GTX 460 SE has no FP16 capability listed.

Memory systems could not be more different. The GTX 460 SE uses 1024 MB of dedicated GDDR5 across a 256-bit bus, delivering 108.8 GB/s bandwidth. The Radeon 760M relies on System Shared memory, with bus width and bandwidth listed as System Shared and System Dependent, respectively. Clock behavior also contrasts sharply: the GTX 460 SE runs its memory at 850 MHz (3.4 Gbps effective) with no listed base or boost clock, while the Radeon has a base clock of 800 MHz and boost up to 2599 MHz.

API support marks another generational leap. The GTX 460 SE supports DirectX 12 (11_0) and OpenGL 4.6, with no Vulkan support. The Radeon 760M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Power requirements diverge wildly: the NVIDIA card draws 150 W and needs a dual-slot cooler with 2x 6-pin power connectors plus a 450 W suggested PSU, while the Radeon is an IGP drawing just 15 W with no power connectors and no suggested PSU.

Where Each One Wins

Based on the benchmark data, the AMD Radeon 760M wins decisively in raw compute workloads. Its Geekbench OpenCL score of 20,255 is more than three times the GTX 460 SE’s 6,389. This suggests the Radeon is far better suited for general-purpose GPU compute, OpenCL-based applications, and any workload that can leverage its higher shading unit count and much higher clock speeds.

The NVIDIA GeForce GTX 460 SE, however, holds a slight edge in overall percentile ranking. It sits at the 37th percentile of all GPUs, while the Radeon 760M sits at the 35th percentile. This means that despite losing the single head-to-head benchmark, the older card ranks marginally higher across the full spectrum of GPUs in the database. This could reflect broader compatibility or the fact that the GTX 460 SE’s dedicated memory and higher ROP count keep it competitive in certain legacy or memory-bandwidth-sensitive scenarios that are not captured in the single direct comparison.

The Radeon 760M also has a much richer benchmark profile, with results across 3DMark Steel Nomad DX12 (400), Geekbench Vulkan (30,336), and multiple Passmark tests (DirectX 10: 19, DirectX 11: 52, DirectX 12: 25, DirectX 9: 65, G2D: 890, G3D: 5,310, GPU Compute: 2,840). The GTX 460 SE has only a single Geekbench OpenCL result. The Radeon’s Vulkan support and modern API compliance make it the obvious choice for any current software stack.

Head-to-Head Benchmarks

The only direct comparison available is Geekbench OpenCL, and it is not close. The AMD Radeon 760M scores 20,255 against the NVIDIA GeForce GTX 460 SE’s 6,389, a delta of −68.5% from the perspective of the NVIDIA card. This means the Radeon outperforms the GTX 460 SE by roughly 217% in this test.

Interpreting this number requires context from the nearest rivals. The GTX 460 SE’s average benchmark score is 6,389, identical to the Geekbench OpenCL result, placing it alongside the NVIDIA GeForce GTX 580M (6,389, 0% delta) and just ahead of the AMD Radeon Pro WX 4100 (6,330, +0.9% delta) and AMD Radeon R7 M350 (6,327, +1% delta). It trails the NVIDIA RTX PRO 5000 72 GB Blackwell (6,407) by only 0.3%. The Radeon 760M’s average score of 6,019 is lower than its OpenCL result, dragged down by the Passmark tests. Its nearest rivals include the AMD Radeon RX 6400 (6,001, +0.3% delta), NVIDIA GeForce GTX 770M (6,000, +0.3% delta), and NVIDIA RTX PRO 6000 Blackwell Server (5,996, +0.4% delta), while it sits 0.5% behind the NVIDIA Quadro P2000 (6,049).

The discrepancy between the Radeon’s strong OpenCL score and its lower average underscores that OpenCL is not representative of its overall performance profile. The GTX 460 SE, with only one benchmark, presents a more uniform picture. The 3DMark Steel Nomad DX12 score of 400 for the Radeon and the Passmark DirectX scores (all below 65) indicate that synthetic gaming workloads show far less impressive results, aligning with its 35th percentile overall ranking.

FAQ

Q: Which GPU has more shading units?

A: The AMD Radeon 760M has 512 shading units, significantly more than the NVIDIA GeForce GTX 460 SE’s 288.

Q: What is the memory configuration difference?

A: The GTX 460 SE uses 1024 MB of dedicated GDDR5 with a 256-bit bus and 108.8 GB/s bandwidth. The Radeon 760M uses System Shared memory with bandwidth listed as System Dependent.

Q: Does the Radeon 760M support ray tracing?

A: Yes, the AMD Radeon 760M includes 8 ray tracing cores, a feature the NVIDIA GeForce GTX 460 SE does not have.

Q: How do they compare in OpenCL performance?

A: The Radeon 760M scores 20,255 in Geekbench OpenCL versus 6,389 for the GTX 460 SE, giving the AMD part a 217% advantage in that specific test.

Q: Which card ranks higher overall in the GPU database?

A: The NVIDIA GeForce GTX 460 SE ranks at the 37th percentile of all GPUs, while the AMD Radeon 760M ranks at the 35th percentile.

Q: What is the power draw difference?

A: The GTX 460 SE has a 150 W TDP and requires dual-slot cooling with 2x 6-pin power connectors. The Radeon 760M has a 15 W TDP, uses no power connectors, and is an IGP.

The Verdict

The data points to a straightforward conclusion for most users: the AMD Radeon 760M is the stronger compute performer. Its OpenCL score of 20,255 versus 6,389, combined with 512 shading units, 5.323 TFLOPS FP32, and modern API support including Vulkan 1.4 and DirectX 12 Ultimate, makes it the practical choice for anyone running current applications. The 15 W power envelope and IGP form factor also mean it can be integrated into a system without dedicated power connectors or a discrete slot.

However, the NVIDIA GeForce GTX 460 SE should not be dismissed outright. Its 37th percentile ranking edges out the Radeon’s 35th, and its nearest rivals include the GeForce GTX 580M at equal score and the RTX PRO 5000 72 GB Blackwell within 0.3%. The dedicated 108.8 GB/s GDDR5 bandwidth and higher ROP count (32 versus 16) may give it an advantage in certain legacy workloads or memory-bound scenarios. The GTX 460 SE also has a launch MSRP of 160 USD; the Radeon 760M has no listed launch MSRP.

For compute-heavy tasks, modern gaming, or anything requiring ray tracing or Vulkan, the Radeon 760M is the clear pick. For users constrained to older software stacks or seeking a card that holds a marginally better overall percentile position, the GTX 460 SE remains competitive despite its age. The production status reinforces this split: the GTX 460 SE is end-of-life, while the Radeon 760M is active.

Specification Differences

| Specification | NVIDIA GeForce GTX 460 SE | AMD Radeon 760M |

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

| Architecture | Fermi | RDNA 3.0 |

| Chip | GF104 | Phoenix |

| Process Node | 40 nm | 4 nm |

| Transistors | 1,950 million | 25,390 million |

| Die Size | 332 mm² | 178 mm² |

| Transistor Density | 5.9M / mm² | 142.6M / mm² |

| Shading Units | 288 | 512 |

| TMUs | 48 | 32 |

| ROPs | 32 | 16 |

| RT Cores | None | 8 |

| FP32 | 748.8 GFLOPS | 5.323 TFLOPS |

| FP16 | None | 5.323 TFLOPS (1:1) |

| TDP | 150 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 2x 6-pin | None |

| Suggested PSU | 450 W | None |

| Bus Interface | PCIe 2.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 2x DVI, 1x mini-HDMI 1.3a | Motherboard Dependent |

| DirectX | 12 (11_0) | 12 Ultimate (12_2) |

| Vulkan | None | 1.4 |

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

| Release Date | 2010-11-14 | 2024-01-30 |

| Launch MSRP | 160 USD | None |