Intel Iris Xe MAX Graphics vs NVIDIA GeForce GTX 690 Comparison

Head-to-Head Benchmarks

The database contains one direct benchmark comparison between these two GPUs: the Geekbench OpenCL test. The results show a clear overall winner, with the NVIDIA GeForce GTX 690 scoring 17,399 points against the Intel Iris Xe MAX Graphics' 14,315 points. That difference translates to a 21.5% advantage for the NVIDIA card, which is a substantial margin in raw compute throughput.

Contextualizing the GTX 690's score against its nearest rivals reinforces its position. The recorded data places it at a 60th percentile among all GPUs, with an average benchmark score of 17,037. It sits within a tight cluster: it is only 0.1% ahead of the AMD Radeon HD 7970M (17,019), 0.6% ahead of the NVIDIA Tesla M4 (16,932), and 0.3% behind the AMD Radeon RX 7600 XT (17,083). The most notable comparison is with the NVIDIA GeForce RTX 3070, which scores 17,208, putting the GTX 690 1% behind that much newer card. This indicates that despite its age, the GTX 690's raw compute performance remains competitive with significantly more recent hardware.

The Intel Iris Xe MAX Graphics, by contrast, holds a 56th percentile ranking with an average score of 14,315. Its nearest rivals cluster around the same point: it is 0.3% behind the AMD Radeon Vega 11 (14,352), 0.3% ahead of the NVIDIA GeForce GTX 1070 Ti (14,277), 0.4% behind the NVIDIA GeForce GTX TITAN (14,373), and 0.5% behind the AMD Radeon RX Vega 11 (14,385). The Intel part is essentially performance-neutral against these peers, trading places within a single percentage point. The 21.5% gap between the GTX 690 and the Iris Xe MAX is therefore far larger than the typical spread seen among each card's closest competitors, marking the NVIDIA part as the decisively faster compute solution in this head-to-head.

Architecture Differences

The two GPUs come from entirely different design philosophies and eras. The GTX 690 is built on NVIDIA's Kepler architecture, using the GK104 chip fabricated on a 28 nm process at TSMC. The Iris Xe MAX uses Intel's Generation 12.1 architecture, built around the DG1 chip on a 10 nm process at Intel's own foundry. The manufacturing difference is significant: the GTX 690 packs 3,540 million transistors into a 294 mm² die, yielding a transistor density of 12.0M per mm². The Intel chip has no recorded transistor count, but its die is considerably smaller at 95 mm².

Clock behavior also diverges sharply. The GTX 690 runs at a 915 MHz base clock with a 1019 MHz boost. The Iris Xe MAX has a much lower 300 MHz base but boosts to 1650 MHz, reflecting a design that relies on aggressive boosting to hit its performance targets. Memory configurations are different as well: the GTX 690 uses 2 GB of GDDR5 on a 256-bit bus, delivering 192.3 GB/s of bandwidth at 1502 MHz (6 Gbps effective). The Iris Xe MAX has 4 GB of LPDDR4X on a 128-bit bus, but that wider capacity comes with a narrower interface and much lower bandwidth at 68.26 GB/s, running at 2133 MHz (4.3 Gbps effective).

Compute resources favor the NVIDIA card in sheer counts. The GTX 690 has 1,536 shading units, 128 texture mapping units, and 32 ROPs. The Iris Xe MAX has 768 shading units, 48 TMUs, and 24 ROPs. Despite the lower unit counts, the Intel part achieves a higher pixel rate: 39.60 GPixel/s versus 32.61 GPixel/s for the GTX 690, a result of its higher boost clock. Texture rate tells a different story, with the GTX 690 reaching 130.4 GTexel/s versus 79.20 GTexel/s for the Intel part. In raw FP32 throughput, the GTX 690 outputs 3.130 TFLOPS against 2.534 TFLOPS for the Iris Xe MAX. The Intel card does offer FP16 at 5.069 TFLOPS with a 2:1 ratio, a capability the GTX 690 does not record.

API support also differs. The GTX 690 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Iris Xe MAX supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, giving it a more modern feature set in both DirectX and Vulkan. The bus interface shows another generational gap: the GTX 690 uses PCIe 3.0 x16, while the Iris Xe MAX uses PCIe 4.0 x8.

Where Each One Wins

The GTX 690 wins decisively in raw compute performance. Its OpenCL score of 17,399 is 21.5% higher than the Iris Xe MAX's 14,315, and its FP32 throughput of 3.130 TFLOPS exceeds the Intel part's 2.534 TFLOPS. Texture throughput is also a clear win, with 130.4 GTexel/s versus 79.20 GTexel/s, nearly double. Memory bandwidth favors the GTX 690 massively at 192.3 GB/s versus 68.26 GB/s, which matters for bandwidth-bound workloads. The GTX 690 also has more shading units, TMUs, and ROPs, giving it an advantage in workloads that scale with those resources.

The Iris Xe MAX wins in other specific areas. Its pixel rate of 39.60 GPixel/s exceeds the GTX 690's 32.61 GPixel/s, so fill-rate-bound scenarios favor the Intel part. It has double the memory capacity at 4 GB versus 2 GB, which helps with larger working sets. Its FP16 throughput of 5.069 TFLOPS is nearly double its own FP32 rate and is a capability the GTX 690 does not offer. The Iris Xe MAX also has a higher boost clock at 1650 MHz versus 1019 MHz, and a more modern API profile with DirectX 12 (12_1) and Vulkan 1.4.

Power consumption heavily favors the Intel part. The GTX 690 draws 300 W and requires a 700 W power supply, while the Iris Xe MAX draws only 25 W and needs just a 200 W supply. This makes the Intel GPU suitable for integrated applications, which is consistent with its IGP slot width and lack of display outputs. The GTX 690 is a dual-slot card requiring two 8-pin power connectors.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 690 has an average score of 17,037, while the Intel Iris Xe MAX Graphics averages 14,315, a difference of roughly 21.5% in favor of the NVIDIA card.

Q: How does the GTX 690 compare to the RTX 3070?

A: The GTX 690 scores 17,399 in OpenCL and averages 17,037 across benchmarks. The RTX 3070 has an average score of 17,208, placing the GTX 690 about 1% behind it.

Q: What is the memory bandwidth difference?

A: The GTX 690 delivers 192.3 GB/s over a 256-bit bus, while the Iris Xe MAX provides 68.26 GB/s over a 128-bit bus. The NVIDIA card has nearly three times the bandwidth.

Q: Does the Iris Xe MAX support FP16?

A: Yes, the Iris Xe MAX supports FP16 at 5.069 TFLOPS with a 2:1 ratio. The GTX 690 has no recorded FP16 capability.

Q: Which GPU is more power efficient?

A: The Iris Xe MAX draws 25 W with a suggested 200 W power supply, while the GTX 690 draws 300 W with a suggested 700 W power supply. The Intel part uses a fraction of the power.

Q: What is the API support difference?

A: The GTX 690 supports DirectX 12 (11_0) and Vulkan 1.2.175, while the Iris Xe MAX supports DirectX 12 (12_1) and Vulkan 1.4. The Intel part has newer API versions.

Specification Differences

The two GPUs differ across nearly every recorded specification. The GTX 690 uses the GK104 chip on a 28 nm TSMC process with 3,540 million transistors and a 294 mm² die. The Iris Xe MAX uses the DG1 chip on a 10 nm Intel process with a 95 mm² die and no recorded transistor count. Clock speeds: the GTX 690 runs at 915 MHz base and 1019 MHz boost, while the Iris Xe MAX runs at 300 MHz base and 1650 MHz boost. Memory: the GTX 690 has 2 GB of GDDR5 on a 256-bit bus with 192.3 GB/s bandwidth; the Iris Xe MAX has 4 GB of LPDDR4X on a 128-bit bus with 68.26 GB/s bandwidth.

Compute units differ: 1,536 shading units, 128 TMUs, and 32 ROPs for the GTX 690 versus 768 shading units, 48 TMUs, and 24 ROPs for the Iris Xe MAX. Pixel rate favors the Intel part at 39.60 GPixel/s versus 32.61 GPixel/s. Texture rate favors NVIDIA at 130.4 GTexel/s versus 79.20 GTexel/s. FP32 is 3.130 TFLOPS for NVIDIA and 2.534 TFLOPS for Intel; FP16 is not recorded for NVIDIA but is 5.069 TFLOPS for Intel. TDP is 300 W versus 25 W. The GTX 690 is dual-slot with two 8-pin connectors and a 700 W PSU suggestion; the Iris Xe MAX is an IGP with no connectors and a 200 W PSU suggestion. Bus interface is PCIe 3.0 x16 for NVIDIA and PCIe 4.0 x8 for Intel. Display outputs are 3x DVI and 1x mini-DisplayPort 1.2 for the GTX 690, while the Iris Xe MAX has no outputs.

API differences: DirectX 12 (11_0) versus 12 (12_1), OpenGL 4.6 for both, Vulkan 1.2.175 versus 1.4. Physical dimensions are recorded only for the GTX 690 at 279 mm length, 111 mm height, and 38 mm width. Release dates are 2012-05-02 for NVIDIA and 2020-10-30 for Intel. The GTX 690 has a launch MSRP of 999 USD; the Iris Xe MAX has no recorded launch MSRP.

The Verdict

The data points to a clear split based on workload and system context. For raw compute performance, the NVIDIA GeForce GTX 690 is the stronger card. Its 21.5% OpenCL lead, higher FP32 throughput, double the texture rate, and nearly triple the memory bandwidth make it the choice for compute-heavy tasks that can use that hardware. Its benchmark percentile of 60 versus 56 for the Intel part, combined with an average score that sits within 1% of an RTX 3070, shows that this older card still competes at a high level in raw throughput.

The Intel Iris Xe MAX Graphics wins on efficiency and modern features. Its 25 W power draw versus 300 W is a massive advantage for systems where power and cooling are constrained. Its newer API support, FP16 capability, higher pixel rate, and double the memory capacity give it a role in lighter workloads and integrated environments. The lack of display outputs and IGP form factor mean it is designed for a completely different deployment scenario than a dual-slot add-in card like the GTX 690.

Users who need maximum compute performance and have the power budget should pick the GTX 690. Users who need a low-power, modern-featured GPU with FP16 support and more memory should pick the Iris Xe MAX. The benchmark data does not support a single winner across all criteria; it supports two winners for two distinct purposes.