NVIDIA GeForce GT 745M vs NVIDIA GeForce GT 755M Comparison

The NVIDIA GeForce GT 755M and the GT 745M are two closely related Kepler-based mobile graphics processors from the GeForce 700M generation. Both are built for laptops, but the benchmark data reveals a clear performance hierarchy: the GT 755M wins both head-to-head tests, with its largest advantage coming in OpenCL compute workloads. The GT 755M posts an average benchmark score of 4033, placing it in the 24th percentile of all GPUs, while the GT 745M averages 3953, sitting just one percentile lower at 23rd. These are modest mobile parts by modern standards, but the delta between them is significant enough to matter for users choosing between two otherwise similar laptops.

The Verdict

The data points to a straightforward recommendation: the GT 755M is the stronger option in every measured scenario. It wins the Geekbench Metal test with a score of 3132 against 2777 for the GT 745M, a 12.8% advantage. The gap widens dramatically in Geekbench OpenCL, where the GT 755M scores 4934 versus 3580, a 37.8% lead. If your workload involves OpenCL acceleration—common in video editing, rendering, or compute tasks—the GT 755M is the clear choice.

The GT 745M is not without a niche. Its lower thermal footprint, with a TDP of 45 W compared to the GT 755M's 50 W, makes it a better fit for thinner, lighter notebooks where power draw and heat dissipation are tighter constraints. For users who prioritize battery life and quieter operation over raw compute throughput, the GT 745M remains a viable option. However, for anyone who plans to run GPU-accelerated applications or play games, the GT 755M's benchmark wins justify its slightly higher power requirement. In short: pick the GT 755M for performance, pick the GT 745M for a marginally more efficient package.

Where Each One Wins

The GT 755M dominates in both benchmark categories recorded. Its Geekbench Metal score of 3132 outperforms the GT 745M's 2777, indicating better performance in Apple's Metal graphics API, which is relevant for macOS applications and certain cross-platform games. The OpenCL result is even more lopsided: 4934 versus 3580. This 37.8% delta suggests the GT 755M has a substantial advantage in general-purpose GPU computing, which includes tasks like image processing, scientific simulations, and machine learning inference.

The GT 745M's only "win" is in the thermal envelope. Its 45 W TDP is 5 W lower than the GT 755M's 50 W, which can translate to less heat generation and potentially longer battery life in a laptop. The GT 745M also has no recorded boost clock in the data, whereas the GT 755M lists a base clock of 980 MHz and a boost of 1020 MHz—this clock speed advantage is a primary driver of its benchmark superiority. Neither card has a win in the head-to-head benchmark table; the GT 755M takes both tests, with winsA equal to 2 and winsB equal to 0.

Architecture Differences

Both GPUs share the same fundamental architecture, which makes their performance gap especially interesting. They are both built on NVIDIA's Kepler architecture using the GK107 chip, fabricated on a 28 nm process at TSMC. The transistor count is identical at 1,270 million, and the die size is the same at 118 mm², yielding a transistor density of 10.8 million transistors per square millimeter.

The core configuration is also identical on paper: 384 shading units, 32 texture mapping units, and 16 raster operation units. Neither card supports ray tracing or tensor cores. Both have 2 GB of GDDR5 memory on a 128-bit bus, and both support PCIe 3.0 x16. The API support matches as well, with both offering DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.

The differences emerge in clock speeds and memory timing. The GT 755M runs at a base clock of 980 MHz with a boost of 1020 MHz, while the GT 745M has no base or boost clock listed in the data. This clock disparity drives the compute metrics: the GT 755M achieves 783.4 GFLOPS of FP32 performance and a texture rate of 32.64 GTexel/s, while the GT 745M manages only 421.6 GFLOPS and 17.57 GTexel/s. The pixel rates tell a similar story: 8.160 GPixel/s for the GT 755M versus 4.392 GPixel/s for the GT 745M.

Memory bandwidth also differs significantly. The GT 755M runs its GDDR5 at 1350 MHz, translating to 5.4 Gbps effective and 86.40 GB/s of bandwidth. The GT 745M's memory is clocked at 1000 MHz, or 4 Gbps effective, yielding 64.00 GB/s. This 35% bandwidth advantage for the GT 755M is a key factor in its OpenCL dominance. The GT 745M is classified as an IGP (integrated graphics processor) in the slot width field, while the GT 755M uses an MXM module—this suggests different physical integration approaches in laptops. Neither card has a launch MSRP listed.

FAQ

Q: Which GPU is faster in Geekbench Metal?

A: The GT 755M scores 3132, which is 12.8% higher than the GT 745M's 2777.

Q: How large is the OpenCL performance gap?

A: The GT 755M scores 4934 in Geekbench OpenCL, a 37.8% advantage over the GT 745M's 3580.

Q: Do both cards have the same memory configuration?

A: Yes, both have 2 GB of GDDR5 on a 128-bit bus, but the GT 755M runs at 1350 MHz (86.40 GB/s) versus the GT 745M's 1000 MHz (64.00 GB/s).

Q: Are the architectures identical?

A: Both use the GK107 chip on Kepler architecture with 384 shading units, but the GT 755M has higher clocks (980/1020 MHz) versus the GT 745M's unlisted base/boost clocks.

Q: Which card has a lower power draw?

A: The GT 745M has a TDP of 45 W, while the GT 755M draws 50 W.

Q: What is the average benchmark score difference?

A: The GT 755M averages 4033, while the GT 745M averages 3953, a difference of 80 points (roughly 2%).

Head-to-Head Benchmarks

The direct comparison between these two GPUs is unambiguous. In Geekbench Metal, the GT 755M scores 3132 against the GT 745M's 2777. This 12.8% delta is substantial for a single benchmark, indicating that the GT 755M handles Metal-optimized workloads—such as those found in macOS applications or games using Metal rendering—noticeably better. The GT 755M's higher clock speeds and memory bandwidth are the likely contributors to this lead.

The Geekbench OpenCL test reveals an even more pronounced separation. The GT 755M posts 4934, while the GT 745M trails at 3580. That 37.8% delta is the single largest performance difference between the two cards in any metric. OpenCL is a compute-oriented API used for general-purpose GPU programming, so this result suggests the GT 755M is markedly superior for tasks like video transcoding, physics simulations, or data-parallel workloads. The GT 755M's memory bandwidth of 86.40 GB/s versus 64.00 GB/s likely plays a critical role here, as compute kernels are often memory-bound.

Looking at the broader competitive landscape, the GT 755M's average score of 4033 places it near the AMD FirePro M4150 (4013, a 0.5% delta) and just below the Intel HD Graphics 630 (4075, a -1% delta). The AMD Radeon RX 9060 XT 8 GB (4093) is only 1.5% ahead of the GT 755M, which is surprising given that the RX 9060 XT is a far more modern part. The GT 745M, meanwhile, sits in a cluster with the AMD Radeon R5 M420 (3956, -0.1% delta), NVIDIA GeForce 830M (3957, -0.1%), and NVIDIA Quadro K2000 (3964, -0.3%). The GT 745M is effectively neck-and-neck with these rivals, while the GT 755M has a small but consistent edge over its own peers. In the head-to-head, the GT 755M wins both tests, bringing the final tally to 2 wins for the GT 755M and 0 for the GT 745M.