AMD Radeon R9 M380 vs NVIDIA GeForce GTX 965M Comparison

The AMD Radeon R9 M380 and NVIDIA GeForce GTX 965M are both end-of-life mobile GPUs from 2015, but the benchmark data reveals a clear performance hierarchy. Based on aggregate scores, the GTX 965M holds a decisive edge, averaging 14,404 points compared to the R9 M380’s 15,521, which translates to a 7.2% advantage for the NVIDIA part. In the only direct head-to-head test available, the Geekbench OpenCL benchmark, the GTX 965M wins decisively, scoring 14,509 against the R9 M380’s 12,565—a 13.4% deficit for the AMD card. This data positions the GTX 965M as the stronger performer, while the R9 M380 sits closer to a different competitive tier.

The Verdict

The data indicates that the NVIDIA GeForce GTX 965M is the superior choice for users prioritizing raw compute performance. Its average benchmark score of 14,404 places it in the 56th percentile of all GPUs, while the AMD Radeon R9 M380, despite a higher average score of 15,521, sits in the 58th percentile. This seeming contradiction is resolved by examining the nearest rivals: the R9 M380’s average score is nearly identical to that of the NVIDIA GeForce GTX 1080 Ti (15,548, deltaPct -0.2%) and the AMD Radeon Pro W5500 (15,679, deltaPct -1%), suggesting its average is buoyed by a strong Metal benchmark result. Conversely, the GTX 965M’s average is closely matched with integrated graphics like the AMD Radeon RX Vega 11 (14,385, deltaPct 0.1%) and the NVIDIA GeForce GTX TITAN (14,373, deltaPct 0.2%), which reflects its more modest compute ceiling.

For the specific OpenCL workload, the verdict is unambiguous: the GTX 965M wins by a substantial margin. The 13.4% delta in its favor is not a marginal difference; it represents a significant performance gap in general-purpose compute tasks. Users who rely on OpenCL acceleration in applications like video editing, 3D rendering, or scientific computing should unequivocally choose the GTX 965M based on this data. The R9 M380, however, is not without merit; its Geekbench Metal score of 18,476 is substantially higher than its OpenCL score of 12,565, indicating that AMD’s architecture may be better optimized for Apple’s Metal API. For users in a Metal-centric environment, the R9 M380 could be the more sensible pick, despite its overall compute deficit.

The R9 M380’s 58th percentile ranking is higher than the GTX 965M’s 56th, but this is misleading. The R9 M380’s nearest rivals include high-end desktop cards like the GTX 1080 Ti, which suggests its average score is skewed by a single strong benchmark. The GTX 965M’s rivals are more modest, including integrated graphics, which places its performance in a more realistic context. Therefore, the verdict is that the GTX 965M is the better all-around performer, while the R9 M380 is a niche choice for Metal-specific workloads or for users who value its higher percentile ranking despite the OpenCL loss.

Architecture Differences

The two GPUs are built on fundamentally different architectures, which explains their divergent performance profiles. The AMD Radeon R9 M380 uses the Strato chip based on GCN 2.0, a mature design from AMD’s Graphics Core Next lineage, fabricated on a 28 nm process at TSMC. The GTX 965M employs the GM204 chip based on Maxwell 2.0, NVIDIA’s second-generation Maxwell architecture, also on a 28 nm TSMC process. Both chips share the same process node and foundry, but their internal designs diverge sharply.

The most striking difference is in transistor count and die size. The GTX 965M’s GM204 packs 5,200 million transistors on a 398 mm² die, while the R9 M380’s Strato contains only 2,080 million transistors on a 160 mm² die. This gives the NVIDIA chip a 2.5x transistor advantage and a 2.5x larger die area, despite having nearly identical transistor density (13.1M / mm² for NVIDIA vs 13.0M / mm² for AMD). This size disparity directly translates to more hardware resources: the GTX 965M has 1,024 shading units, 64 texture mapping units (TMUs), and 32 raster operation units (ROPs), while the R9 M380 has 768 shaders, 48 TMUs, and just 16 ROPs. The GTX 965M’s 33% more shaders and double the ROPs are critical to its performance lead.

Clock speeds tell a nuanced story. The R9 M380 has a base clock of 900 MHz and a boost clock of 1000 MHz, while the GTX 965M has a base clock of 924 MHz and a boost of 950 MHz. The AMD card’s boost clock is 50 MHz higher, but the NVIDIA card’s base clock is 24 MHz higher. The R9 M380’s higher boost clock does not compensate for its fewer execution units. Memory configurations also differ: both use GDDR5 with a 128-bit bus, but the R9 M380 has 4 GB of memory running at 1500 MHz (6 Gbps effective) for a bandwidth of 96.00 GB/s, while the GTX 965M has 2 GB at 1253 MHz (5 Gbps effective) for 80.19 GB/s. The AMD card has a 19.7% bandwidth advantage and double the VRAM capacity. The GTX 965M compensates with a higher pixel rate of 30.40 GPixel/s versus 16.00 GPixel/s and a texture rate of 60.80 GTexel/s versus 48.00 GTexel/s, leading to a 1.27x FP32 throughput advantage (1.946 TFLOPS vs 1.536 TFLOPS).

Head-to-Head Benchmarks

The only direct benchmark comparison in the data is Geekbench OpenCL, and it is a decisive win for the NVIDIA GeForce GTX 965M. The GTX 965M scores 14,509, while the AMD Radeon R9 M380 scores 12,565, resulting in a 13.4% delta favoring NVIDIA. This is a substantial gap that underscores the architectural efficiency of Maxwell 2.0 over GCN 2.0 in OpenCL workloads. The GTX 965M’s higher shading unit count (1,024 vs 768) and FP32 throughput (1.946 TFLOPS vs 1.536 TFLOPS) directly contribute to this result, allowing it to process more parallel threads per cycle.

The R9 M380’s higher memory bandwidth (96.00 GB/s vs 80.19 GB/s) and larger 4 GB frame buffer do not help it in this compute test, indicating that the bottleneck is raw shader throughput rather than memory access. The R9 M380’s 16 ROPs also limit its ability to handle compute tasks that require frequent memory writes, whereas the GTX 965M’s 32 ROPs provide double the rasterization throughput. This benchmark result is consistent with the overall average scores: the GTX 965M’s 14,404 average is only 0.7% lower than its OpenCL score, while the R9 M380’s 15,521 average is 23.5% higher than its OpenCL score, suggesting that the AMD card’s Metal benchmark (18,476) is its strong suit, not OpenCL.

The deltaPct of -13.4% for the R9 M380 in this single test is the largest performance gap observed in the entire dataset. For comparison, the R9 M380’s nearest rivals show much smaller deltas: -0.2% vs the GTX 1080 Ti, -1% vs the Radeon Pro W5500, +1.5% vs the RTX 2060, and +1.6% vs the GTX 580. This indicates that the R9 M380’s OpenCL performance is an outlier on the low end, while the GTX 965M’s OpenCL score of 14,509 is nearly identical to its average, placing it in a consistent performance band. The head-to-head data is clear: for OpenCL, the GTX 965M is superior by a wide margin.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon R9 M380 has a higher average benchmark score of 15,521, compared to the NVIDIA GeForce GTX 965M’s 14,404. This places the R9 M380 in the 58th percentile of all GPUs, versus the 56th percentile for the GTX 965M.

Q: How do the two GPUs compare in the Geekbench OpenCL test?

A: The NVIDIA GeForce GTX 965M wins decisively, scoring 14,509 against the AMD Radeon R9 M380’s 12,565. This is a 13.4% advantage for the NVIDIA card, which is the only direct head-to-head benchmark available.

Q: What is the memory capacity difference between the two cards?

A: The AMD Radeon R9 M380 has 4 GB of GDDR5 memory, while the NVIDIA GeForce GTX 965M has 2 GB of GDDR5 memory. The R9 M380 also has higher memory bandwidth at 96.00 GB/s versus 80.19 GB/s for the GTX 965M.

Q: Which GPU has more shading units and higher FP32 throughput?

A: The NVIDIA GeForce GTX 965M has 1,024 shading units and 1.946 TFLOPS of FP32 performance. The AMD Radeon R9 M380 has 768 shading units and 1.536 TFLOPS, giving the GTX 965M a 33% more shaders and a 26.7% higher FP32 throughput.

Q: What are the nearest rivals for each GPU based on average score?

A: The AMD Radeon R9 M380’s nearest rival is the NVIDIA GeForce GTX 1080 Ti (15,548, deltaPct -0.2%), followed by the AMD Radeon Pro W5500 (15,679, deltaPct -1%). The NVIDIA GeForce GTX 965M’s nearest rival is the AMD Radeon RX Vega 11 (14,385, deltaPct 0.1%), followed by the NVIDIA GeForce GTX TITAN (14,373, deltaPct 0.2%).

Q: Which GPU has a higher transistor density?

A: The NVIDIA GeForce GTX 965M has a slightly higher transistor density of 13.1M / mm², compared to the AMD Radeon R9 M380’s 13.0M / mm². Both are fabricated on a 28 nm TSMC process.

Where Each One Wins

Based strictly on the benchmark data, the NVIDIA GeForce GTX 965M wins in OpenCL compute performance, which is the primary metric for general-purpose GPU acceleration. Its 13.4% lead over the R9 M380 in the Geekbench OpenCL test is decisive, and its lower average score of 14,404 is still more consistent with its OpenCL result, indicating reliable performance across workloads. The GTX 965M also wins in theoretical throughput metrics: it has a 26.7% higher FP32 rate (1.946 TFLOPS vs 1.536 TFLOPS), a 90% higher pixel rate (30.40 GPixel/s vs 16.00 GPixel/s), and a 26.7% higher texture rate (60.80 GTexel/s vs 48.00 GTexel/s). These numbers suggest it is the better choice for gaming, rendering, and any task that relies on raw shading power.

The AMD Radeon R9 M380 wins in memory-related categories. It has double the VRAM capacity (4 GB vs 2 GB) and a 19.7% higher memory bandwidth (96.00 GB/s vs 80.19 GB/s). This could be an advantage in texture-heavy applications or at higher resolutions where the larger frame buffer reduces the need for memory swapping. Additionally, the R9 M380’s Geekbench Metal score of 18,476 is significantly higher than its OpenCL score, and while there is no direct Metal comparison with the GTX 965M, this suggests that AMD’s GCN 2.0 architecture is better optimized for Apple’s Metal API. For users in a Metal-centric ecosystem, the R9 M380 may offer superior performance, despite its OpenCL deficit.

The R9 M380 also wins on the basis of its higher average benchmark score (15,521 vs 14,404) and higher percentile ranking (58th vs 56th). However, this is misleading because its average is inflated by the strong Metal result, while the GTX 965M’s average is more balanced. In practical terms, the GTX 965M is the winner for most compute tasks, while the R9 M380 is the winner for memory-intensive workloads and Metal-specific applications. The data shows a clear split: NVIDIA for raw compute and gaming, AMD for memory capacity and Metal compatibility.

Specification Differences

The following table highlights only the fields where the two GPUs differ, based on the provided data:

| Specification | AMD Radeon R9 M380 | NVIDIA GeForce GTX 965M |

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

| Chip | Strato | GM204 |

| Architecture | GCN 2.0 | Maxwell 2.0 |

| Generation | Gem System (R9 M300) | GeForce 900M |

| Transistors | 2,080 million | 5,200 million |

| Die Size | 160 mm² | 398 mm² |

| Transistor Density | 13.0M / mm² | 13.1M / mm² |

| Base Clock | 900 MHz | 924 MHz |

| Boost Clock | 1000 MHz | 950 MHz |

| Memory Clock | 1500 MHz (6 Gbps effective) | 1253 MHz (5 Gbps effective) |

| Memory Size | 4 GB | 2 GB |

| Memory Bandwidth | 96.00 GB/s | 80.19 GB/s |

| Shading Units | 768 | 1024 |

| TMUs | 48 | 64 |

| ROPs | 16 | 32 |

| Pixel Rate | 16.00 GPixel/s | 30.40 GPixel/s |

| Texture Rate | 48.00 GTexel/s | 60.80 GTexel/s |

| FP32 | 1.536 TFLOPS | 1.946 TFLOPS |

| Slot Width | Not specified | MXM Module |

| Power Connectors | Not specified | None |

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

| Display Outputs | Not specified | Portable Device Dependent |

| DirectX | 12 (12_0) | 12 (12_1) |

| Vulkan | 1.2.170 | 1.4 |

| Release Date | 2015-05-04 | 2015-01-08 |

| Predecessor | Solar System | GeForce 800M |

| Successor | Polaris Mobile | GeForce 10 Mobile |

| Geekbench OpenCL | 12,565 | 14,509 |

| Geekbench Metal | 18,476 | Not available |

| Geekbench Vulkan | Not available | 14,299 |

| Average Benchmark Score | 15,521 | 14,404 |

| Percentile vs All GPUs | 58 | 56 |

The GTX 965M is clearly the larger and more complex chip, with 2.5x more transistors and a 2.5x larger die, which enables its higher core counts and throughput. The R9 M380 counters with higher clocks (1000 MHz boost vs 950 MHz), more memory (4 GB vs 2 GB), and higher bandwidth (96.00 GB/s vs 80.19 GB/s). The NVIDIA card supports DirectX 12_1 and Vulkan 1.4, while the AMD card supports DirectX 12_0 and Vulkan 1.2.170. The GTX 965M also has a Vulkan benchmark score of 14,299, which is absent for the R9 M380, and the R9 M380 has a Metal score of 18,476, which is absent for the GTX 965M.