AMD Radeon R7 M365X vs NVIDIA GeForce GTX 765M Comparison

The NVIDIA GeForce GTX 765M and AMD Radeon R7 M365X are both end-of-life mobile graphics solutions from different architectural eras, yet they land in the same performance percentile. The GTX 765M, built on Kepler, carries a substantial lead in raw compute and memory bandwidth, while the R7 M365X counters with a more modern GCN 1.0 feature set and marginally better transistor density. Benchmark data shows the NVIDIA part wins every head-to-head test, but the AMD chip remains competitive in specific API workloads, making the choice dependent on whether you prioritize peak performance or broader driver feature support.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 765M scores 5501 on average, while the AMD Radeon R7 M365X scores 5416. That is a difference of 85 points, or roughly 1.6% in favor of the GTX 765M.

Q: How large is the GTX 765M's lead in OpenCL performance?

A: In the Geekbench OpenCL test, the GTX 765M scores 7176 versus 5939 for the R7 M365X. This translates to a 20.8% advantage for the NVIDIA part.

Q: Does the AMD Radeon R7 M365X win any benchmark comparison?

A: No. In the head-to-head results, the GTX 765M wins both available tests (OpenCL and Vulkan). The R7 M365X has zero wins in direct comparison.

Q: What is the difference in Vulkan performance between the two?

A: The GTX 765M scores 6714 in Geekbench Vulkan, while the R7 M365X scores 4893. The NVIDIA GPU leads by 37.2%, which is its largest margin in any tested workload.

Q: Are these GPUs on the same manufacturing process?

A: Yes, both are fabricated on TSMC's 28 nm process. However, the GTX 765M uses a 221 mm² die with 2,540 million transistors, while the R7 M365X uses a 77 mm² die with 950 million transistors.

Q: Which GPU has better transistor density?

A: The AMD Radeon R7 M365X has a density of 12.3M transistors per mm², slightly higher than the GTX 765M's 11.5M per mm². This is despite the AMD chip having fewer total transistors.

Architecture Differences

The GTX 765M is built on NVIDIA's Kepler architecture with the GK106 chip, while the R7 M365X uses AMD's GCN 1.0 architecture with the Litho chip. This fundamental difference shapes their respective strengths. The Kepler design dedicates more silicon to shading units and texture mapping, whereas GCN 1.0 focuses on a more balanced compute-oriented layout.

The transistor counts tell a clear story: the GTX 765M packs 2,540 million transistors into a 221 mm² die, compared to the R7 M365X's 950 million transistors on a 77 mm² die. The NVIDIA chip is 2.7x larger in die area and carries 2.7x more transistors, which explains its higher raw throughput. However, the AMD part achieves a modestly better transistor density (12.3M vs 11.5M per mm²), indicating a more efficient use of silicon area.

Clock behavior also differs. The GTX 765M has explicit base and boost clocks of 797 MHz and 863 MHz respectively, whereas the R7 M365X has no listed base or boost clock in the data. Memory clocks are nearly identical, with the GTX 765M at 1002 MHz (4 Gbps effective) and the R7 M365X at 1000 MHz (also 4 Gbps effective).

The memory subsystems differ in capacity but not width: both use a 128-bit bus, but the GTX 765M comes with 2 GB of GDDR5 while the R7 M365X has only 1024 MB. This gives the NVIDIA part 64.13 GB/s of bandwidth versus 64.00 GB/s for the AMD — a marginal 0.2% difference.

DirectX support favors the AMD chip slightly. The R7 M365X supports DirectX 12 (11_1), while the GTX 765M is limited to DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan, with the GTX 765M having a slightly newer Vulkan version (1.2.175 vs 1.2.170).

The Verdict

For raw performance, the NVIDIA GeForce GTX 765M is the clear choice. It wins both head-to-head benchmarks with a 20.8% margin in OpenCL and a 37.2% margin in Vulkan. Its higher average score (5501 vs 5416) and superior specifications across shading units, texture units, and ROPs make it the stronger GPU for compute-heavy tasks.

The AMD Radeon R7 M365X is not without merit. It offers a more modern GCN 1.0 architecture with better DirectX 12 feature support (11_1 vs 11_0) and a denser transistor layout. For users who prioritize driver compatibility with newer API features or who need a smaller, more power-efficient package, the AMD part might be preferable despite its lower performance.

The data indicates the GTX 765M is the pick for anyone seeking maximum frame rates or compute throughput. The R7 M365X makes sense only if the specific API support or the smaller die size matters more than the 20-37% performance deficit.

Specification Differences

The GTX 765M and R7 M365X diverge sharply in nearly every internal specification. The NVIDIA part features 768 shading units, 64 texture mapping units, and 16 ROPs, while the AMD part has 384 shading units, 24 TMUs, and 8 ROPs. This means the GTX 765M has exactly double the shading units, 2.7x the TMUs, and double the ROPs.

Pixel and texture rates reflect this disparity. The GTX 765M achieves 13.81 GPixel/s and 55.23 GTexel/s, compared to the R7 M365X's 6.600 GPixel/s and 19.80 GTexel/s. The NVIDIA GPU is 2.1x faster in pixel fill and 2.8x faster in texture fill.

FP32 compute follows the same pattern: the GTX 765M delivers 1,325.6 GFLOPS versus 633.6 GFLOPS for the R7 M365X, a 2.1x advantage. Neither GPU lists FP16 performance.

Memory capacity differs, with the GTX 765M offering 2 GB versus the R7 M365X's 1024 MB. Both use GDDR5 on a 128-bit bus, but bandwidth slightly favors the NVIDIA part at 64.13 GB/s versus 64.00 GB/s.

Power and interface also diverge. The GTX 765M has a listed TDP of 75 W, uses an MXM-B (3.0) interface, and has no power connectors. The R7 M365X has no TDP listed, uses PCIe 3.0 x8, and lacks power connector data. The GTX 765M is an MXM module, while the AMD part uses a standard PCIe slot.

Head-to-Head Benchmarks

The Geekbench OpenCL test shows the GTX 765M scoring 7176 against the R7 M365X's 5939, a 20.8% advantage for NVIDIA. This is a substantial gap that reflects the GTX 765M's doubling of shading units and higher FP32 throughput. In practical terms, this means OpenCL compute workloads — such as video encoding or physics simulations — will complete noticeably faster on the NVIDIA GPU.

The Vulkan test reveals an even larger divide. The GTX 765M scores 6714, while the R7 M365X manages only 4893, giving NVIDIA a 37.2% lead. This is the biggest margin in any comparison, suggesting that the Kepler architecture handles Vulkan's draw calls and command buffers more efficiently than GCN 1.0 in this specific driver implementation. The delta is more than double the OpenCL gap, indicating Vulkan performance is a particular weakness for the AMD part.

The average benchmark scores corroborate these results. The GTX 765M's 5501 average sits comfortably above the R7 M365X's 5416, though the difference narrows to just 1.6% when averaged across all tests. This is because the R7 M365X has no Metal benchmark listed, while the GTX 765M includes a Geekbench Metal score of 2612, which drags its average down.

Looking at nearest rivals, the GTX 765M trades blows with the NVIDIA GeForce MX130 (5508, -0.1% delta) and AMD Radeon R7 M440 (5483, +0.3% delta), while the R7 M365X sits close to the AMD Radeon 610M (5444, -0.5% delta) and Intel UHD Graphics P630 (5370, +0.9% delta). Both GPUs occupy the same performance tier, but the GTX 765M's wins are more decisive within that tier.

Where Each One Wins

The NVIDIA GeForce GTX 765M wins in every measured benchmark category. In OpenCL, its 20.8% advantage makes it the better choice for any application that leverages general-purpose GPU computing. The 37.2% Vulkan lead suggests it is also superior for games or applications that use the Vulkan API, delivering smoother frame pacing and higher throughput.

The GTX 765M also wins on memory capacity, offering 2 GB versus 1024 MB on the R7 M365X. This matters for texture-heavy workloads or running modern game assets at higher resolutions, where the extra memory prevents swapping and stutter.

The AMD Radeon R7 M365X wins in architecture efficiency and feature support. Its GCN 1.0 design achieves a higher transistor density (12.3M vs 11.5M per mm²), meaning it uses its silicon more efficiently. It also supports DirectX 12 (11_1) compared to the GTX 765M's DirectX 12 (11_0), which could be relevant for specific DX12 titles that require the newer feature level.

The R7 M365X also has a more modern bus interface (PCIe 3.0 x8) compared to the GTX 765M's MXM-B (3.0) module, though this is a form-factor difference rather than a performance one. For systems that require a standard PCIe slot rather than an MXM module, the AMD part is the only viable option between the two.

For pure gaming performance or compute workloads, the GTX 765M is the definitive winner. For users with a PCIe-based system that needs DirectX 11_1 support or values architectural efficiency, the R7 M365X offers a valid alternative despite its lower scores. The data shows no scenario where the AMD part out-performs the NVIDIA GPU in raw speed, but its feature set and smaller footprint make it a reasonable fallback choice.