AMD Radeon 760M vs NVIDIA GeForce GTX 670MX Comparison
AMD Radeon 760M
GeForce GTX 670MX
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon 760M vs NVIDIA GeForce GTX 670MX
The AMD Radeon 760M and NVIDIA GeForce GTX 670MX represent two very different eras of mobile graphics, and the benchmark data reflects that divide clearly. The Radeon 760M, built on a 4 nm process with RDNA 3.0 architecture, is a modern integrated graphics processor that decisively outperforms the older discrete GeForce GTX 670MX in every shared test. The GTX 670MX, a 28 nm Kepler part from 2012, is now end-of-life and trails by massive margins, making the comparison less about competition and more about generational leap.
The Verdict
The data points to a single clear choice: the AMD Radeon 760M wins outright. In the two benchmarks where both GPUs have comparable results, the Radeon 760M dominates. It scores 20,255 in Geekbench OpenCL versus 6,125 for the GTX 670MX, a 230.7% advantage. In Geekbench Vulkan, the gap widens to 470.7%, with the Radeon 760M posting 30,336 against the GTX 670MX’s 5,316.
The average benchmark score tells a similar story. The Radeon 760M sits at 6,019, placing it in the 35th percentile of all GPUs, while the GTX 670MX averages 5,721, ranking in the 33rd percentile. The Radeon 760M’s nearest rivals include the AMD Radeon RX 6400 and NVIDIA GeForce GTX 770M, both within 0.3% of its average score. The GTX 670MX, by contrast, sits near the Intel Iris Pro Graphics P6300 and NVIDIA GeForce GTX 550 Ti, with deltas of 0.2% and -0.2% respectively.
For any user choosing between these two, the Radeon 760M is the only rational pick. It is faster, newer, more feature-rich, and consumes less power. The GTX 670MX, despite being a discrete GPU with dedicated memory, cannot keep pace with the modern integrated solution. The only scenario where the GTX 670MX might seem relevant is legacy system compatibility, but even then, the performance deficit is so large that it offers no practical advantage.
Where Each One Wins
The Radeon 760M wins every head-to-head benchmark in the data. In Geekbench OpenCL, it delivers 20,255 points, which is more than three times the GTX 670MX’s 6,125. The Vulkan test is even more lopsided: 30,336 versus 5,316. This means the Radeon 760M is not just faster in compute workloads; it is in a completely different performance class.
Beyond the shared tests, the Radeon 760M has a full suite of additional benchmark results that the GTX 670MX lacks entirely. It scores 5,310 in Passmark G3D, 2,840 in Passmark GPU Compute, and 890 in Passmark G2D. It also shows strong DirectX performance with 65 in Passmark DirectX 9, 52 in DirectX 11, 25 in DirectX 12, and 19 in DirectX 10. The GTX 670MX has no comparable results for these tests, meaning the Radeon 760M wins by default in all of them.
The GTX 670MX has no wins anywhere in the dataset. Its only two benchmark scores are the Geekbench results, and it loses both by enormous margins. The data shows zero wins for the NVIDIA part, reinforcing that this is not a competitive matchup but a generational gap in performance.
Architecture Differences
The architectural gap between these two GPUs is stark. The AMD Radeon 760M uses the Phoenix chip with RDNA 3.0 architecture, manufactured on a 4 nm process at TSMC. It packs 25,390 million transistors on a 178 mm² die, yielding a transistor density of 142.6 million per mm². The NVIDIA GeForce GTX 670MX, in contrast, uses the GK104 chip with Kepler architecture, built on a 28 nm process. It has 3,540 million transistors on a 294 mm² die, with a density of just 12.0 million per mm².
The Radeon 760M has 512 shading units, 32 texture mapping units, and 16 render output units. It also includes 8 ray tracing cores, a feature entirely absent from the GTX 670MX, which has no ray tracing support. The GTX 670MX does have more raw shading units at 960, along with 80 TMUs and 24 ROPs, but its clock speeds are far lower. The Radeon 760M boosts to 2,599 MHz from a base of 800 MHz, while the GTX 670MX is locked at 601 MHz for both base and boost.
Memory is another major divider. The Radeon 760M uses system shared memory, with bandwidth described as system dependent. The GTX 670MX has 3 GB of dedicated GDDR5 memory on a 192-bit bus, delivering 67.20 GB/s. The Radeon 760M’s memory clock is also system shared, whereas the GTX 670MX runs at 700 MHz with 2.8 Gbps effective.
The Radeon 760M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The GTX 670MX tops out at DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Radeon 760M also has a significantly lower TDP at 15 W, compared to the GTX 670MX’s 75 W. The Radeon 760M is an IGP with no power connectors, while the GTX 670MX also has no power connectors but is designed for portable devices.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The AMD Radeon 760M has an average benchmark score of 6,019, while the NVIDIA GeForce GTX 670MX averages 5,721.
Q: How much faster is the Radeon 760M in Geekbench OpenCL?
A: The Radeon 760M scores 20,255 compared to the GTX 670MX’s 6,125, a delta of 230.7%.
Q: Does the GTX 670MX have any ray tracing cores?
A: No, the GTX 670MX has no ray tracing cores, whereas the Radeon 760M includes 8.
Q: What is the process node difference between the two?
A: The Radeon 760M is built on a 4 nm process, while the GTX 670MX uses a 28 nm process.
Q: Which GPU supports the newer Vulkan API version?
A: The Radeon 760M supports Vulkan 1.4, while the GTX 670MX supports Vulkan 1.2.175.
Q: What is the TDP of each GPU?
A: The Radeon 760M has a TDP of 15 W, and the GTX 670MX has a TDP of 75 W.
Head-to-Head Benchmarks
The head-to-head data contains only two tests, and the Radeon 760M wins both by enormous margins. In Geekbench OpenCL, the Radeon 760M scores 20,255 against the GTX 670MX’s 6,125. That is a 230.7% difference, meaning the AMD part delivers more than triple the compute performance. This result aligns with the Radeon 760M’s higher FP32 throughput of 5.323 TFLOPS, compared to the GTX 670MX’s 1,153.9 GFLOPS.
The Geekbench Vulkan test shows an even larger gap. The Radeon 760M posts 30,336, while the GTX 670MX manages only 5,316. The delta is 470.7%, nearly five times the performance. This massive advantage likely stems from the Radeon 760M’s modern RDNA 3.0 architecture, which includes dedicated ray tracing cores and much higher boost clocks up to 2,599 MHz. The GTX 670MX, with its older Kepler design and fixed 601 MHz clock, simply cannot compete in Vulkan workloads.
The Radeon 760M’s other benchmark scores further underscore its dominance. Its Passmark G3D score of 5,310 is nearly identical to its average benchmark score of 6,019, indicating strong overall performance. The Passmark GPU Compute score of 2,840 shows solid compute capability, while the Passmark G2D score of 890 reflects decent 2D performance. In DirectX tests, the Radeon 760M scores 65 in DirectX 9, 52 in DirectX 11, 25 in DirectX 12, and 19 in DirectX 10.
The GTX 670MX has no comparable results for any of these tests, so its performance profile is incomplete. What is clear from the available data is that the Radeon 760M outperforms the GTX 670MX in every measurable way. The average benchmark scores, the percentile rankings, and the direct head-to-head results all point to the same conclusion: the AMD Radeon 760M is the superior GPU by a wide margin. Its nearest rivals, such as the AMD Radeon RX 6400 and NVIDIA GeForce GTX 770M, are within 0.3% of its average score, placing it in a competitive position among modern GPUs. The GTX 670MX, however, sits near older parts like the Intel Iris Pro Graphics P6300 and NVIDIA GeForce GTX 550 Ti, confirming its status as a legacy component.