NVIDIA GeForce GTX 770M vs NVIDIA GeForce GTX 980M Comparison

Head-to-Head Benchmarks

The database contains one directly comparable benchmark between these two mobile graphics processors, and the result is decisive. In the Geekbench OpenCL compute test, the NVIDIA GeForce GTX 980M scores 23,832 points, while the NVIDIA GeForce GTX 770M scores 8,552 points. This represents a 64.1% advantage for the GTX 980M, making it the clear winner in raw compute throughput. The GTX 770M trails significantly, and the delta is large enough that no other recorded test is needed to establish the overall performance hierarchy between these two parts.

The OpenCL score reflects general-purpose GPU compute workloads, which are often a proxy for how well a GPU handles tasks like video encoding, physics simulations, and certain rendering tasks. The GTX 980M’s result is nearly three times higher, indicating that it can handle substantially heavier compute loads. For gaming, while no direct DirectX or Vulkan head-to-head tests exist in the database, the compute advantage strongly correlates with higher frame rates in modern titles that leverage GPU compute for post-processing and physics.

Looking at the GTX 980M’s broader benchmark suite, it posts a PassMark G3D score of 7,338, a PassMark GPU Compute score of 2,816, and a Geekbench Vulkan score of 17,703. The GTX 770M’s only other recorded benchmark is its Geekbench Metal score of 3,448, which is not directly comparable to the GTX 980M’s results due to differing test conditions. However, the OpenCL head-to-head is unambiguous: the GTX 980M outperforms the GTX 770M by a wide margin.

The average benchmark score across all recorded tests tells a similar story. The GTX 770M averages 6,000 points, while the GTX 980M averages 5,308 points. This apparent contradiction, where the GTX 980M has a lower average despite winning the head-to-head, is explained by the composition of the benchmark suites. The GTX 770M has only two recorded scores, both from Geekbench tests that tend to produce high numbers. The GTX 980M has ten recorded scores, including several PassMark tests with smaller numerical values (such as 35 for DirectX 10 and 31 for DirectX 12), which drag down its arithmetic average. The single directly comparable test, however, is what matters for a head-to-head comparison, and that test clearly favors the GTX 980M.

In terms of percentile ranking, the GTX 770M sits in the 35th percentile of all GPUs in the database, while the GTX 980M sits in the 31st percentile. These rankings are based on average scores, not the head-to-head result, so they do not contradict the OpenCL finding. Instead, they reflect that both parts are mid-range mobile solutions by modern standards, with the GTX 980M’s average being pulled down by its larger number of lower-magnitude test scores.

The Verdict

The data makes one conclusion straightforward: the NVIDIA GeForce GTX 980M is the stronger performer in compute-heavy workloads. The 64.1% lead in Geekbench OpenCL is substantial and consistent with the GTX 980M’s newer architecture and larger silicon. For any user running applications that utilize OpenCL, whether for content creation, scientific computing, or GPU-accelerated rendering, the GTX 980M is the superior choice.

However, the average benchmark scores and percentile rankings introduce nuance. The GTX 770M’s average score of 6,000 places it ahead of the GTX 980M’s 5,308 average, and its 35th percentile ranking is four points higher. This is primarily a function of the GTX 980M having a broader, more demanding test suite. The GTX 980M’s PassMark DirectX 9 score of 125, DirectX 11 score of 57, and DirectX 10 score of 35 are all relatively low numbers that lower its average, even though its DirectX 12 score of 31 is similarly modest. The GTX 770M simply does not have equivalent low-scoring tests recorded.

For gaming, the GTX 980M’s higher clock speeds, more shading units, and larger memory bus suggest it should deliver better frame rates, but the database does not include a direct gaming benchmark comparison. The user should weigh the head-to-head OpenCL result heavily, as it is the only apples-to-apples measurement available.

In practical terms, the GTX 980M is the pick for users who need maximum compute performance in a mobile platform. It offers 1,536 shading units compared to the GTX 770M’s 960, 96 texture mapping units versus 80, and 64 raster output units versus 24. The GTX 980M also has 8 GB of GDDR5 memory on a 256-bit bus, delivering 160.4 GB/s of bandwidth, versus the GTX 770M’s 3 GB on a 192-bit bus at 96.19 GB/s. These are not speculative advantages; they are recorded specifications that directly impact compute and rendering performance.

The GTX 770M is not without merit. Its 75 W TDP is modest, and its 28 nm process node matches the GTX 980M. For older games or less demanding applications, it remains a functional mobile GPU. But the benchmark data shows a clear generational leap: the GTX 980M’s OpenCL score is more than 2.7 times higher, and its pixel rate of 72.13 GPixel/s dwarfs the GTX 770M’s 15.94 GPixel/s. The GTX 980M also achieves a texture rate of 108.2 GTexel/s versus 63.76 GTexel/s.

The verdict is simple: choose the GTX 980M for performance, especially in compute and modern workloads. Choose the GTX 770M only if the system is already equipped with it and the workload is light, or if power draw is an absolute constraint, though the GTX 980M’s TDP is not recorded in the database.

FAQ

Q: Which GPU is faster in the only directly comparable benchmark?

A: The NVIDIA GeForce GTX 980M wins the Geekbench OpenCL test with a score of 23,832 versus the GTX 770M’s 8,552, a 64.1% advantage.

Q: Why does the GTX 770M have a higher average benchmark score than the GTX 980M?

A: The GTX 770M has only two recorded scores, both from Geekbench tests with high numerical values, giving it an average of 6,000. The GTX 980M has ten recorded scores, including several PassMark tests with lower numerical values, bringing its average to 5,308. The head-to-head OpenCL test, however, favors the GTX 980M.

Q: What are the memory specifications for each GPU?

A: The GTX 770M has 3 GB of GDDR5 memory on a 192-bit bus with 96.19 GB/s bandwidth. The GTX 980M has 8 GB of GDDR5 on a 256-bit bus with 160.4 GB/s bandwidth.

Q: Which GPU has more shading units and texture mapping units?

A: The GTX 980M has 1,536 shading units and 96 TMUs. The GTX 770M has 960 shading units and 80 TMUs.

Q: Are both GPUs based on the same manufacturing process?

A: Yes, both use a 28 nm process node from TSMC.

Q: What is the DirectX support level for each GPU?

A: The GTX 770M supports DirectX 12 (11_0), while the GTX 980M supports DirectX 12 (12_1). The GTX 980M also records a higher Vulkan version, 1.4, versus the GTX 770M’s 1.2.175.

Specification Differences

The two GPUs differ in nearly every measurable specification. The GTX 770M uses the GK106 chip with the Kepler architecture, while the GTX 980M uses the GM204 chip with the Maxwell 2.0 architecture. The GTX 770M has a base clock of 706 MHz and a boost clock of 797 MHz, while the GTX 980M runs at 1,038 MHz base and 1,127 MHz boost. Memory clocks also differ: the GTX 770M operates at 1,002 MHz (4 Gbps effective), and the GTX 980M at 1,253 MHz (5 Gbps effective).

Memory capacity and bandwidth are significantly different. The GTX 770M offers 3 GB of GDDR5 on a 192-bit bus, delivering 96.19 GB/s. The GTX 980M offers 8 GB on a 256-bit bus, delivering 160.4 GB/s. The compute resources also diverge: the GTX 770M has 960 shading units, 80 TMUs, and 24 ROPs, while the GTX 980M has 1,536 shading units, 96 TMUs, and 64 ROPs.

Pixel and texture rates reflect the hardware differences. The GTX 770M achieves 15.94 GPixel/s and 63.76 GTexel/s, while the GTX 980M achieves 72.13 GPixel/s and 108.2 GTexel/s. Floating-point performance (FP32) is 1.530 TFLOPS for the GTX 770M versus 3.462 TFLOPS for the GTX 980M.

The GTX 770M has a TDP of 75 W, while the GTX 980M’s TDP is not recorded in the database. Both use MXM modules with MXM-B (3.0) interfaces, have no power connectors, and have portable-device-dependent display outputs. The GTX 770M belongs to the GeForce 700M generation, released on 2013-05-29, while the GTX 980M is from the GeForce 900M generation, released on 2014-10-06. Both are end-of-life products.

Architecture Differences

The architectural gap between these two GPUs is substantial. The GTX 770M is built on the Kepler architecture, specifically the GK106 chip, while the GTX 980M uses the Maxwell 2.0 architecture with the GM204 chip. Both are manufactured on a 28 nm TSMC process, but the transistor counts differ dramatically: the GTX 770M has 2,540 million transistors on a 221 mm² die, while the GTX 980M has 5,200 million transistors on a 398 mm² die. The transistor density is 11.5M per mm² for the GTX 770M and 13.1M per mm² for the GTX 980M, indicating a more efficient layout in the newer chip.

Kepler and Maxwell 2.0 represent two distinct design philosophies. Kepler was NVIDIA’s first architecture to emphasize power efficiency per core, while Maxwell 2.0 refined that approach with improved scheduling and reduced per-core power draw. The GTX 980M’s higher clock speeds, despite a larger die, suggest the Maxwell 2.0 architecture was more efficient at the same process node. The GTX 980M also supports a newer DirectX feature level (12_1 versus 11_0) and a higher Vulkan version (1.4 versus 1.2.175), indicating better support for modern graphics APIs.

The memory subsystem differs not just in capacity but also in bus width, which affects how much data can be moved to and from the GPU. The GTX 980M’s 256-bit bus is 33% wider than the GTX 770M’s 192-bit bus, and its effective memory clock is higher (5 Gbps versus 4 Gbps). This combination yields a 67% increase in bandwidth, which is critical for high-resolution textures and compute workloads.

Neither GPU has ray tracing cores or tensor cores, as those features appeared in later architectures. Both are traditional rasterization-focused designs. The GTX 980M’s ROP count of 64 versus 24 is a major difference, directly explaining its much higher pixel rate. The GTX 770M’s 75 W TDP is recorded, while the GTX 980M’s is absent, but the latter’s larger die and higher clock speeds imply a higher power draw. Both use MXM-B (3.0) bus interfaces and have no external power connectors, meaning they are designed for laptop or small-form-factor implementations.

The release dates place these GPUs about 17 months apart, and the architectural leap is clear. Kepler was first introduced in desktop GPUs in 2012, while Maxwell 2.0 debuted in 2014. The GTX 980M’s successor is listed as GeForce 10 Mobile, while the GTX 770M’s successor is GeForce 800M, further confirming the generational progression. The GTX 770M’s predecessor is GeForce 600M, and the GTX 980M’s predecessor is GeForce 800M, showing each part sits at a different point in NVIDIA’s mobile lineup.

Overall, the architecture differences explain the benchmark results. The GTX 980M is a larger, more modern chip with more compute resources, higher clocks, and a wider memory bus. The GTX 770M is a smaller, older design that, while capable, cannot match the newer GPU’s throughput. The database’s single head-to-head result, a 64.1% win for the GTX 980M, is consistent with these architectural advantages.