AMD Radeon HD 6850 X2 vs NVIDIA GeForce 920MX Comparison

The NVIDIA GeForce 920MX and the AMD Radeon HD 6850 X2 represent two very different approaches to graphics hardware, separated by five years of architectural evolution. The data shows a single direct benchmark comparison, but the specifications reveal stark contrasts in design philosophy, power requirements, and intended use cases.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test, where the NVIDIA GeForce 920MX scores 4,068 against the AMD Radeon HD 6850 X2's 3,977. This gives the 920MX a 2.3% lead, a narrow margin that places both cards in a similar performance tier despite their vastly different underlying designs. The 920MX wins the sole head-to-head matchup, taking 1 win while the HD 6850 X2 records 0 wins.

Contextualizing these scores through their nearest rivals helps clarify the competitive landscape. The 920MX's average benchmark score of 3,528 places it at the 21st percentile of all GPUs. Its closest rival, the NVIDIA GeForce GT 545, scores 3,594, which is 1.8% higher. The NVIDIA RTX 5000 Mobile Ada Generation scores 3,596, 1.9% higher, and the GeForce GT 735M scores 3,616, 2.4% higher. On the other side, the Quadro 2000M scores 3,434, which is 2.7% lower than the 920MX's average. This positions the 920MX in a tight cluster where small percentage differences separate competitors.

The HD 6850 X2's average benchmark score of 3,977 sits at the 24th percentile of all GPUs, slightly higher than the 920MX's percentile ranking. Its nearest rival is the NVIDIA Quadro K2000 at 3,964, a mere 0.3% difference. The GeForce 830M scores 3,957, 0.5% lower, while the Radeon R5 M420 and GeForce GT 745M score 3,956 and 3,953 respectively, both 0.5% and 0.6% lower. The HD 6850 X2's rival cluster shows an even tighter grouping, with all four competitors within 0.6% of its score.

The 2.3% delta between the two cards in direct comparison is consistent with their percentile standings. The HD 6850 X2's higher percentile rank (24 vs. 21) suggests it has a slight edge in the broader GPU population, yet the head-to-head result favors the 920MX. This apparent contradiction is explained by the different benchmark sets: the HD 6850 X2 has only one recorded benchmark (OpenCL at 3,977), while the 920MX has two (OpenCL at 4,068 and Vulkan at 2,987), with the Vulkan score dragging down its average substantially.

Architecture Differences

The architectural gulf between these two GPUs is considerable. The NVIDIA GeForce 920MX uses the GM108S chip built on the Maxwell architecture, fabricated on a 28 nm process at TSMC. It contains 1,020 million transistors on a 77 mm² die, yielding a transistor density of 13.2 million transistors per square millimeter. This is a mobile-first design from the GeForce 900M generation, released in 2016, and represents the efficiency-focused end of the Maxwell lineup.

In contrast, the AMD Radeon HD 6850 X2 uses the Barts chip based on the TeraScale 2 architecture, fabricated on a 40 nm process, also at TSMC. This older design packs 1,700 million transistors onto a 255 mm² die, resulting in a transistor density of just 6.7 million per square millimeter. The HD 6850 X2 belongs to the Northern Islands generation (HD 6800 series), released in 2011, and targets desktop performance rather than mobile efficiency.

The memory subsystems diverge sharply. The 920MX uses 2 GB of DDR3 memory on a 64-bit bus, delivering 14.40 GB/s of bandwidth. Its memory clock runs at 900 MHz, translating to 1800 Mbps effective. The HD 6850 X2 also has 2 GB of memory, but uses GDDR5 on a 256-bit bus, achieving 134.4 GB/s of bandwidth — more than nine times the 920MX's throughput. Its memory operates at 1050 MHz, or 4.2 Gbps effective.

Compute resources favor the AMD card substantially. The HD 6850 X2 has 960 shading units, 48 texture mapping units, and 32 ROPs, compared to the 920MX's 256 shading units, 24 TMUs, and 8 ROPs. The result is a pixel rate of 25.60 GPixel/s and a texture rate of 38.40 GTexel/s for the HD 6850 X2, versus 7.944 GPixel/s and 23.83 GTexel/s for the 920MX. In raw FP32 throughput, the HD 6850 X2 delivers 1.536 TFLOPS, triple the 920MX's 508.4 GFLOPS.

The power envelope tells the opposite story. The 920MX has a TDP of just 16 W, requires no power connectors, and uses an MXM module slot. The HD 6850 X2 demands 254 W, needs two 8-pin power connectors, a 600 W suggested PSU, and occupies a dual-slot form factor. The 920MX connects via PCIe 3.0 x8, while the HD 6850 X2 uses PCIe 2.0 x16. Display outputs also differ: the 920MX is "portable device dependent," while the HD 6850 X2 offers 2x DVI, 1x HDMI 1.3a, and 1x DisplayPort 1.1.

API support reflects their respective eras. The 920MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4, while the HD 6850 X2 supports DirectX 11.2 (11_0), OpenGL 4.4, and no Vulkan support at all.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The AMD Radeon HD 6850 X2 delivers 1.536 TFLOPS of FP32 performance, exactly three times the 508.4 GFLOPS of the NVIDIA GeForce 920MX.

Q: Why does the 920MX win the only direct benchmark despite lower specifications?

A: The Geekbench OpenCL score favors the 920MX at 4,068 versus 3,977 for the HD 6850 X2, a 2.3% margin. The 920MX's Maxwell architecture and newer process node may offset the HD 6850 X2's larger compute resources in this specific workload.

Q: How do their power requirements compare?

A: The 920MX has a 16 W TDP with no power connectors, while the HD 6850 X2 has a 254 W TDP with two 8-pin connectors and a 600 W suggested PSU — a 16x difference in thermal design power.

Q: What memory bandwidth does each card provide?

A: The HD 6850 X2 offers 134.4 GB/s via GDDR5 on a 256-bit bus, while the 920MX provides 14.40 GB/s via DDR3 on a 64-bit bus.

Q: Which card supports newer graphics APIs?

A: The 920MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The HD 6850 X2 is limited to DirectX 11.2 (11_0) and OpenGL 4.4, with no Vulkan support.

Q: How do their release dates and production statuses compare?

A: The 920MX was released in March 2016 and is end-of-life, succeeding the GeForce 800M and preceding GeForce 10 Mobile. The HD 6850 X2 was released in September 2011, is also end-of-life, and succeeds Evergreen while preceding Southern Islands.

The Verdict

The data presents a clear choice based on use case. For anyone needing a low-power, mobile-capable GPU with modern API support, the NVIDIA GeForce 920MX is the only reasonable option. Its 16 W TDP, MXM form factor, and no power connector requirement make it suitable for portable devices. The Vulkan 1.4 support and OpenGL 4.6 compatibility ensure access to contemporary software stacks.

For desktop users with adequate power delivery and a need for maximum raw throughput, the AMD Radeon HD 6850 X2 offers triple the FP32 performance, more than nine times the memory bandwidth, and significantly higher pixel and texture rates. The 254 W TDP and dual-slot design are acceptable trade-offs for users prioritizing compute density over efficiency.

The benchmark scores, however, indicate that these theoretical advantages do not translate into proportional real-world gains. The HD 6850 X2's 3,977 OpenCL score is only 2.3% behind the 920MX's 4,068, despite the massive specification differences. This suggests that the 920MX's newer architecture extracts more practical performance from its limited resources. The 920MX's 21st percentile and the HD 6850 X2's 24th percentile rankings confirm they occupy similar performance strata overall.

Specification Differences

| Specification | NVIDIA GeForce 920MX | AMD Radeon HD 6850 X2 |

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

| Chip | GM108S | Barts |

| Architecture | Maxwell | TeraScale 2 |

| Generation | GeForce 900M | Northern Islands (HD 6800) |

| Process Node | 28 nm | 40 nm |

| Transistors | 1,020 million | 1,700 million |

| Die Size | 77 mm² | 255 mm² |

| Transistor Density | 13.2M / mm² | 6.7M / mm² |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 64 bit | 256 bit |

| Memory Bandwidth | 14.40 GB/s | 134.4 GB/s |

| Shading Units | 256 | 960 |

| TMUs | 24 | 48 |

| ROPs | 8 | 32 |

| Pixel Rate | 7.944 GPixel/s | 25.60 GPixel/s |

| Texture Rate | 23.83 GTexel/s | 38.40 GTexel/s |

| FP32 | 508.4 GFLOPS | 1.536 TFLOPS |

| TDP | 16 W | 254 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 2x 8-pin |

| Suggested PSU | N/A | 600 W |

| Bus Interface | PCIe 3.0 x8 | PCIe 2.0 x16 |

| Display Outputs | Portable Device Dependent | 2x DVI, 1x HDMI 1.3a, 1x DisplayPort 1.1 |

| DirectX | 12 (11_0) | 11.2 (11_0) |

| OpenGL | 4.6 | 4.4 |

| Vulkan | 1.4 | None |

Where Each One Wins

The NVIDIA GeForce 920MX wins in scenarios requiring minimal power draw. Its 16 W TDP versus 254 W makes it the clear choice for battery-powered devices. The lack of power connectors and MXM form factor further reinforce its mobile orientation. It also wins on API modernity, offering Vulkan 1.4 and OpenGL 4.6 support, which the HD 6850 X2 lacks entirely. The 920MX's 28 nm process node and higher transistor density (13.2M / mm² vs. 6.7M / mm²) demonstrate superior manufacturing efficiency.

The AMD Radeon HD 6850 X2 wins decisively on raw compute specifications. Its 1.536 TFLOPS FP32 throughput, 134.4 GB/s memory bandwidth, 960 shading units, and 25.60 GPixel/s pixel rate are all multiples of the 920MX's corresponding figures. The 256-bit memory bus and GDDR5 memory provide a bandwidth advantage that matters for texture-heavy workloads. The dual-slot design with 2x 8-pin power connectors and a 600 W suggested PSU indicates a card built for sustained desktop performance rather than mobility.

The benchmark data complicates this clear-cut split. The 920MX's 2.3% OpenCL victory suggests that architectural efficiency can compensate for massive specification deficits. The 920MX's average benchmark score of 3,528 versus the HD 6850 X2's 3,977 shows the AMD card winning on aggregate, but the 920MX's Vulkan score of 2,987 is not part of the HD 6850 X2's benchmark set, making direct average comparisons incomplete. Ultimately, the 920MX wins for portable, efficient, modern-API workloads, while the HD 6850 X2 wins for desktop compute performance where power is not a constraint.