NVIDIA GeForce GTX 765M vs NVIDIA GeForce GTX 770M Comparison

Where Each One Wins

The recorded benchmark data shows a clear split between these two Kepler-based mobile GPUs. The NVIDIA GeForce GTX 770M takes the lead in both available head-to-head tests, while the GTX 765M does not secure a single win in the measured categories. That said, the margin of victory is not uniform across workloads, which hints at where each part might be better suited.

In the Geekbench Metal test, the GTX 770M scores 3448 versus 2612 for the GTX 765M, a delta of 32 percent. This is the larger of the two victories and suggests that the 770M has a substantial advantage in compute tasks that leverage Apple's Metal API. For users running Metal-based applications or games on compatible platforms, this is the decisive metric.

The Geekbench OpenCL test tells a slightly different story. Here the GTX 770M scores 8552 against 7176 for the GTX 765M, a delta of 19.2 percent. The 770M still wins, but the gap narrows considerably. OpenCL workloads tend to stress memory bandwidth and raw shader throughput, and while the 770M still comes out ahead, the 765M is comparatively closer in this scenario.

Notably, the GTX 765M has a Geekbench Vulkan score of 6714 recorded in the database, while the GTX 770M has no Vulkan benchmark entry. This means that for Vulkan-specific workloads, the 765M is the only one of the two with measurable data. Users targeting Vulkan applications cannot directly compare the two from the available numbers, but the 765M's presence in that test indicates it can at least run such workloads.

The average benchmark score reinforces the overall hierarchy: the GTX 770M sits at 6000, while the GTX 765M trails at 5501. That difference of roughly 499 points places the 770M about 9.1 percent ahead on average. The percentile rankings also differ, with the 770M at the 35th percentile among all GPUs and the 765M at the 32nd percentile. Neither part is a high-flyer in the current landscape, but the 770M is consistently the stronger of the two.

Architecture Differences

Both GPUs share the same fundamental DNA. Each uses the GK106 chip, built on the Kepler architecture, fabricated by TSMC on a 28 nm process. The transistor count is identical at 2,540 million, and the die size is the same at 221 mm², yielding a transistor density of 11.5M per mm². The 770M and 765M also share the same API support: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. Both are MXM modules with MXM-B (3.0) bus interfaces, consume 75 W TDP, and require no power connectors. Display outputs are listed as portable device dependent for both.

The differences emerge in the execution resources and memory subsystem. The GTX 770M packs 960 shading units, 80 texture mapping units, and 24 raster output units. The GTX 765M is trimmed down to 768 shading units, 64 TMUs, and 16 ROPs. That is a 25 percent reduction in shader count and a similar cut in texture units, while the ROP count drops by one-third. These are structural differences that directly affect fill rate and texture throughput.

Clock speeds tell an interesting story. The GTX 765M actually runs higher clocks: its base is 797 MHz and boost is 863 MHz, compared to the 770M's 706 MHz base and 797 MHz boost. The 765M is the faster-clocked part, but it cannot overcome the 770M's wider execution engine. The 770M compensates for lower clocks with more hardware.

Memory configuration also diverges sharply. The GTX 770M uses 3 GB of GDDR5 on a 192-bit bus, delivering 96.19 GB/s of bandwidth. The GTX 765M has 2 GB of GDDR5 on a 128-bit bus, yielding 64.13 GB/s. That is a 50 percent wider bus for the 770M and roughly 50 percent more bandwidth. Both run their memory at 1002 MHz with 4 Gbps effective data rate, so the bandwidth gap is purely a function of bus width. The 770M's extra memory capacity also gives it more headroom for high-resolution textures.

Pixel and texture rates follow the hardware configuration. The 770M posts 15.94 GPixel/s and 63.76 GTexel/s, while the 765M manages 13.81 GPixel/s and 55.23 GTexel/s. The 770M leads by about 15.4 percent in pixel rate and 15.4 percent in texture rate. FP32 throughput is 1.530 TFLOPS for the 770M versus 1,325.6 GFLOPS for the 765M, a lead of roughly 15.4 percent for the larger part. The consistency of these margins reflects the shader and ROP scaling between the two.

The GTX 770M also records a Geekbench OpenCL score of 8552 against the 765M's 7176, which aligns with its broader compute resources. The Metal test shows an even larger gap, 3448 versus 2612, suggesting that Metal workloads are particularly sensitive to the 770M's additional shader units and memory bandwidth.

The Verdict

The data points to a straightforward conclusion: the NVIDIA GeForce GTX 770M is the stronger GPU in every head-to-head benchmark recorded. It wins both the Metal and OpenCL tests, and it holds a higher average benchmark score, a higher percentile ranking, and superior memory bandwidth. Users who need maximum performance from a Kepler-era mobile GPU should select the 770M.

The GTX 765M is not without justification, however. It runs at higher clock speeds, which can be beneficial in lightly threaded or latency-sensitive workloads that do not scale with shader count. Its lower memory footprint and narrower bus also mean it draws the same 75 W TDP as the 770M, so it is not more power-efficient in the database's measurements. The 765M does have a Vulkan benchmark score, which the 770M lacks, so for Vulkan-only scenarios the 765M is the only one with verified data.

For gaming and general compute, the 770M's 32 percent lead in Metal and 19.2 percent lead in OpenCL make it the clear choice. For users specifically targeting Vulkan, the 765M at least has a recorded score to reference, even though no direct comparison is possible. In short, the 770M is the performance pick, while the 765M is the fallback for niche API needs.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 770M has an average benchmark score of 6000, while the GTX 765M scores 5501.

Q: How much faster is the GTX 770M in the Geekbench Metal test?

A: The GTX 770M scores 3448 versus 2612 for the GTX 765M, a 32 percent advantage.

Q: What is the memory bandwidth difference between the two?

A: The GTX 770M delivers 96.19 GB/s over a 192-bit bus, while the GTX 765M provides 64.13 GB/s over a 128-bit bus.

Q: Do both GPUs use the same chip and process node?

A: Yes, both use the GK106 chip on the Kepler architecture, fabricated by TSMC on a 28 nm process with 2,540 million transistors.

Q: Which GPU has more shading units?

A: The GTX 770M has 960 shading units, while the GTX 765M has 768, a 25 percent difference.

Q: Does the GTX 765M have any benchmark where it is the only one with a recorded score?

A: Yes, the GTX 765M has a Geekbench Vulkan score of 6714, while the GTX 770M has no recorded Vulkan benchmark in the database.

Head-to-Head Benchmarks

The most decisive single result belongs to the GTX 770M in the Geekbench Metal test. Its score of 3448 against 2612 for the 765M translates to a 32 percent lead, the largest margin in any shared benchmark. This result is consistent with the 770M's hardware advantages: 25 percent more shading units, 33 percent more ROPs, and 50 percent more memory bandwidth. Metal compute kernels often scale with these resources, and the data confirms that the 770M delivers a substantial uplift in this API.

The Geekbench OpenCL test narrows the gap but still favors the 770M. Here the scores are 8552 for the 770M and 7176 for the 765M, a delta of 19.2 percent. OpenCL workloads can be more sensitive to clock speed than raw resource counts, and the 765M runs at a higher base clock (797 MHz versus 706 MHz) and boost clock (863 MHz versus 797 MHz). That clock advantage helps the 765M close some of the distance, but the 770M's wider execution engine and faster memory subsystem keep it ahead.

The remaining benchmark, Geekbench Vulkan, is a one-sided entry. The GTX 765M scores 6714, but the GTX 770M has no recorded Vulkan result. This is not a win for the 765M in the traditional sense, since there is no rival score to beat, but it does mean the 765M is the only one of the two with verified Vulkan performance. For developers or users who prioritize Vulkan compatibility, this is a point in the 765M's favor.

Looking at the broader context, the GTX 770M's average score of 6000 places it in the 35th percentile of all GPUs, with its nearest rival being the AMD Radeon RX 6400 at 6001, a delta of 0 percent. The GTX 765M, at 5501, sits in the 32nd percentile, with the NVIDIA GeForce MX130 at 5508 as its closest competitor, a delta of -0.1 percent. These rival comparisons show that both parts are clustered in the same performance tier, but the 770M sits slightly higher within that tier.

The texture and pixel rate figures reinforce the 770M's dominance. It posts 63.76 GTexel/s and 15.94 GPixel/s, versus 55.23 GTexel/s and 13.81 GPixel/s for the 765M. These are roughly 15 percent improvements, matching the FP32 throughput gap (1.530 TFLOPS versus 1,325.6 GFLOPS). The consistency across these metrics indicates that the 770M's advantage is systemic rather than workload-specific.

In the end, the head-to-head data is unambiguous: the GTX 770M wins both shared benchmarks, and its average score is 499 points higher. The GTX 765M's higher clocks and Vulkan result are its only distinguishing positives. For anyone choosing between these two, the 770M is the superior part in every measurable comparison where both have data.