AMD Radeon RX 7700 vs NVIDIA GeForce GTX 965M Comparison

Head-to-Head Benchmarks

The benchmark data paints an extremely lopsided picture. The AMD Radeon RX 7700 and the NVIDIA GeForce GTX 965M share only one common benchmark result in the database: Geekbench OpenCL. In that test, the RX 7700 scores 106,028 points, while the GTX 965M scores 14,509 points. That is a 630.8% difference in favor of the AMD card. To put that in perspective, the RX 7700 delivers more than seven times the raw compute performance of the older NVIDIA part in this specific workload.

Looking at the overall average benchmark scores reinforces the gap. The RX 7700 averages 15,852 points across all of its tested workloads, while the GTX 965M averages 14,404 points. While the raw numbers might seem close, the context matters: the RX 7700’s average is pulled down by a very low Passmark DirectX 10 score of 92, while the GTX 965M only has two Geekbench results to its name. The RX 7700’s strongest result is a Passmark G3D score of 20,974, a figure that the GTX 965M does not even have a comparable data point for. The RX 7700 also posts a Passmark GPU Compute score of 10,963, which is substantial for compute-heavy tasks.

The GTX 965M’s best benchmark result is its Geekbench Vulkan score of 14,299, which is still over 13% lower than the RX 7700’s OpenCL score in absolute terms. There are no head-to-head DirectX or Vulkan gaming benchmarks available for both cards, so the OpenCL result is the only direct comparison. The data shows a clear, unambiguous winner in every measurable category. The RX 7700 wins the single shared benchmark by a landslide, and its additional benchmark results demonstrate far higher peak performance in DirectX 11, DirectX 12, and compute workloads.

Architecture Differences

The architectural divide between these two GPUs is vast, representing nearly a decade of silicon evolution. The AMD Radeon RX 7700 is built on the Navi 32 chip using the RDNA 3.0 architecture, fabricated on a 5 nm process at TSMC. It packs 28,100 million transistors into a 346 mm² die, yielding a transistor density of 81.2 million per mm². In contrast, the NVIDIA GeForce GTX 965M uses the GM204 chip with the Maxwell 2.0 architecture, built on an older 28 nm process, also at TSMC. It contains 5,200 million transistors on a larger 398 mm² die, resulting in a much lower density of 13.1 million per mm².

Clock speeds tell a similar story. The RX 7700 has a base clock of 1900 MHz, a game clock of 2041 MHz, and a boost clock of 2459 MHz. The GTX 965M operates at a base clock of 924 MHz and a boost clock of just 950 MHz. That means the RX 7700’s base clock is more than double the GTX 965M’s boost clock. Memory technology also differs completely: the RX 7700 uses 16 GB of GDDR6 memory on a 256-bit bus, delivering 624.1 GB/s of bandwidth, while the GTX 965M uses 2 GB of GDDR5 on a 128-bit bus, providing only 80.19 GB/s. The memory bandwidth difference is roughly 7.8x in favor of the AMD card.

The compute resources are equally disparate. The RX 7700 has 2560 shading units, 160 texture mapping units, and 96 raster operation pipelines. The GTX 965M has 1024 shading units, 64 TMUs, and 32 ROPs. The RX 7700 also features 40 dedicated ray tracing cores, a feature entirely absent from the GTX 965M, which has no ray tracing hardware. Pixel and texture rates reflect the hardware gap: the RX 7700 achieves 236.1 GPixel/s and 393.4 GTexel/s, whereas the GTX 965M manages 30.40 GPixel/s and 60.80 GTexel/s. FP32 throughput is 25.18 TFLOPS for the AMD card versus 1.946 TFLOPS for the NVIDIA card.

The Verdict

The data is unambiguous: the AMD Radeon RX 7700 is in a completely different performance class than the NVIDIA GeForce GTX 965M. The RX 7700 wins the only shared benchmark by 630.8%, and its overall average score, despite being dragged down by one anomalous low Passmark result, is still 10.1% higher than the GTX 965M’s average. The RX 7700 also holds a 58th percentile ranking among all GPUs, compared to the GTX 965M’s 56th percentile, but that percentile gap undersells the actual performance difference because the GTX 965M’s percentile is based on far fewer benchmark results.

The GTX 965M’s nearest rivals are integrated and older discrete graphics solutions like the AMD Radeon RX Vega 11, NVIDIA GeForce GTX TITAN, and Intel Iris Xe MAX Graphics, all of which sit within 0.6% of its average score. The RX 7700’s nearest rivals, by contrast, include the AMD Radeon RX 9060 and NVIDIA GeForce RTX 3060 Ti, with the RX 7700 sitting within 1.7% of those cards. That places the RX 7700 in the company of modern mainstream discrete GPUs, while the GTX 965M is stuck in the territory of entry-level and legacy parts.

For anyone choosing between these two, the decision is straightforward. The RX 7700 is an active production card with modern features, while the GTX 965M is end-of-life. The RX 7700 offers 16 GB of memory versus 2 GB, ray tracing support versus none, and a 5 nm process versus 28 nm. The GTX 965M’s only advantage is its MXM module form factor, which is portable-device dependent, and its lack of external power connectors. If you need a modern desktop GPU, the RX 7700 is the only logical choice. If you are constrained to a legacy laptop or portable device, the GTX 965M is what it is, but the data shows it is not competitive with even a fraction of the RX 7700’s capability.

FAQ

Q: Which GPU has higher memory bandwidth?

A: The AMD Radeon RX 7700 has a memory bandwidth of 624.1 GB/s, while the NVIDIA GeForce GTX 965M has a bandwidth of 80.19 GB/s. That is a 7.8x difference in favor of the RX 7700.

Q: Does the GTX 965M support ray tracing?

A: No. The GTX 965M has no ray tracing cores listed in its specifications. The RX 7700 includes 40 dedicated ray tracing cores.

Q: What is the process node difference?

A: The RX 7700 is fabricated on a 5 nm process at TSMC, while the GTX 965M uses a 28 nm process, also at TSMC. The newer node allows the RX 7700 to pack 81.2 million transistors per mm² versus 13.1 million per mm² for the GTX 965M.

Q: Which card has more shading units?

A: The RX 7700 has 2560 shading units, compared to 1024 on the GTX 965M. The RX 7700 also has 160 TMUs and 96 ROPs, versus 64 TMUs and 32 ROPs on the GTX 965M.

Q: Is the GTX 965M still in production?

A: No. The GTX 965M is marked as end-of-life in the data. The RX 7700 is marked as active production.

Q: What is the FP32 performance difference?

A: The RX 7700 delivers 25.18 TFLOPS of FP32 performance, while the GTX 965M delivers 1.946 TFLOPS. The RX 7700 is approximately 13x faster in raw FP32 throughput.

Where Each One Wins

The AMD Radeon RX 7700 wins in every benchmark category where both cards have data. In the sole head-to-head Geekbench OpenCL test, it is 630.8% faster. Its Passmark G3D score of 20,974 indicates strong DirectX gaming performance, while its Passmark GPU Compute score of 10,963 shows solid compute capability. The RX 7700 also supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it suitable for modern gaming and productivity workloads. Its 16 GB of GDDR6 memory and 256-bit bus are designed for high-resolution textures and large datasets.

The NVIDIA GeForce GTX 965M does not win any benchmark comparisons in the data. Its only strengths are qualitative: it is an MXM module, meaning it fits in portable devices, and it requires no external power connectors, drawing power from the host system. Its DirectX 12 (12_1) support and Vulkan 1.4 compatibility mean it can run modern APIs, but with significantly lower performance. If you are building a desktop, the GTX 965M is not a viable option because of its form factor. If you are repairing an older laptop, it may be the only available choice, but the data shows its performance is closer to integrated Vega graphics than to any modern discrete GPU.

Specification Differences

| Specification | AMD Radeon RX 7700 | NVIDIA GeForce GTX 965M |

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

| Architecture | RDNA 3.0 | Maxwell 2.0 |

| Process Node | 5 nm | 28 nm |

| Transistors | 28,100 million | 5,200 million |

| Die Size | 346 mm² | 398 mm² |

| Transistor Density | 81.2M / mm² | 13.1M / mm² |

| Base Clock | 1900 MHz | 924 MHz |

| Boost Clock | 2459 MHz | 950 MHz |

| Memory Size | 16 GB | 2 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 624.1 GB/s | 80.19 GB/s |

| Shading Units | 2560 | 1024 |

| TMUs | 160 | 64 |

| ROPs | 96 | 32 |

| Ray Tracing Cores | 40 | None |

| Pixel Rate | 236.1 GPixel/s | 30.40 GPixel/s |

| Texture Rate | 393.4 GTexel/s | 60.80 GTexel/s |

| FP32 Performance | 25.18 TFLOPS | 1.946 TFLOPS |

| Slot Width | Dual-slot | MXM Module |

| Power Connectors | 2x 8-pin | None |

| Bus Interface | PCIe 4.0 x16 | MXM-B (3.0) |

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

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

| Release Date | 2025-09-17 | 2015-01-08 |