Intel Iris Xe MAX Graphics vs NVIDIA GeForce GTX 950 Comparison

The data presents a clear generational clash: NVIDIA’s GeForce GTX 950, a 2015 discrete desktop card built on Maxwell 2.0, faces off against Intel’s Iris Xe MAX Graphics, a 2020 mobile-class integrated part on the Xe Architecture. While the Intel part is newer, smaller, and far more power-efficient, the benchmark results from the FACT PACK show the GTX 950 maintains a decisive performance advantage in the one test both share.

The Verdict

Based strictly on the available benchmark data, the NVIDIA GeForce GTX 950 is the faster GPU. In the Geekbench OpenCL test, the GTX 950 scores 15,662 points, which is 9.4% higher than the Intel Iris Xe MAX Graphics’ score of 14,315. This is the only head-to-head benchmark available, and the GTX 950 wins it outright. The data shows the GTX 950 also has a higher average benchmark score of 13,189 across all its tests, compared to the Iris Xe MAX’s single-test average of 14,315, though this comparison is skewed by the different number of tests each card has.

However, the choice is not purely about raw speed. The Intel Iris Xe MAX Graphics offers a significantly different value proposition in its physical and power characteristics. With a TDP of just 25 W versus the GTX 950’s 90 W, the Intel part is designed for slim, power-conscious systems, whereas the GTX 950 requires a dual-slot cooler, a 1x 6-pin power connector, and a 250 W suggested PSU. The GTX 950 is also end-of-life with a 202 mm length, making it a legacy desktop part, while the Iris Xe MAX is an integrated GPU (IGP) with no display outputs, meaning it must be paired with a system that has its own output solution.

Who should pick which? A user building a compact, low-power system where every watt counts should look at the Intel Iris Xe MAX Graphics. A user with a desktop chassis that can accommodate a full-length, dual-slot card and who prioritizes raw compute performance in OpenCL workloads should pick the NVIDIA GeForce GTX 950. The GTX 950 is the performance winner, but the Iris Xe MAX is the efficiency and form-factor winner.

Architecture Differences

The two GPUs represent fundamentally different design philosophies and manufacturing generations.

• Process Node and Foundry: The GTX 950 is built on a 28 nm process at TSMC, while the Iris Xe MAX uses Intel’s 10 nm process. This is a stark contrast in manufacturing technology, with Intel’s node being significantly more advanced.
• Chip and Architecture: The NVIDIA part uses the GM206 chip, based on the Maxwell 2.0 architecture. The Intel part uses the DG1 chip, based on the Generation 12.1 architecture (Xe Graphics). These are entirely different GPU microarchitectures from different vendors.
• Die Size and Transistors: The GTX 950 has a die size of 228 mm² and contains 2,940 million transistors, giving it a transistor density of 12.9M / mm². The Iris Xe MAX has a much smaller die at 95 mm²; its transistor count and density are not listed in the data.
• Core Configuration: Both parts have 768 shading units and 48 texture mapping units (TMUs). However, they differ in render output units (ROPs): the GTX 950 has 32 ROPs, while the Iris Xe MAX has 24 ROPs.
• Memory Subsystem: The GTX 950 uses 2 GB of GDDR5 memory on a 128-bit bus, achieving a bandwidth of 105.8 GB/s. The Iris Xe MAX uses 4 GB of LPDDR4X memory, also on a 128-bit bus, but with a lower bandwidth of 68.26 GB/s. The GTX 950’s memory clock is 1653 MHz (6.6 Gbps effective), while the Intel part’s is 2133 MHz (4.3 Gbps effective).
• Clock Speeds: The GTX 950 has a base clock of 1024 MHz and a boost clock of 1188 MHz. The Iris Xe MAX has a significantly lower base clock of 300 MHz but a much higher boost clock of 1650 MHz.
• Compute Capabilities: Despite the GTX 950’s lower clock speeds, it achieves a pixel rate of 38.02 GPixel/s and a texture rate of 57.02 GTexel/s. The Iris Xe MAX has a higher pixel rate of 39.60 GPixel/s and a much higher texture rate of 79.20 GTexel/s. However, the GTX 950’s FP32 performance is 1.825 TFLOPS, while the Iris Xe MAX’s is higher at 2.534 TFLOPS. The Intel part also supports FP16 at 5.069 TFLOPS (2:1), a feature the GTX 950 does not list.
• Interface and Outputs: The GTX 950 uses a PCIe 3.0 x16 interface and offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2 outputs. The Iris Xe MAX uses a PCIe 4.0 x8 interface and has no display outputs, highlighting its role as a co-processor or integrated solution.

FAQ

Q: Which GPU is faster in the available benchmark?

A: The NVIDIA GeForce GTX 950 is faster. In the Geekbench OpenCL test, it scores 15,662 points, which is 9.4% higher than the Intel Iris Xe MAX Graphics’ score of 14,315.

Q: How does the power consumption compare?

A: The Intel Iris Xe MAX Graphics has a TDP of 25 W, which is significantly lower than the NVIDIA GeForce GTX 950’s TDP of 90 W. The GTX 950 also requires a 250 W suggested PSU and a 1x 6-pin power connector, while the Iris Xe MAX has no power connectors listed and a 200 W suggested PSU.

Q: What is the difference in memory capacity and type?

A: The GTX 950 comes with 2 GB of GDDR5 memory, while the Iris Xe MAX comes with 4 GB of LPDDR4X memory. Both have a 128-bit bus, but the GTX 950 has higher bandwidth at 105.8 GB/s compared to the Intel part’s 68.26 GB/s.

Q: Are these GPUs comparable in their physical design?

A: No. The GTX 950 is a dual-slot, 202 mm (8 inches) long discrete card for desktop systems. The Iris Xe MAX is an integrated GPU (IGP) with no display outputs, meaning it is not a standalone card you can install.

Q: How do their overall performance percentiles compare?

A: The Intel Iris Xe MAX Graphics has a higher percentile ranking at 56, compared to the GTX 950’s percentile of 53. This is based on all GPUs in the database, despite the GTX 950 winning the direct head-to-head test.

Q: What are their release dates?

A: The NVIDIA GeForce GTX 950 was released on 2015-08-19, while the Intel Iris Xe MAX Graphics was released much later on 2020-10-30. Both are now end-of-life products.

Specification Differences

The following specifications differ between the two cards, based only on the FACT PACK data:

• Manufacturer: NVIDIA vs. Intel
• Chip: GM206 vs. DG1
• Architecture: Maxwell 2.0 vs. Generation 12.1
• Generation: GeForce 900 vs. Xe Graphics
• Process Node: 28 nm vs. 10 nm
• Foundry: TSMC vs. Intel
• Transistors: 2,940 million vs. (not listed)
• Die Size: 228 mm² vs. 95 mm²
• Transistor Density: 12.9M / mm² vs. (not listed)
• Base Clock: 1024 MHz vs. 300 MHz
• Boost Clock: 1188 MHz vs. 1650 MHz
• Memory Clock: 1653 MHz (6.6 Gbps effective) vs. 2133 MHz (4.3 Gbps effective)
• Memory Size: 2 GB vs. 4 GB
• Memory Type: GDDR5 vs. LPDDR4X
• Memory Bandwidth: 105.8 GB/s vs. 68.26 GB/s
• ROPs: 32 vs. 24
• Pixel Rate: 38.02 GPixel/s vs. 39.60 GPixel/s
• Texture Rate: 57.02 GTexel/s vs. 79.20 GTexel/s
• FP32: 1.825 TFLOPS vs. 2.534 TFLOPS
• FP16: (not listed) vs. 5.069 TFLOPS (2:1)
• TDP: 90 W vs. 25 W
• Slot Width: Dual-slot vs. IGP
• Power Connectors: 1x 6-pin vs. (none)
• Suggested PSU: 250 W vs. 200 W
• Bus Interface: PCIe 3.0 x16 vs. PCIe 4.0 x8
• Display Outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 vs. No outputs
• Dimensions (Length): 202 mm (8 inches) vs. (not listed)
• Release Date: 2015-08-19 vs. 2020-10-30
• Predecessor: GeForce 700 vs. Graphics
• Successor: GeForce 10 vs. Alchemist
• Launch MSRP: 159 USD vs. (not listed)

Head-to-Head Benchmarks

The data provides a single, direct benchmark comparison between these two GPUs: Geekbench OpenCL. This is a compute-oriented test that measures general-purpose GPU performance.

Geekbench OpenCL: NVIDIA GeForce GTX 950 Wins

• NVIDIA GeForce GTX 950: 15,662
• Intel Iris Xe MAX Graphics: 14,315
• Winner: NVIDIA GeForce GTX 950
• Delta: 9.4%

This result is significant because the Iris Xe MAX has a higher theoretical FP32 throughput (2.534 TFLOPS) and a much higher texture rate (79.20 GTexel/s) than the GTX 950. Despite these architectural advantages on paper, the GTX 950’s higher memory bandwidth (105.8 GB/s vs. 68.26 GB/s) and its larger ROP count (32 vs. 24) likely contribute to its superior OpenCL score. The 9.4% delta shows a clear, but not overwhelming, performance lead for the older NVIDIA card in this specific workload.

The GTX 950’s average benchmark score of 13,189 is also higher than its nearest rival, the AMD Radeon Pro 555X, by 1%, and it sits 0.8% behind the GeForce GTX 480. The Iris Xe MAX’s average score of 14,315 puts it 0.3% behind the AMD Radeon Vega 11 and 0.3% ahead of the NVIDIA GeForce GTX 1070 Ti in its own rival list. These rival comparisons place the Intel part in a higher overall percentile (56th vs. 53rd), suggesting that while it loses the direct head-to-head, its overall standing in the broader GPU landscape is slightly better. The single benchmark win for the GTX 950 is the only head-to-head data point, so it stands as the definitive performance verdict between these two specific cards.