GPU Comparison

NVIDIA GeForce 920MX and NVIDIA GeForce 830M are two end-of-life mobile graphics solutions built on the same Maxwell architecture, yet benchmark results show a clear performance hierarchy between them. The data indicates that the older GeForce 830M, released in March 2014, outperforms the newer GeForce 920MX, released in March 2016, in every recorded test. Across two Geekbench workloads, the 830M leads by margins ranging from 5.9% to 16.8%, making it the stronger option for compute-oriented tasks despite its higher power draw.

Where Each One Wins

The benchmark results are unambiguous: the NVIDIA GeForce 830M wins both recorded head-to-head tests, giving it a 2-0 victory in the comparison. The 920MX does not secure a single win in any benchmark category. In the Geekbench OpenCL test, the 830M scores 4324 against the 920MX’s 4068, a 5.9% advantage. The gap widens considerably in the Geekbench Vulkan test, where the 830M achieves 3590 compared to the 920MX’s 2987, a 16.8% lead. This pattern suggests that the 830M is particularly stronger in scenarios that rely on modern graphics API performance, while its advantage in raw compute is more modest but still consistent.

Looking at average benchmark scores, the 830M posts 3957 versus 3528 for the 920MX, reinforcing its overall performance superiority. The percentile rankings also favor the 830M, which sits at the 24th percentile among all GPUs, while the 920MX ranks at the 21st percentile. For users prioritizing compute workloads, the 830M is the clear choice. The 920MX, however, does not offer any compensating advantage in the benchmark data, it loses in both OpenCL and Vulkan, making it difficult to recommend for any performance-focused task based on these numbers.

Architecture Differences

Both GPUs share the same fundamental architecture, process node, and die characteristics. They are built on NVIDIA’s Maxwell architecture and manufactured by TSMC on a 28 nm process. Each chip contains 1,020 million transistors on a 77 mm² die, yielding a transistor density of 13.2 million transistors per square millimeter. The memory subsystems are identical as well: both feature 2 GB of DDR3 memory on a 64-bit bus with a bandwidth of 14.40 GB/s, and both operate at a memory clock of 900 MHz with 1800 Mbps effective speed.

The differences emerge in the chip design and clock speeds. The 920MX uses the GM108S chip, while the 830M uses the GM108 chip. The 920MX has a base clock of 965 MHz and a boost clock of 993 MHz, whereas the 830M runs significantly faster at 1082 MHz base and 1150 MHz boost. This clock advantage is partially offset by the 920MX having more texture mapping units, 24 versus 16 for the 830M. Both GPUs have 256 shading units and 8 ROPs. The higher TMU count on the 920MX does not compensate for its lower clocks, as evidenced by the texture rates: the 920MX achieves 23.83 GTexel/s, while the 830M reaches only 18.40 GTexel/s, the 920MX actually wins this metric. However, the 830M holds the edge in pixel rate at 9.200 GPixel/s versus 7.944 GPixel/s, and in FP32 compute at 588.8 GFLOPS versus 508.4 GFLOPS.

Power consumption differs markedly. The 920MX has a TDP of 16 W and uses an MXM Module slot width, while the 830M has a 33 W TDP and uses an IGP form factor. Neither requires external power connectors. Both support the same APIs: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The 920MX belongs to the GeForce 900M generation with the GeForce 800M as its predecessor and GeForce 10 Mobile as its successor, while the 830M belongs to the GeForce 800M generation with the GeForce 700M as its predecessor and GeForce 900M as its successor.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce 830M has a higher average benchmark score of 3957, compared to 3528 for the NVIDIA GeForce 920MX.

Q: How much faster is the 830M in the Geekbench Vulkan test?

A: The 830M scores 3590 in Geekbench Vulkan, while the 920MX scores 2987. This represents a 16.8% advantage for the 830M.

Q: Do both GPUs use the same memory configuration?

A: Yes, both the 920MX and 830M feature 2 GB of DDR3 memory on a 64-bit bus with 14.40 GB/s bandwidth and 900 MHz memory clock.

Q: What are the clock speed differences between the two?

A: The 920MX has a base clock of 965 MHz and a boost clock of 993 MHz. The 830M runs at 1082 MHz base and 1150 MHz boost, making it faster in both metrics.

Q: Which GPU has more texture mapping units?

A: The 920MX has 24 TMUs, while the 830M has only 16 TMUs. This gives the 920MX a higher texture rate of 23.83 GTexel/s versus 18.40 GTexel/s.

Q: How do their power requirements compare?

A: The 920MX has a TDP of 16 W, while the 830M has a TDP of 33 W. The 920MX uses an MXM Module slot, whereas the 830M uses an IGP form factor.

Specification Differences

| Specification | NVIDIA GeForce 920MX | NVIDIA GeForce 830M |

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

| Chip | GM108S | GM108 |

| Generation | GeForce 900M | GeForce 800M |

| Base Clock | 965 MHz | 1082 MHz |

| Boost Clock | 993 MHz | 1150 MHz |

| TMUs | 24 | 16 |

| Pixel Rate | 7.944 GPixel/s | 9.200 GPixel/s |

| Texture Rate | 23.83 GTexel/s | 18.40 GTexel/s |

| FP32 | 508.4 GFLOPS | 588.8 GFLOPS |

| TDP | 16 W | 33 W |

| Slot Width | MXM Module | IGP |

| Release Date | 2016-03-24 | 2014-03-11 |

| Predecessor | GeForce 800M | GeForce 700M |

| Successor | GeForce 10 Mobile | GeForce 900M |

The table above lists only the fields where the two GPUs differ. All other specifications, including process node, foundry, transistor count, die size, memory size, memory type, bus width, bandwidth, shading units, ROPs, power connectors, bus interface, display outputs, and API support, are identical between the two.

Head-to-Head Benchmarks

The Geekbench OpenCL test establishes the baseline for comparison. The 830M scores 4324, while the 920MX trails at 4068. This 5.9% difference is the smaller of the two gaps, suggesting that raw compute performance favors the 830M but not by an overwhelming margin. The 830M’s higher clock speeds likely contribute to this result, as both GPUs share the same 256 shading units and 8 ROPs.

The Geekbench Vulkan test reveals a much larger divide. Here, the 830M achieves 3590, while the 920MX manages only 2987. The 16.8% delta indicates that the 830M is significantly more efficient in Vulkan workloads. This could be attributed to its higher boost clock of 1150 MHz versus 993 MHz, which allows better sustained performance in API-level tasks. The 920MX’s additional TMUs do not help in this test, as Vulkan performance appears more dependent on clock speed and compute throughput.

The average benchmark scores provide additional context. The 830M’s average of 3957 places it in the 24th percentile of all GPUs, with its nearest rivals being the AMD Radeon R5 M420 at 3956 (0% delta), NVIDIA GeForce GT 745M at 3953 (0.1% delta), NVIDIA Quadro K2000 at 3964 (-0.2% delta), and AMD Radeon HD 6850 X2 at 3977 (-0.5% delta). The 920MX’s average of 3528 puts it in the 21st percentile, with its nearest rivals including the NVIDIA GeForce GT 545 at 3594 (-1.8% delta), NVIDIA RTX 5000 Mobile Ada Generation at 3596 (-1.9% delta), NVIDIA GeForce GT 735M at 3616 (-2.4% delta), and NVIDIA Quadro 2000M at 3434 (2.7% delta). The 920MX’s rivals show that it sits in a lower performance tier overall, while the 830M’s rivals cluster much closer to its own score.

The Verdict

The data clearly favors the NVIDIA GeForce 830M across all benchmark categories. It wins both head-to-head tests, holds a higher average benchmark score, and ranks in a higher percentile among all GPUs. For users who need maximum compute performance from a Maxwell-based mobile GPU, the 830M is the obvious choice. Its 16.8% lead in Vulkan performance is particularly notable, as it suggests better responsiveness in modern graphics workloads.

The NVIDIA GeForce 920MX, despite being released two years later and belonging to a newer generation, does not offer any performance advantage in the recorded data. Its lower power draw of 16 W versus 33 W may appeal to users prioritizing energy efficiency over performance, and its higher TMU count gives it a better texture rate. However, in every benchmark where the two are directly compared, the 920MX comes up short. Users who already own a device with an 830M have no reason to upgrade based on performance alone, while those choosing between the two for a new system should select the 830M if benchmark scores are the primary consideration. The 920MX’s only defensible position is in scenarios where power consumption is critical and performance is secondary, but even then, the 830M’s substantial lead in Vulkan and consistent advantage in OpenCL make it the stronger overall product.