AMD Radeon RX Vega 11 vs NVIDIA GeForce GTX 965M Comparison

The NVIDIA GeForce GTX 965M and AMD Radeon RX Vega 11 occupy the same percentile rank (56th) among all GPUs, yet they achieve that standing through different performance profiles. The GTX 965M, a mobile discrete part from 2015, and the RX Vega 11, a 2019 integrated graphics processor, post nearly identical average benchmark scores: 14,404 for the NVIDIA and 14,385 for the AMD. That 0.1% gap in the GTX 965M’s favor places these two as direct rivals, with the data showing a statistical tie in overall compute output. However, the specific workloads tell a more nuanced story, as the NVIDIA part wins both head-to-head tests, while the AMD part counters with a separate benchmark result not directly compared.

Head-to-Head Benchmarks

The most decisive victory for the NVIDIA GeForce GTX 965M comes in the Geekbench OpenCL test, where it scores 14,509 against the AMD Radeon RX Vega 11’s 12,525. That represents a 15.8% advantage, the largest delta between the two parts in any shared benchmark. This is a substantial margin for GPUs that otherwise sit at the same overall percentile, suggesting the GTX 965M’s architecture handles OpenCL compute workloads more efficiently than the Vega IGP’s GCN 5.0 design. The data indicates that in raw parallel compute tasks, the discrete NVIDIA solution holds a clear edge.

The second head-to-head test, Geekbench Vulkan, narrows the gap considerably. The GTX 965M scores 14,299, while the RX Vega 11 scores 13,543, giving the NVIDIA part a 5.6% win. While still a victory for the GTX 965M, the reduced margin hints that the AMD integrated GPU gains relative ground in Vulkan workloads compared to OpenCL. The RX Vega 11’s higher boost clock of 1400 MHz versus the GTX 965M’s 950 MHz may contribute to this closer result, though the NVIDIA part’s larger shading unit count (1,024 vs. 704) likely preserves its advantage.

Notably absent from the head-to-head comparison is the Geekbench Metal test, where the RX Vega 11 scores 17,086. This is the AMD part’s single highest benchmark score across all recorded tests, surpassing both its OpenCL (12,525) and Vulkan (13,543) results by 36.4% and 26.2%, respectively. Since Metal is Apple’s graphics API and the GTX 965M has no corresponding Metal score in the data, this result cannot be directly compared. However, it demonstrates that the RX Vega 11’s architecture is highly capable in specific API environments, even if its OpenCL and Vulkan scores lag the GTX 965M.

Looking at the nearest rival data, both GPUs are clustered within a tight performance band. The GTX 965M’s nearest rivals include the RX Vega 11 (0.1% delta), the NVIDIA GeForce GTX TITAN (0.2%), the AMD Radeon Vega 11 (0.4%), and the Intel Iris Xe MAX Graphics (0.6%). The RX Vega 11’s nearest rivals mirror this grouping, with the GTX TITAN at 0.1%, the GTX 965M at -0.1%, the Radeon Vega 11 at 0.2%, and the Iris Xe MAX at 0.5%. This clustering indicates that all five GPUs deliver essentially equivalent aggregate compute performance, with differences of less than one percent separating them.

The Verdict

The benchmark data supports a clear division of labor. The NVIDIA GeForce GTX 965M is the stronger choice for users prioritizing OpenCL and Vulkan compute workloads, as it wins both shared tests with margins of 15.8% and 5.6%. Its average benchmark score of 14,404 also edges out the RX Vega 11’s 14,385, and its nearest rival list shows it leading the AMD part by 0.1%. For applications that rely on these APIs, the GTX 965M delivers measurably better performance.

The AMD Radeon RX Vega 11, however, presents a compelling case based on its Metal score of 17,086, which is the highest single benchmark result among all scores recorded for either GPU. If a user’s workload is Metal-centric, the data suggests the RX Vega 11 would outperform the GTX 965M, though no direct comparison exists to confirm this. Additionally, the RX Vega 11’s status as an IGP with a 15 W TDP means it requires no separate graphics card, making it the only option for systems relying solely on integrated graphics.

From a pure performance standpoint, the GTX 965M wins the head-to-head. It leads in both direct comparisons and holds the higher average score. The RX Vega 11 counters with superior Metal performance and a much newer release date (2019 vs. 2015), but the data does not show it overcoming the GTX 965M’s lead in shared benchmarks. Users who need the highest OpenCL or Vulkan throughput should choose the GTX 965M, while those operating in Metal environments or requiring an integrated solution should consider the RX Vega 11.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 965M posts an average benchmark score of 14,404, while the AMD Radeon RX Vega 11 averages 14,385, putting the GTX 965M ahead by 0.1%.

Q: What is the largest performance gap between the two in a shared test?

A: In the Geekbench OpenCL test, the GTX 965M scores 14,509 versus the RX Vega 11’s 12,525, a 15.8% difference in favor of NVIDIA.

Q: Does the RX Vega 11 win any benchmark test?

A: The RX Vega 11 scores 17,086 in Geekbench Metal, which is its highest result, but the GTX 965M has no Metal score recorded, so no direct head-to-head comparison exists.

Q: How do the two GPUs rank against other hardware?

A: Both GPUs sit at the 56th percentile among all GPUs. The GTX 965M’s nearest rival is the RX Vega 11 at 0.1% delta, while the RX Vega 11’s nearest rival is the GTX TITAN at 0.1% delta.

Q: Which GPU has more shading units?

A: The GTX 965M has 1,024 shading units, compared to the RX Vega 11’s 704, a difference of 320 units.

Q: What is the clock speed difference?

A: The GTX 965M has a base clock of 924 MHz and a boost clock of 950 MHz, while the RX Vega 11 has a base clock of 300 MHz and a boost clock of 1400 MHz.

Specification Differences

The GTX 965M and RX Vega 11 differ across nearly every hardware specification. The GTX 965M uses a 28 nm process node from TSMC, while the RX Vega 11 uses a 12 nm node from GlobalFoundries. Transistor counts are close, with the GTX 965M at 5,200 million and the RX Vega 11 at 4,940 million, but die size diverges sharply: the GTX 965M measures 398 mm² versus the RX Vega 11’s 210 mm². This results in vastly different transistor densities, with the RX Vega 11 packing 23.5M transistors per mm² compared to the GTX 965M’s 13.1M per mm².

Memory configurations are fundamentally different. The GTX 965M has 2 GB of dedicated GDDR5 memory on a 128-bit bus, delivering 80.19 GB/s of bandwidth. The RX Vega 11 uses system-shared memory, with its size, type, bus width, and bandwidth all listed as system-dependent. Clock speeds also differ: the GTX 965M runs at 924 MHz base and 950 MHz boost, while the RX Vega 11 runs at 300 MHz base and 1400 MHz boost. The GTX 965M’s memory clock is 1253 MHz (5 Gbps effective), whereas the RX Vega 11’s memory clock is tied to system memory.

Compute unit counts show the GTX 965M with 64 TMUs and 32 ROPs, against the RX Vega 11’s 44 TMUs and 8 ROPs. Pixel rates reflect this: the GTX 965M outputs 30.40 GPixel/s versus the RX Vega 11’s 11.20 GPixel/s. Texture rates are nearly identical at 60.80 GTexel/s for NVIDIA and 61.60 GTexel/s for AMD. Floating-point performance is also close, with the GTX 965M at 1.946 TFLOPS FP32 and the RX Vega 11 at 1.971 TFLOPS FP32; the RX Vega 11 additionally supports FP16 at 3.942 TFLOPS (2:1), while the GTX 965M has no FP16 rating.

The RX Vega 11 has a TDP of 15 W, while the GTX 965M has no TDP listed. Form factors differ completely: the GTX 965M is an MXM Module with an MXM-B (3.0) bus interface, while the RX Vega 11 is an IGP with an IGP bus interface. Display outputs are portable-device dependent for the GTX 965M and motherboard dependent for the RX Vega 11. Both GPUs support DirectX 12 (12_1) and OpenGL 4.6, but the GTX 965M supports Vulkan 1.4 while the RX Vega 11 supports Vulkan 1.3.

Architecture Differences

The GTX 965M is built on NVIDIA’s Maxwell 2.0 architecture, using the GM204 chip. The RX Vega 11 uses AMD’s GCN 5.0 architecture, based on the Picasso chip. These are fundamentally different GPU designs from different eras, reflected in their transistor densities and feature sets. Maxwell 2.0 was designed for discrete mobile graphics in the GeForce 900M generation, while GCN 5.0 powers the Vega IGP integrated graphics found in Picasso APUs.

The GTX 965M’s Maxwell 2.0 architecture supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RX Vega 11’s GCN 5.0 architecture also supports DirectX 12 (12_1) and OpenGL 4.6, but only Vulkan 1.3. Neither GPU includes ray tracing cores or tensor cores, as both predate those hardware features. The RX Vega 11 offers FP16 compute at 3.942 TFLOPS with a 2:1 ratio, a capability the GTX 965M lacks entirely.

The RX Vega 11’s 12 nm process node and smaller die size (210 mm²) allow for a much higher transistor density of 23.5M per mm², despite having 260 million fewer transistors than the GTX 965M. The GTX 965M’s larger 398 mm² die on 28 nm technology achieves only 13.1M transistors per mm². This architectural difference explains how the RX Vega 11 fits integrated graphics performance into a 15 W TDP, while the GTX 965M requires a dedicated MXM module with no power connector listed.

Both GPUs are end-of-life products. The GTX 965M was released on January 8, 2015, succeeding the GeForce 800M and preceding the GeForce 10 Mobile. The RX Vega 11 launched on July 6, 2019, succeeding GCN 3.0 IGP and preceding Vega II IGP. The RX Vega 11’s system-shared memory architecture is a defining feature, contrasting with the GTX 965M’s dedicated 2 GB GDDR5 allocation. These architectural choices explain the performance patterns observed in the benchmark data, with the discrete GTX 965M offering more consistent compute throughput while the integrated RX Vega 11 relies on system resources and achieves exceptional Metal performance.