NVIDIA GeForce 920M vs NVIDIA GeForce GT 755M Comparison

The Verdict

The NVIDIA GeForce GT 755M is the clear performance leader in this comparison. The recorded data shows a decisive advantage in the only shared benchmark, with a 32.5% higher score in Geekbench OpenCL. This places the GT 755M at a 24th percentile ranking across all GPUs, while the GeForce 920M sits at the 20th percentile. The GT 755M's average benchmark score of 4033 substantially outpaces the 920M's 3287, a gap that puts the 920M in a lower competitive tier entirely.

The GeForce 920M is not without its merits, however. It consumes significantly less power, with a 33 W TDP versus the GT 755M's 50 W. This makes the 920M a better fit for ultrathin notebooks where thermal headroom is limited. The 920M also benefits from a newer release date, launching in March 2015 versus June 2013, meaning it arrived later in the mobile product cycle. For users prioritizing battery life over raw compute, the 920M is the sensible pick. For anyone needing the strongest available graphics performance in this pairing, the GT 755M is the only logical choice.

FAQ

Q: Which GPU is faster in the shared Geekbench OpenCL test?

A: The NVIDIA GeForce GT 755M wins decisively, scoring 4934 against the GeForce 920M's 3725, a 32.5% advantage.

Q: How do these two GPUs compare in overall standing relative to all other GPUs?

A: The GT 755M ranks in the 24th percentile of all GPUs, while the 920M ranks in the 20th percentile. Their average benchmark scores are 4033 and 3287, respectively.

Q: Which GPU has the lower power draw?

A: The GeForce 920M has a 33 W TDP, making it more power-efficient than the GT 755M, which has a 50 W TDP.

Q: What memory types do these GPUs use, and does it impact bandwidth?

A: The GT 755M uses GDDR5 memory with a 128-bit bus, delivering 86.40 GB/s of bandwidth. The 920M uses DDR3 memory on a 64-bit bus, yielding only 14.40 GB/s, a massive difference in memory throughput.

Q: Are these GPUs from the same architecture generation?

A: No, despite both being built by TSMC on a 28 nm process. The GT 755M uses the Kepler architecture with the GK107 chip, while the 920M uses Kepler 2.0 with the GK208B chip.

Q: Which GPU has a faster boost clock?

A: The GT 755M has a boost clock of 1020 MHz, while the 920M's boost clock is fixed at 954 MHz, identical to its base clock.

Architecture Differences

The two GPUs share a common manufacturing foundation: both are built by TSMC on a 28 nm process node. However, their internal architectures differ in meaningful ways. The GT 755M is based on the original Kepler architecture, utilizing the GK107 chip. The 920M employs a revised design called Kepler 2.0, built around the GK208B chip. This architectural revision is smaller in physical terms: the GK107 die measures 118 mm² with 1,270 million transistors, while the GK208B is 87 mm² with 1,020 million transistors. Interestingly, the smaller GK208B has a higher transistor density at 11.7M per mm², versus 10.8M per mm² for the GK107.

The shading core counts are identical at 384 shading units and 32 texture mapping units for both GPUs. The key architectural split appears in the render output stage: the GT 755M has 16 ROPs, while the 920M has only 8 ROPs. This halving of ROPs directly contributes to the GT 755M's higher pixel rate of 8.160 GPixel/s versus 7.632 GPixel/s on the 920M. The texture rates follow a similar pattern, with the GT 755M achieving 32.64 GTexel/s against the 920M's 30.53 GTexel/s.

The memory subsystem represents a major architectural divergence. The GT 755M pairs its GK107 chip with GDDR5 memory on a 128-bit bus, achieving 86.40 GB/s of bandwidth. The 920M uses DDR3 memory on a 64-bit bus, resulting in just 14.40 GB/s. This six-fold difference in memory bandwidth is the single largest architectural gap between the two. The GT 755M also operates at a higher boost clock of 1020 MHz versus the 920M's 954 MHz, and its memory runs at 1350 MHz with 5.4 Gbps effective throughput, far exceeding the 920M's 900 MHz and 1800 Mbps effective rate.

Both GPUs support DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175, so API compatibility is identical. Neither GPU features ray tracing cores or tensor cores. The GT 755M connects via PCIe 3.0 x16, while the 920M uses PCIe 3.0 x8, indicating a halved interface width for the newer part.

Specification Differences

The table below highlights only the fields where the two GPUs differ, based on recorded data.

| Specification | GT 755M | 920M |

|---|---|---|

| Architecture | Kepler | Kepler 2.0 |

| Chip | GK107 | GK208B |

| Generation | GeForce 700M | GeForce 900M |

| Transistors | 1,270 million | 1,020 million |

| Die Size | 118 mm² | 87 mm² |

| Transistor Density | 10.8M / mm² | 11.7M / mm² |

| Base Clock | 980 MHz | 954 MHz |

| Boost Clock | 1020 MHz | 954 MHz |

| Memory Clock | 1350 MHz, 5.4 Gbps effective | 900 MHz, 1800 Mbps effective |

| Memory Type | GDDR5 | DDR3 |

| Bus Width | 128 bit | 64 bit |

| Memory Bandwidth | 86.40 GB/s | 14.40 GB/s |

| ROPs | 16 | 8 |

| Pixel Rate | 8.160 GPixel/s | 7.632 GPixel/s |

| Texture Rate | 32.64 GTexel/s | 30.53 GTexel/s |

| FP32 | 783.4 GFLOPS | 732.7 GFLOPS |

| TDP | 50 W | 33 W |

| Slot Width | MXM Module | IGP |

| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x8 |

| Release Date | 2013-06-24 | 2015-03-12 |

| Predecessor | GeForce 600M | GeForce 800M |

| Successor | GeForce 800M | GeForce 10 Mobile |

Head-to-Head Benchmarks

The database contains one directly comparable benchmark between these two GPUs: Geekbench OpenCL. The GT 755M scores 4934, while the 920M scores 3725. This represents a 32.5% advantage for the GT 755M. This single result aligns with the broader performance indicators in the specification data. The GT 755M's FP32 throughput of 783.4 GFLOPS exceeds the 920M's 732.7 GFLOPS, but the margin there is only about 7%. The real separator is memory bandwidth: at 86.40 GB/s versus 14.40 GB/s, the GT 755M has exactly six times the memory throughput. This explains why the OpenCL score gap is so much larger than the raw compute gap, as memory-intensive workloads are heavily penalized on the 920M.

The GT 755M also wins on pixel and texture rates, with 8.160 GPixel/s and 32.64 GTexel/s versus 7.632 GPixel/s and 30.53 GTexel/s on the 920M. These advantages are modest, ranging from 6.9% to 7.3%, but they compound in real-world rendering scenarios. The 920M's sole advantages are efficiency and form factor. Its 33 W TDP is 34% lower than the GT 755M's 50 W, and its IGP slot width contrasts with the MXM Module of the GT 755M, suggesting the 920M is designed for direct motherboard integration rather than modular replacement.

The nearest rival data contextualizes both GPUs within their respective performance neighborhoods. The GT 755M's closest competitors include the AMD FirePro M4150 with an average score of 4013 (0.5% slower), the Intel HD Graphics 630 at 4075 (1% faster), the AMD Radeon HD 6850 X2 at 3977 (1.4% slower), and the AMD Radeon RX 9060 XT 8 GB at 4093 (1.5% faster). This clustering shows the GT 755M sits near a tight group of mid-range parts. The 920M's rivals are lower tier: the NVIDIA GeForce GT 730M at 3316 (0.9% faster), Intel HD Graphics 530 at 3332 (1.4% faster), NVIDIA GeForce GT 640 at 3210 (2.4% slower), and Intel HD Graphics P4600 at 3389 (3% faster). The 920M's average score of 3287 places it below all but one of its nearest rivals, indicating it sits near the bottom of its immediate competitive set.

The benchmark data shows no contest in raw performance. The GT 755M wins the only head-to-head test and holds superior specifications across memory, ROPs, clocks, and fill rates. The 920M counters with lower power consumption and a smaller physical footprint, but these advantages do not translate into any benchmark victories. Users choosing between these two should base their decision on the trade-off between compute capability and power efficiency. The GT 755M delivers 32.5% more OpenCL performance but requires 17 W more power. For notebook designs where battery life is paramount, the 920M is the conservative choice. For any workload that stresses the GPU, the GT 755M is demonstrably superior.