NVIDIA GeForce GTX 760 vs NVIDIA GeForce GTX 780M Comparison

Where Each One Wins

The benchmark split is decisive: the GeForce GTX 780M wins all three recorded head-to-head tests, while the GeForce GTX 760 records zero wins. The largest separation comes in Geekbench Metal, where the 780M scores 8319 against the 760's 4524, a delta of 83.9%. That is not a narrow margin; it is a dominant result in compute workloads that lean on Metal API performance. The other two tests are closer, but the 780M still holds the lead in both Geekbench OpenCL (12769 versus 11299, a 13% advantage) and Geekbench Vulkan (12696 versus 12551, a 1.2% edge).

The use-case picture follows the scores. If the workload is Metal-based, the 780M is the clear choice. The 83.9% lead means it is not merely faster, it is roughly twice as fast in that specific test. For OpenCL workloads, the 780M remains ahead but by a smaller margin, suggesting that the two GPUs are more evenly matched in general-purpose compute. Vulkan is the tightest contest, with the 780M edging out the 760 by just 1.2%, a result that could be considered near-parity in real-world conditions. The data shows no scenario where the 760 wins outright, but it is competitive in Vulkan and respectable in OpenCL.

For gaming, the absence of a dedicated gaming benchmark in the record means conclusions must come from the compute scores. The 780M's higher average benchmark score (11261 versus 9458) and higher percentile rank (50th versus 46th) support a general performance advantage. However, the 760's higher base and boost clocks (980 MHz and 1032 MHz versus 771 MHz and 797 MHz) suggest it could close the gap in latency-sensitive or clock-bound scenarios. The database does not record such a test, so the verdict must rest on what is measured.

Architecture Differences

Both GPUs share the same fundamental design: GK104 chip, Kepler architecture, 28 nm process, TSMC foundry, 3,540 million transistors, and a 294 mm² die. The transistor density is identical at 12.0M per mm². They also match on memory bus width (256 bit), ROPs (32), DirectX support (12 with 11_0 feature level), OpenGL (4.6), and Vulkan (1.2.175). The architectural family is the same, but the configurations differ in several key ways.

The 780M has more compute resources: 1536 shading units versus 1152, 128 texture mapping units versus 96. That is a 33% increase in shaders and a 33% increase in TMUs. The 780M also carries 4 GB of GDDR5 memory versus the 760's 2 GB. The 760 counters with higher clocks: a 980 MHz base and 1032 MHz boost against the 780M's 771 MHz and 797 MHz. Memory speed also favors the 760, with 1502 MHz (6 Gbps effective) versus 1250 MHz (5 Gbps effective). The 760's memory bandwidth is 192.3 GB/s, while the 780M manages 160.0 GB/s.

The pixel rate and texture rate are close: the 780M posts 25.50 GPixel/s and 102.0 GTexel/s, while the 760 posts 24.77 GPixel/s and 99.07 GTexel/s. The 780M's extra shaders and TMUs offset its lower clocks, producing slightly higher throughput rates. The 780M also has a higher FP32 peak at 2.448 TFLOPS versus 2.378 TFLOPS, a small but real advantage. Neither GPU has RT cores or tensor cores, and FP16 is not specified for either.

Form factor differences are significant. The 780M is an MXM module with no power connectors and a 122 W TDP, designed for portable devices. The 760 is a dual-slot card, 241 mm long (9.5 inches), requiring 2x 6-pin power connectors and a 450 W suggested PSU, with a 170 W TDP. The 760 offers fixed display outputs (2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2), while the 780M's outputs are portable-device dependent. The 760 uses PCIe 3.0 x16; the 780M uses MXM-B (3.0). Release dates are close: the 780M launched on 2013-05-10, the 760 on 2013-06-24.

Head-to-Head Benchmarks

The Geekbench Metal test delivers the most dramatic result. The 780M scores 8319, the 760 scores 4524. The delta is 83.9%, meaning the 780M is nearly 84% faster. This is the single biggest win in the comparison and drives the overall verdict. A user running Metal-accelerated applications on the 780M platform should see substantial performance headroom.

Geekbench OpenCL shows a more modest lead. The 780M records 12769, the 760 records 11299, a 13% delta. This indicates that in OpenCL compute, the 780M's additional shading units and TMUs deliver a measurable but not overwhelming advantage. The 760's higher clocks and memory bandwidth help it stay within striking distance, but the 780M still wins.

Geekbench Vulkan is nearly a tie. The 780M scores 12696, the 760 scores 12551, a delta of just 1.2%. The 760's higher memory bandwidth (192.3 GB/s versus 160.0 GB/s) and faster clocks likely contribute to closing the gap in this API. In Vulkan-specific workloads, the two GPUs are effectively interchangeable according to the recorded data. Still, the 780M wins, making the head-to-head sweep 3-0.

The average benchmark scores reinforce the pattern. The 780M averages 11261 across its recorded tests, while the 760 averages 9458, a difference of roughly 19%. The 780M sits at the 50th percentile of all GPUs, the 760 at the 46th. The nearest rivals for the 780M include the AMD Radeon Pro WX 3200 (avg 11228, 0.3% behind) and the AMD FirePro W4300 (avg 11225, 0.3% behind), showing that the 780M is positioned in a tight cluster. The 760's nearest rival is the NVIDIA GeForce GTX TITAN BLACK (avg 9474, 0.2% ahead), followed by the AMD Radeon R7 M380 (avg 9313, 1.6% behind). This places the 760 slightly below the 780M in overall standing.

The Verdict

The data supports a clear conclusion: the GeForce GTX 780M is the faster GPU in this comparison. It wins all three head-to-head benchmarks, holds a higher average score (11261 versus 9458), and ranks higher in the percentile distribution (50th versus 46th). The Metal result is the standout, with an 83.9% lead that dwarfs the other tests. For any workload that favors Metal, the 780M is the unambiguous pick.

The 760 is not without merit. Its Vulkan score trails by only 1.2%, and its OpenCL score is within 13%. The 760 also has a higher memory bandwidth and faster clocks, which could matter in applications that are memory-bound or clock-sensitive. Its desktop form factor, with fixed display outputs and a PCIe 3.0 x16 interface, makes it a conventional card for standard PC builds. The 780M, as an MXM module, is limited to portable systems that support that slot.

Who should choose which? A user with a laptop or portable device that accepts MXM-B modules should favor the 780M, as it delivers superior compute performance across all recorded tests. A desktop builder with a standard PCIe slot and a 450 W PSU could consider the 760, but the benchmark data says they would be accepting lower performance in exchange for the convenience of a desktop form factor. The 760's launch MSRP was 249 USD, which may be noted as a historical reference, but the database does not indicate that the 780M had a comparable price. The production status of both is end-of-life, so neither is a current purchase recommendation. Based strictly on measured performance, the 780M wins.

FAQ

Q: Which GPU wins in Geekbench Metal?

A: The GeForce GTX 780M wins with a score of 8319 versus the GeForce GTX 760's 4524, a delta of 83.9%.

Q: How close is the Vulkan performance between the two?

A: The 780M scores 12696 and the 760 scores 12551, a delta of just 1.2%, making Vulkan the closest test in the comparison.

Q: Do both GPUs use the same architecture?

A: Yes, both use the GK104 chip with Kepler architecture, a 28 nm process, 3,540 million transistors, and a 294 mm² die size.

Q: What is the memory configuration difference?

A: The 780M has 4 GB of GDDR5 with a 256-bit bus and 160.0 GB/s bandwidth. The 760 has 2 GB of GDDR5 with a 256-bit bus and 192.3 GB/s bandwidth.

Q: Which GPU has more shading units?

A: The 780M has 1536 shading units, while the 760 has 1152, a 33% difference in favor of the 780M.

Q: What are the form factor differences?

A: The 780M is an MXM module with no power connectors and a 122 W TDP. The 760 is a dual-slot card, 241 mm long, requiring 2x 6-pin power connectors, a 450 W suggested PSU, and a 170 W TDP.

Specification Differences

• Shading Units: 1536 (780M) versus 1152 (760)
• Texture Mapping Units: 128 (780M) versus 96 (760)
• Base Clock: 771 MHz (780M) versus 980 MHz (760)
• Boost Clock: 797 MHz (780M) versus 1032 MHz (760)
• Memory Clock: 1250 MHz, 5 Gbps effective (780M) versus 1502 MHz, 6 Gbps effective (760)
• Memory Size: 4 GB (780M) versus 2 GB (760)
• Memory Bandwidth: 160.0 GB/s (780M) versus 192.3 GB/s (760)
• Pixel Rate: 25.50 GPixel/s (780M) versus 24.77 GPixel/s (760)
• Texture Rate: 102.0 GTexel/s (780M) versus 99.07 GTexel/s (760)
• FP32 Performance: 2.448 TFLOPS (780M) versus 2.378 TFLOPS (760)
• TDP: 122 W (780M) versus 170 W (760)
• Slot Width: MXM Module (780M) versus Dual-slot (760)
• Power Connectors: None (780M) versus 2x 6-pin (760)
• Suggested PSU: Not specified (780M) versus 450 W (760)
• Bus Interface: MXM-B (3.0) (780M) versus PCIe 3.0 x16 (760)
• Display Outputs: Portable Device Dependent (780M) versus 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 (760)
• Length: Not specified (780M) versus 241 mm, 9.5 inches (760)
• Release Date: 2013-05-10 (780M) versus 2013-06-24 (760)
• Generation: GeForce 700M (780M) versus GeForce 700 (760)
• Predecessor: GeForce 600M (780M) versus GeForce 600 (760)
• Successor: GeForce 800M (780M) versus GeForce 900 (760)
• Launch MSRP: Not specified (780M) versus 249 USD (760)
• Average Benchmark Score: 11261 (780M) versus 9458 (760)
• Percentile vs All GPUs: 50th (780M) versus 46th (760)