AMD Radeon R7 Graphics vs NVIDIA GeForce GTX 765M Comparison

The Verdict

The data splits this matchup cleanly along workload type. The NVIDIA GeForce GTX 765M is the stronger GPU overall, with an average benchmark score of 5501 against 4998 for the AMD Radeon R7 Graphics, a lead of roughly 10%. It wins both recorded head-to-head tests, and its 32nd percentile ranking among all GPUs sits above the AMD part's 29th percentile. For anyone who needs consistent compute performance in a portable chassis, the GTX 765M is the clear choice.

That said, the AMD Radeon R7 Graphics is not without a role. It is an integrated graphics processor, drawing just 25 W, and it slots into a completely different class of machine. The GTX 765M is a discrete MXM module with a 75 W TDP and requires a dedicated slot. If you are selecting a GPU for a thin, low-power system where the processor already includes graphics, the AMD part is the only one of the two that fits. The benchmark gap is real, but so is the physical and power envelope difference.

The GTX 765M wins on raw numbers, but the R7 Graphics wins on integration. Pick the NVIDIA part if you have a laptop with an MXM slot and can feed it 75 W. Pick the AMD IGP if you are building or buying a system around a Kaveri APU and cannot accommodate a discrete module. The data does not suggest the AMD part is competitive in performance, but it does occupy a niche the NVIDIA card cannot fill.

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 Graphics scores 4998. The NVIDIA part leads by about 10%.

Q: How do the two compare in OpenCL performance?

A: The GTX 765M scores 7176 in Geekbench OpenCL, versus 4015 for the R7 Graphics. That is a 78.7% advantage for the NVIDIA card.

Q: Is the AMD Radeon R7 Graphics competitive in Vulkan?

A: It is closer but still behind. The GTX 765M scores 6714 in Geekbench Vulkan, and the R7 Graphics scores 5980, a 12.3% gap. The AMD part is within striking distance but loses that test as well.

Q: What are the power requirements for each GPU?

A: The NVIDIA GeForce GTX 765M has a 75 W TDP and uses no external power connectors. The AMD Radeon R7 Graphics has a 25 W TDP and is an integrated processor, so it draws from the system's existing power delivery.

Q: Can the AMD Radeon R7 Graphics be used in a laptop with an MXM slot?

A: No. The AMD part is an IGP, meaning it is built into the processor and connected via the motherboard. The NVIDIA card uses an MXM-B (3.0) interface and is a removable module.

Q: Which GPU has better support for modern graphics APIs?

A: The AMD Radeon R7 Graphics supports DirectX 12 (12_0), while the NVIDIA card supports DirectX 12 (11_0). Both support OpenGL 4.6, and both support Vulkan, with the NVIDIA part listing Vulkan 1.2.175 versus 1.2.170 for AMD.

Architecture Differences

The two GPUs come from different design schools entirely. The NVIDIA GeForce GTX 765M uses the GK106 chip built on the Kepler architecture, manufactured by TSMC on a 28 nm process. It packs 2,540 million transistors into a 221 mm² die, yielding a transistor density of 11.5 million per square millimeter. The AMD Radeon R7 Graphics uses the Spectre Lite chip, which is part of the GCN 2.0 architecture and goes by the generation label "GCN 2.0 IGP (Kaveri)". It is built by GlobalFoundries, also on 28 nm, but the die is larger at 245 mm² while holding slightly fewer transistors at 2,410 million. That works out to a lower density of 9.8 million per square millimeter.

The compute resources differ sharply. NVIDIA's Kepler chip provides 768 shading units, 64 texture mapping units, and 16 raster operations pipelines. AMD's GCN 2.0 IGP offers 384 shading units, 24 TMUs, and 8 ROPs. In every count, the NVIDIA part has more hardware to throw at a workload. The pixel rate tells the same story: 13.81 GPixel/s for NVIDIA versus 5.760 GPixel/s for AMD. Texture rate is 55.23 GTexel/s against 17.28 GTexel/s. Floating-point throughput is 1,325.6 GFLOPS versus 553.0 GFLOPS.

Memory architecture is a fundamental split. The GTX 765M uses 2 GB of dedicated GDDR5 on a 128-bit bus, with 64.13 GB/s of bandwidth and a 1002 MHz memory clock (4 Gbps effective). The R7 Graphics has no dedicated memory at all: it uses system shared memory, with a system-dependent bus width and bandwidth. That means the AMD part's performance will vary with the host system's RAM configuration, while the NVIDIA card has a fixed, predictable memory pipeline.

Both chips support DirectX 12, but at different feature levels. NVIDIA lists DirectX 12 (11_0), AMD lists DirectX 12 (12_0). Both have OpenGL 4.6 and Vulkan support, with NVIDIA at Vulkan 1.2.175 and AMD at 1.2.170. Neither has dedicated ray tracing cores or tensor cores. The NVIDIA part is marked end-of-life, as is the AMD IGP, and both have successors listed.

Specification Differences

The clearest differences between the two come down to form factor, memory, and compute resources.

• Process node: Both are 28 nm, but NVIDIA uses TSMC and AMD uses GlobalFoundries.
• Transistors: NVIDIA has 2,540 million; AMD has 2,410 million.
• Die size: NVIDIA is 221 mm²; AMD is 245 mm².
• Transistor density: NVIDIA is 11.5M per mm²; AMD is 9.8M per mm².
• Shading units: NVIDIA has 768; AMD has 384.
• TMUs: NVIDIA has 64; AMD has 24.
• ROPs: NVIDIA has 16; AMD has 8.
• Pixel rate: NVIDIA is 13.81 GPixel/s; AMD is 5.760 GPixel/s.
• Texture rate: NVIDIA is 55.23 GTexel/s; AMD is 17.28 GTexel/s.
• FP32 throughput: NVIDIA is 1,325.6 GFLOPS; AMD is 553.0 GFLOPS.
• Memory: NVIDIA has 2 GB GDDR5 on a 128-bit bus with 64.13 GB/s; AMD uses system shared memory with system-dependent bandwidth.
• Memory clock: NVIDIA runs at 1002 MHz (4 Gbps effective); AMD has no dedicated memory clock.
• TDP: NVIDIA is 75 W; AMD is 25 W.
• Slot width: NVIDIA is an MXM Module; AMD is an IGP.
• Bus interface: NVIDIA is MXM-B (3.0); AMD is IGP.
• Power connectors: NVIDIA lists none; AMD has none listed.
• Display outputs: NVIDIA is portable-device dependent; AMD is motherboard dependent.
• DirectX support: NVIDIA is 12 (11_0); AMD is 12 (12_0).
• Vulkan version: NVIDIA is 1.2.175; AMD is 1.2.170.
• Release date: NVIDIA launched on 2013-05-29; AMD launched on 2014-02-16.

The AMD part has no base or boost clock listed, while the NVIDIA card has a 797 MHz base and 863 MHz boost. That absence reflects the integrated nature of the AMD GPU, whose clocks are tied to the host processor.

Head-to-Head Benchmarks

The database records two direct comparisons, and the NVIDIA card wins both. In Geekbench OpenCL, the GTX 765M scores 7176 against 4015 for the R7 Graphics. That is a 78.7% delta, a massive gap that shows the NVIDIA part is more than capable of handling compute-heavy OpenCL workloads. The AMD IGP is not in the same league here, and the difference is large enough that any OpenCL task will finish noticeably faster on the NVIDIA card.

Vulkan is a closer contest. The GTX 765M scores 6714, and the R7 Graphics scores 5980, a 12.3% delta. The AMD part holds up better in this API, likely due to its newer DirectX 12 (12_0) feature set and Vulkan 1.2.170 support. Still, the NVIDIA card wins, and the margin is not trivial. In percentage terms, Vulkan is the AMD part's best showing, but it does not flip the result.

The aggregate numbers confirm the trend. The GTX 765M has an average benchmark score of 5501, putting it just ahead of the NVIDIA GeForce MX130 (5508, -0.1%) and the AMD Radeon R7 M440 (5483, 0.3%), and just behind the AMD FirePro M4000 (5537, -0.7%). The R7 Graphics averages 4998, sitting near the NVIDIA Quadro 4000 (4979, 0.4%) and the AMD Radeon R5 M430 (5018, -0.4%). The GTX 765M's nearest rivals all cluster within roughly a point, meaning it is a solid mid-pack mobile GPU. The R7 Graphics sits in a lower band, closer to entry-level discrete parts.

The wins tally is 2 for the NVIDIA card and 0 for the AMD part. There is no benchmark in the recorded data where the R7 Graphics takes the lead.

Where Each One Wins

The NVIDIA GeForce GTX 765M wins every measured benchmark, so the use-case split is less about performance and more about deployment. The GTX 765M is the correct pick for any system that has an MXM-B (3.0) slot and can supply 75 W. Its 2 GB of dedicated GDDR5 memory with 64.13 GB/s of bandwidth means it does not depend on system RAM, so performance is consistent regardless of the host machine's memory configuration. The 768 shading units and 1,325.6 GFLOPS of FP32 throughput give it a clear edge in OpenCL workloads, where it leads the AMD part by 78.7%. For gaming, content creation, or any GPU-accelerated task that can use Vulkan, the 12.3% lead in that API still favors the NVIDIA card. Its 32nd percentile ranking among all GPUs also puts it in a better overall position than the AMD part's 29th percentile.

The AMD Radeon R7 Graphics wins the integration battle. It is an IGP with a 25 W TDP, so it fits into Kaveri-based systems with no discrete graphics slot. It uses system shared memory, which means there is no separate VRAM purchase and no power connector to worry about. Its DirectX 12 (12_0) support is technically a higher feature level than the NVIDIA card's 12 (11_0), which could matter for specific titles that exploit DX12 features. In Vulkan, the gap narrows to 12.3%, and the AMD part is competitive enough for lighter workloads. It is also the only one of the two that can be used in a motherboard-dependent display configuration, since it outputs through the motherboard rather than a portable device.

For a builder with an MXM slot, the choice is straightforward: the GTX 765M. For a builder constrained to an APU platform with no discrete option, the R7 Graphics is the only viable pick, and the data shows it can handle Vulkan tasks reasonably well, just at a lower performance level. The recorded benchmarks do not show any scenario where the AMD part wins, so the decision rests entirely on system compatibility and power budget.