NVIDIA GeForce 945M vs NVIDIA GeForce GTX 850M Comparison

Where Each One Wins

The recorded benchmark data splits cleanly between these two mobile GPUs. The NVIDIA GeForce GTX 850M wins the only shared benchmark test, Geekbench OpenCL, by a decisive margin. Its score of 9821 stands 21.3% above the GeForce 945M's 8099. The GTX 850M also has a Vulkan result of 8782, while the GeForce 945M has no recorded Vulkan score, giving the older chip a broader software compatibility footprint in the database.

For the GeForce 945M, the data does not show any benchmark where it outpaces the GTX 850M. Its average benchmark score of 8099 places it in the 42nd percentile of all GPUs, while the GTX 850M sits at the 46th percentile with an average of 9302. The 945M does have a higher pixel rate and texture rate on paper (16.32 GPixel/s and 40.80 GTexel/s versus 14.43 GPixel/s and 36.08 GTexel/s respectively), but those raw specification advantages do not translate into a benchmark win in the available measurements.

The use-case split is therefore straightforward: for general compute workloads and any Vulkan-based application, the GTX 850M is the stronger choice. The GeForce 945M's higher clock speeds may help in specific scenarios, but the database contains no test where it converts that into a victory.

Architecture Differences

Both GPUs share the same fundamental architecture. The GTX 850M and GeForce 945M are built on NVIDIA's Maxwell architecture, use the GM107 chip, and are fabricated by TSMC on a 28 nm process node. Both have 1,870 million transistors on a 148 mm² die, yielding a transistor density of 12.6 million transistors per square millimeter. The two chips also have identical core configurations: 640 shading units, 40 texture mapping units, and 16 raster output pipelines.

The differences begin with clock speeds. The GeForce 945M records a base clock of 928 MHz and a boost clock of 1020 MHz. The GTX 850M has no base or boost clock listed in the database, so its operating frequency cannot be directly compared. The memory clocks also differ: the GTX 850M runs its DDR3 memory at 1001 MHz with 2 Gbps effective transfer, while the GeForce 945M runs at 900 MHz with 1800 Mbps effective. This produces a memory bandwidth gap, 32.03 GB/s for the GTX 850M versus 28.80 GB/s for the 945M, despite both using 2 GB of DDR3 on a 128 bit bus.

Power and physical specifications diverge more sharply. The GTX 850M has a TDP of 45 W and uses an IGP slot width, meaning it is integrated into the motherboard. The GeForce 945M has a TDP of 75 W and uses an MXM Module slot width with an MXM-B (3.0) bus interface. Neither uses external power connectors, and both are marked as end-of-life products. The GTX 850M was released in March 2014 under the GeForce 800M generation, while the GeForce 945M came later, in October 2015, under the GeForce 900M generation. The 945M's predecessor is listed as the GeForce 800M, which places the GTX 850M in its direct lineage.

The API support is identical for both: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. Neither chip includes ray tracing or tensor cores, which is consistent with their Maxwell generation. The key architectural takeaway is that these are the same silicon with different clock, power, and packaging configurations, and the memory clock difference is the most consequential intern.

The Verdict

The benchmark data points to a clear conclusion: the NVIDIA GeForce GTX 850M is the faster GPU in real-world compute tests, despite being the older design. Its 21.3% lead in Geekbench OpenCL over the GeForce 945M is not a marginal gap; it is a substantial advantage that outweighs the 945M's higher clocks on paper.

The GTX 850M also occupies a better position in the overall performance distribution. Its 46th percentile ranking and average score of 9302 sit above the 945M's 42nd percentile and 8099 average. Looking at the nearest rivals for each card reinforces this: the GTX 850M trades blows with the NVIDIA GeForce GTX 465 (0.1% delta), AMD Radeon R7 M380 (0.1% behind), NVIDIA GeForce GTX 960 (0.3% ahead), and AMD Radeon Vega 8 (0.9% ahead). The GeForce 945M, by contrast, sits alongside the NVIDIA GRID K2 (0.2% delta), AMD Radeon R9 M360 (0.4% behind), NVIDIA GeForce GTX 650 Ti Boost (0.4% ahead), and NVIDIA GeForce GTX 950M (0.4% behind).

Who should pick which? From the data, anyone choosing between these two for compute workloads should take the GTX 850M. It also offers the Vulkan result that the 945M lacks. The GeForce 945M is only preferable if the application is constrained by the specific MXM module form factor or requires the higher 75 W power envelope, but the benchmarks do not reward that choice with better performance. The GTX 850M is the data-backed pick.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The NVIDIA GeForce GTX 850M scores 9821, which is 21.3% higher than the GeForce 945M's 8099.

Q: Do both GPUs use the same architecture?

A: Yes, both are based on the Maxwell architecture with the GM107 chip, fabricated on a 28 nm process with 1,870 million transistors.

Q: What is the memory bandwidth difference?

A: The GTX 850M delivers 32.03 GB/s, while the GeForce 945M delivers 28.80 GB/s. Both use 2 GB of DDR3 on a 128 bit bus.

Q: Which GPU has a Vulkan benchmark result?

A: Only the GTX 850M has a recorded Geekbench Vulkan score, which is 8782. The GeForce 945M has no Vulkan result in the database.

Q: How do the TDP values compare?

A: The GTX 850M has a TDP of 45 W, while the GeForce 945M has a TDP of 75 W.

Q: What are the nearest rivals for each GPU?

A: The GTX 850M's closest rival is the NVIDIA GeForce GTX 465 with a 0.1% delta, while the GeForce 945M's closest rival is the NVIDIA GRID K2 with a 0.2% delta.

Head-to-Head Benchmarks

The database contains one direct head-to-head benchmark between these two GPUs: Geekbench OpenCL. The GTX 850M scores 9821 against the GeForce 945M's 8099, producing a delta of 21.3% in favor of the older card. This is the single largest and most important comparative data point, and it aligns with the GTX 850M's higher memory clock (1001 MHz versus 900 MHz) and resulting bandwidth advantage (32.03 GB/s versus 28.80 GB/s).

The GeForce 945M's counterargument comes from its clock speed and fillrate figures. Its base clock of 928 MHz and boost of 1020 MHz are higher than anything recorded for the GTX 850M, and its pixel rate of 16.32 GPixel/s and texture rate of 40.80 GTexel/s exceed the GTX 850M's 14.43 GPixel/s and 36.08 GTexel/s. Its FP32 throughput of 1,305.6 GFLOPS also beats the GTX 850M's 1,154.6 GFLOPS. Yet none of these theoretical advantages produce a higher benchmark score, which suggests the memory subsystem is the limiting factor for the 945M.

The average benchmark scores tell the same story. The GTX 850M averages 9302 across its two recorded tests, while the GeForce 945M averages 8099 from its single OpenCL result. The percentile rankings also separate the two: 46th for the GTX 850M versus 42nd for the 945M. When placed against comparable GPUs, the GTX 850M is effectively dead even with the GTX 465 and R7 M380, while the 945M is a slight step behind its own closest competitors such as the GTX 950M (0.4% behind) and R9 M360 (0.4% behind).

The only conclusion the head-to-head data supports is that the GTX 850M is the stronger performer in the workload measured. The 945M's higher fillrates and clocks are real specification differences, but they do not manifest as a win in any recorded test.

Specification Differences

The table below lists only the fields where the two GPUs differ in the database.

| Specification | NVIDIA GeForce GTX 850M | NVIDIA GeForce 945M |

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

| Generation | GeForce 800M | GeForce 900M |

| Base clock | Not listed | 928 MHz |

| Boost clock | Not listed | 1020 MHz |

| Memory clock | 1001 MHz, 2 Gbps effective | 900 MHz, 1800 Mbps effective |

| Memory bandwidth | 32.03 GB/s | 28.80 GB/s |

| Pixel rate | 14.43 GPixel/s | 16.32 GPixel/s |

| Texture rate | 36.08 GTexel/s | 40.80 GTexel/s |

| FP32 | 1,154.6 GFLOPS | 1,305.6 GFLOPS |

| TDP | 45 W | 75 W |

| Slot width | IGP | MXM Module |

| Bus interface | PCIe 3.0 x16 | MXM-B (3.0) |

| Release date | 2014-03-11 | 2015-10-26 |

| Predecessor | GeForce 700M | GeForce 800M |

| Successor | GeForce 900M | GeForce 10 Mobile |

| Geekbench OpenCL score | 9821 | 8099 |

| Geekbench Vulkan score | 8782 | Not listed |

| Average benchmark score | 9302 | 8099 |

| Percentile vs all GPUs | 46 | 42 |

The shared specifications include the GM107 chip, Maxwell architecture, 28 nm process, 1,870 million transistors, 148 mm² die size, 640 shading units, 40 TMUs, 16 ROPs, 2 GB DDR3 memory, 128 bit bus, DirectX 12 (11_0), OpenGL 4.6, Vulkan 1.4, no power connectors, and end-of-life production status. Both are NVIDIA parts with no listed launch MSRP. The GTX 850M is the faster card in the benchmark data, while the 945M offers higher theoretical throughput and a newer generation label, but the measurements favor the 850M.