AMD Radeon 760M vs NVIDIA GeForce MX230 Comparison

The GeForce MX230 and Radeon 760M are both integrated-style GPUs, but they represent vastly different eras of mobile computing. The MX230 is a legacy Pascal part from 2019, while the 760M is a modern RDNA 3.0 IGP from 2024. The data is unequivocal: the Radeon 760M dominates in every benchmark where they overlap, delivering roughly 3.5x the OpenCL performance and nearly 5x the Vulkan performance. However, the MX230 is a 10W part compared to the 760M's 15W TDP, and it uses dedicated GDDR5 memory, which can be advantageous in systems where shared system memory is a bottleneck. Choose the 760M for any serious gaming or compute workload; the MX230 only makes sense in the most power-constrained legacy systems where its dedicated VRAM and lower power draw are critical.

The Verdict

The benchmark data is stark. In the two head-to-head tests available, the AMD Radeon 760M wins decisively. The 760M scores 20,255 in Geekbench OpenCL, a 71.7% lead over the MX230's 5,739. In Geekbench Vulkan, the gap widens further: the 760M scores 30,336 versus the MX230's 6,414, a 78.9% advantage. When the average benchmark scores are compared, the 760M's 6,019 is just 1% higher than the MX230's 6,077, but this average is skewed by the MX230 having no results for the 3DMark or Passmark tests where the 760M shows its range. The 760M is the clear performance winner.

Who should pick the GeForce MX230? Only someone building or upgrading a system that absolutely requires a 10W TDP and has no room for the 760M's 15W draw. The MX230's dedicated 2GB of GDDR5 memory over a 64-bit bus provides 48.06 GB/s of bandwidth, which is not dependent on system RAM. For a very specific, low-power embedded or legacy application, this could be a deciding factor. The data shows the MX230 is end-of-life, so it is a legacy choice.

Who should pick the Radeon 760M? Anyone else. The 760M is an active product with a modern feature set. It offers 512 shading units, 8 ray tracing cores, and supports DirectX 12 Ultimate, while the MX230 is limited to DirectX 12 (12_1). For gaming, general compute, or anything beyond basic desktop acceleration, the 760M is the only rational choice from this data. Its 5.323 TFLOPS of FP32 performance is an order of magnitude higher than the MX230's 783.9 GFLOPS.

Architecture Differences

The architectural gap between these two GPUs is a generational leap. The MX230 is built on NVIDIA's Pascal architecture, fabricated on a 14nm process at Samsung. It uses the GP108 chip, which packs 1,800 million transistors into a 74 mm² die, yielding a transistor density of 24.3M per mm². In contrast, the Radeon 760M uses AMD's RDNA 3.0 architecture, built on a 4nm process at TSMC. The Phoenix chip contains 25,390 million transistors on a 178 mm² die, for a density of 142.6M per mm². This process advantage is a primary reason for the performance disparity.

The compute resources differ significantly. The MX230 has 256 shading units, 16 TMUs, and 16 ROPs. The 760M doubles the shading units to 512 and also has 32 TMUs, while keeping 16 ROPs. The 760M also features 8 dedicated ray tracing cores, a feature entirely absent from the Pascal-based MX230. The clock behavior is also different: the MX230 has a narrow boost range (1,519 MHz base to 1,531 MHz boost), while the 760M ramps from a low 800 MHz base to a very high 2,599 MHz boost. This suggests the 760M is designed for aggressive power scaling.

Memory architecture is a fundamental divergence. The MX230 has 2GB of dedicated GDDR5 memory on a 64-bit bus, delivering 48.06 GB/s of fixed bandwidth. The 760M uses System Shared memory, meaning its bandwidth and capacity are entirely dependent on the host system's RAM configuration. This is a double-edged sword: the 760M can access far more than 2GB, but its performance is tied to system memory speed and availability.

Head-to-Head Benchmarks

The two overlapping benchmarks tell a story of total AMD dominance. In Geekbench OpenCL, the MX230 scores 5,739 while the Radeon 760M scores 20,255. That is a 71.7% deficit for the NVIDIA part. The 760M is not just faster; it is in a different performance class. This delta is consistent with the raw specs: the 760M's 5.323 TFLOPS FP32 rate is nearly 7x the MX230's 783.9 GFLOPS.

The Geekbench Vulkan result is even more lopsided. The MX230 scores 6,414, but the 760M posts 30,336, a 78.9% advantage. Vulkan is a low-level API that often scales well with raw compute and shading resources, which explains why the 760M's 512 shading units and higher clocks translate into such a massive lead. The MX230's older Pascal architecture was not designed for modern low-level API workloads.

Looking at the broader benchmark suite for the 760M, it shows strengths across different APIs. It scores 5,310 in Passmark G3D, 2,840 in Passmark GPU Compute, and 890 in Passmark G2D. It also handles legacy APIs well, with scores of 65 in Passmark DirectX 9 and 52 in DirectX 11. The 3DMark Steel Nomad DX12 test yields a score of 400. The MX230 has no comparable results in these tests within the FACT PACK, so a direct comparison is impossible, but the available data consistently points to the 760M being the superior part.

FAQ

Q: Which GPU has better raw compute performance?

A: The Radeon 760M is overwhelmingly faster. It scores 20,255 in Geekbench OpenCL versus the MX230's 5,739, a 71.7% difference. Its FP32 throughput is 5.323 TFLOPS versus 783.9 GFLOPS.

Q: Does the MX230 have any advantage in memory?

A: Yes. The MX230 has dedicated 2GB GDDR5 memory with 48.06 GB/s bandwidth over a 64-bit bus. The 760M relies on System Shared memory, so its bandwidth is System Dependent. For workloads that require predictable, dedicated VRAM, the MX230's setup is unique.

Q: Is the Radeon 760M better for modern gaming APIs?

A: Yes. The 760M supports DirectX 12 Ultimate (12_2) and has 8 ray tracing cores. The MX230 only supports DirectX 12 (12_1) and has no ray tracing hardware. The Vulkan benchmark also shows the 760M's advantage, scoring 30,336 versus 6,414.

Q: Which GPU is more power efficient per frame?

A: The data does not provide a per-frame wattage measurement. However, the MX230 has a 10W TDP while the 760M has a 15W TDP. While the 760M uses 50% more power, it delivers approximately 3.5x the OpenCL performance, suggesting far better performance per watt.

Q: What is the production status of each GPU?

A: The NVIDIA GeForce MX230 is End-of-life, having been released in February 2019. The AMD Radeon 760M is Active and was released in January 2024, with a predecessor listed as Navi II IGP.

Q: Do both GPUs support the same level of PCIe connectivity?

A: No. The MX230 uses PCIe 3.0 x4, while the 760M uses PCIe 4.0 x8. The newer PCIe 4.0 standard with double the lanes gives the 760M significantly more bandwidth to the host system, which is critical for its shared memory architecture.

Where Each One Wins

The Radeon 760M wins in every measurable performance category. For gaming, the 760M's 512 shading units, 8 ray tracing cores, and DirectX 12 Ultimate support make it the only viable option for modern titles. Its Vulkan score of 30,336 is nearly 5x that of the MX230, indicating a massive advantage in low-level API games. The compute landscape is similar: 20,255 OpenCL points versus 5,739 means the 760M is the clear choice for GPGPU tasks like video encoding or machine learning inference. The 760M's 5.323 TFLOPS FP32 rate is in a different league entirely.

The GeForce MX230 has a narrow, specific niche. Its 10W TDP is 33% lower than the 760M's 15W, which can be critical in passively cooled systems or ultra-portable designs. More importantly, its dedicated 2GB GDDR5 memory is a system-independent resource. In a system with slow or insufficient RAM, the MX230's fixed 48.06 GB/s bandwidth will not be affected, whereas the 760M's performance could degrade. The MX230 is also a simpler part: no ray tracing cores, no shared memory complexities, just a basic Pascal GPU that works. For a legacy industrial PC or a specific embedded application where software is written for Pascal and power is at a premium, the MX230 remains a functional, if obsolete, choice.

Specification Differences

The following table highlights only the fields where the two GPUs differ according to the FACT PACK.

| Specification | NVIDIA GeForce MX230 | AMD Radeon 760M |

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

| Chip | GP108 | Phoenix |

| Architecture | Pascal | RDNA 3.0 |

| Generation | GeForce MX (2xx) | Navi III IGP (Phoenix) |

| Process Node | 14 nm | 4 nm |

| Foundry | Samsung | TSMC |

| Transistors | 1,800 million | 25,390 million |

| Die Size | 74 mm² | 178 mm² |

| Transistor Density | 24.3M / mm² | 142.6M / mm² |

| Base Clock | 1519 MHz | 800 MHz |

| Boost Clock | 1531 MHz | 2599 MHz |

| Memory Clock | 1502 MHz (6 Gbps effective) | System Shared |

| Memory Size | 2 GB | System Shared |

| Memory Type | GDDR5 | System Shared |

| Memory Bus Width | 64 bit | System Shared |

| Memory Bandwidth | 48.06 GB/s | System Dependent |

| Shading Units | 256 | 512 |

| TMUs | 16 | 32 |

| RT Cores | None | 8 |

| Pixel Rate | 24.50 GPixel/s | 41.58 GPixel/s |

| Texture Rate | 24.50 GTexel/s | 83.17 GTexel/s |

| FP32 Performance | 783.9 GFLOPS | 5.323 TFLOPS |

| FP16 Performance | 12.25 GFLOPS (1:64) | 5.323 TFLOPS (1:1) |

| TDP | 10 W | 15 W |

| Bus Interface | PCIe 3.0 x4 | PCIe 4.0 x8 |

| Display Outputs | Portable Device Dependent | Motherboard Dependent |

| DirectX Support | 12 (12_1) | 12 Ultimate (12_2) |

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

| Release Date | 2019-02-20 | 2024-01-30 |

| Predecessor | None | Navi II IGP |