NVIDIA GeForce RTX 5070 SUPER vs NVIDIA GeForce RTX 5090 D V2 Comparison

Where Each One Wins

The recorded benchmark data splits cleanly between the two cards, with the NVIDIA GeForce RTX 5090 D V2 taking the only head-to-head victory. In the single tested workload, 3DMark Steel Nomad DX12, the RTX 5090 D V2 scores 16504 against the RTX 5070 SUPER's 2690, a delta of 83.7 percent. That means the RTX 5090 D V2 delivers roughly six times the performance in this specific test. The RTX 5070 SUPER does not win any benchmark in the database, so its case rests on other characteristics rather than measured frame rates or compute scores.

The RTX 5070 SUPER occupies the 18th percentile among all GPUs, while the RTX 5090 D V2 sits at the 59th percentile. This gap in percentile ranking reflects how each card positions against the broader field: the RTX 5070 SUPER lands near entry-level territory, with its closest rivals being the NVIDIA Quadro K1100M (average score 2664, delta 1 percent), the NVIDIA GeForce GT 1030 (2662, delta 1.1 percent), and the Intel Arc Pro B50 (2660, delta 1.1 percent). The RTX 5090 D V2, by contrast, sits among much faster company, with nearest rivals including the NVIDIA T400 (16508, delta 0 percent), the AMD Radeon PRO W7500 (16415, delta 0.5 percent), and the NVIDIA RTX PRO 6000 Blackwell (16408, delta 0.6 percent).

The use-case split is therefore straightforward. The RTX 5090 D V2 is the clear choice for any workload that depends on raw graphics throughput, as indicated by its dominant Steel Nomad result. The RTX 5070 SUPER, lacking a single benchmark win, does not make a performance-based case in this data. Instead, its advantages appear in physical size, power draw, and memory configuration, which may suit systems where those factors matter more than absolute speed. The RTX 5070 SUPER draws 275 W versus the RTX 5090 D V2's 575 W, and it measures 245 mm in length versus 304 mm. These are meaningful differences for chassis compatibility and thermal design, even if they do not translate into benchmark victories.

The Verdict

For a buyer prioritizing measured 3D performance, the data points exclusively to the RTX 5090 D V2. Its Steel Nomad score of 16504 dwarfs the RTX 5070 SUPER's 2690, and its 59th percentile standing among all GPUs places it far above the RTX 5070 SUPER's 18th percentile. The RTX 5090 D V2 also carries a launch MSRP of 2,299 USD, a figure recorded in the database for reference.

The RTX 5070 SUPER, despite losing the only benchmark comparison, still has a defined role. Its 275 W power draw is less than half of the RTX 5090 D V2's 575 W, and its 245 mm length makes it compatible with smaller cases. The 18 GB memory capacity, while smaller than the RTX 5090 D V2's 24 GB, still provides substantial VRAM for many tasks. The RTX 5070 SUPER also uses a 192-bit bus with 672.0 GB/s bandwidth, whereas the RTX 5090 D V2 uses a 384-bit bus with 1.34 TB/s. For users who cannot accommodate a 304 mm dual-slot card or who need a lower power envelope, the RTX 5070 SUPER is the only option between the two, even though it sacrifices the massive performance lead of its larger sibling.

The RTX 5090 D V2 also has a suggested PSU of 950 W, while the RTX 5070 SUPER has no recorded suggested PSU, further reinforcing the former's higher system requirements. The verdict from the data: the RTX 5090 D V2 wins on every measured performance axis, while the RTX 5070 SUPER wins on physical footprint and power efficiency.

Head-to-Head Benchmarks

The single head-to-head benchmark in the database is 3DMark Steel Nomad DX12, and it is not a close contest. The RTX 5090 D V2 scores 16504, while the RTX 5070 SUPER scores 2690, yielding a delta of 83.7 percent in favor of the RTX 5090 D V2. This means the RTX 5090 D V2 completes the workload at over six times the speed of the RTX 5070 SUPER, a margin that dominates any other comparison in this data.

Contextualizing the RTX 5070 SUPER's score against its nearest rivals shows how low it sits. The Quadro K1100M averages 2664, just 1 percent behind, while the GT 1030 averages 2662, 1.1 percent behind, and the Arc Pro B50 averages 2660, also 1.1 percent behind. The RTX 5070 SUPER's 2690 puts it only marginally ahead of these older or lower-tier cards, suggesting its performance class is closer to entry-level than to mid-range or high-end.

The RTX 5090 D V2's nearest rivals tell a different story. The T400 averages 16508, effectively identical with a 0 percent delta, while the Radeon PRO W7500 averages 16415, 0.5 percent behind, and the RTX PRO 6000 Blackwell averages 16408, 0.6 percent behind. The RTX 5090 D V2's 16504 places it in a tight cluster with these cards, all within a fraction of a percent of each other. This indicates that the RTX 5090 D V2 is not an outlier even among its peers; it simply sits at the top of a closely grouped performance band.

The delta of 83.7 percent between the two cards in question is the largest recorded gap in the head-to-head data. No other metric in the database comes close to bridging this divide. The RTX 5090 D V2's wins column shows 1 victory, while the RTX 5070 SUPER shows 0, matching the single benchmark result exactly.

FAQ

Q: Which card has the higher benchmark score in 3DMark Steel Nomad DX12?

A: The NVIDIA GeForce RTX 5090 D V2 scores 16504, while the NVIDIA GeForce RTX 5070 SUPER scores 2690, a delta of 83.7 percent in favor of the RTX 5090 D V2.

Q: How does the RTX 5070 SUPER compare to its nearest rivals?

A: The RTX 5070 SUPER's average score of 2690 is 1 percent ahead of the NVIDIA Quadro K1100M (2664), 1.1 percent ahead of the NVIDIA GeForce GT 1030 (2662), and 1.1 percent ahead of the Intel Arc Pro B50 (2660).

Q: What are the memory differences between the two cards?

A: The RTX 5070 SUPER has 18 GB of GDDR7 memory on a 192-bit bus with 672.0 GB/s bandwidth. The RTX 5090 D V2 has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth.

Q: Which card has a lower power draw?

A: The RTX 5070 SUPER has a TDP of 275 W, while the RTX 5090 D V2 has a TDP of 575 W. The RTX 5090 D V2 also lists a suggested PSU of 950 W, while the RTX 5070 SUPER has no recorded suggested PSU.

Q: What is the percentile ranking of each card among all GPUs?

A: The RTX 5070 SUPER sits at the 18th percentile, while the RTX 5090 D V2 sits at the 59th percentile.

Q: How does the RTX 5090 D V2 compare to its nearest rivals?

A: The RTX 5090 D V2's average score of 16504 is 0 percent different from the NVIDIA T400 (16508), 0.5 percent ahead of the AMD Radeon PRO W7500 (16415), and 0.6 percent ahead of the NVIDIA RTX PRO 6000 Blackwell (16408).

Architecture Differences

Both cards share the Blackwell 2.0 architecture and are built by TSMC on a 5 nm process, but they diverge significantly at the chip level. The RTX 5070 SUPER uses the GB205 chip with 31,100 million transistors on a 263 mm² die, yielding a transistor density of 118.3M per mm². The RTX 5090 D V2 uses the GB202 chip with 92,200 million transistors on a 750 mm² die, yielding a density of 122.9M per mm². The RTX 5090 D V2 packs nearly three times the transistors onto nearly three times the die area.

Compute resources differ by wide margins. The RTX 5070 SUPER has 6400 shading units, 200 texture mapping units, and 80 raster output units. The RTX 5090 D V2 has 21760 shading units, 680 TMUs, and 176 ROPs. Ray tracing cores number 50 on the RTX 5070 SUPER versus 170 on the RTX 5090 D V2, and tensor cores number 200 versus 680. These ratios roughly track the transistor count difference, with the RTX 5090 D V2 holding a 3.4x lead in shading units and TMUs, a 2.2x lead in ROPs, a 3.4x lead in RT cores, and a 3.4x lead in tensor cores.

Pixel and texture rates follow the hardware counts. The RTX 5070 SUPER achieves 201.0 GPixel/s and 502.4 GTexel/s, while the RTX 5090 D V2 achieves 423.6 GPixel/s and 1,636.8 GTexel/s. Floating-point performance shows a similar gap: the RTX 5070 SUPER delivers 32.15 TFLOPS for both FP32 and FP16 (1:1), while the RTX 5090 D V2 delivers 104.8 TFLOPS for both. The RTX 5090 D V2 is roughly 3.3x faster in raw compute throughput.

Clock speeds do not follow the same pattern. The RTX 5070 SUPER has a base clock of 2325 MHz and a boost of 2512 MHz, while the RTX 5090 D V2 has a base of 2017 MHz and a boost of 2407 MHz. The smaller chip runs faster, but the larger chip's massive resource pool overcomes the clock disadvantage. Both use GDDR7 memory at 1750 MHz with 28 Gbps effective speed, so memory clock parity does not factor into the performance gap.

Specification Differences

The two cards diverge on nearly every major specification. Memory size: 18 GB on the RTX 5070 SUPER versus 24 GB on the RTX 5090 D V2. Memory bus width: 192-bit versus 384-bit. Memory bandwidth: 672.0 GB/s versus 1.34 TB/s. The RTX 5090 D V2 doubles the bus width and nearly doubles the bandwidth.

Physical dimensions differ as well. The RTX 5070 SUPER measures 245 mm in length, 115 mm in height, and 40 mm in width. The RTX 5090 D V2 measures 304 mm in length, 137 mm in height, and 48 mm in width. Both are dual-slot cards, and both use a single 16-pin power connector. The RTX 5090 D V2 lists a suggested PSU of 950 W, while the RTX 5070 SUPER has no recorded suggested PSU.

Power draw is a major differentiator: 275 W for the RTX 5070 SUPER versus 575 W for the RTX 5090 D V2. The RTX 5090 D V2 consumes over twice the power, which aligns with its larger die and higher resource counts. The RTX 5090 D V2 also has a recorded launch MSRP of 2,299 USD, while the RTX 5070 SUPER has no recorded launch MSRP.

Both cards share several specifications: PCIe 5.0 x16 bus interface, 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs (with the RTX 5090 D V2's display output string formatted as "1x HDMI 2.1b3x DisplayPort 2.1b" in the database), DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are active production statuses, from the GeForce 50-series, and both use GDDR7 memory at 1750 MHz with 28 Gbps effective speed. The RTX 5090 D V2 lists a predecessor of GeForce 40 and a successor of GeForce 60, while the RTX 5070 SUPER has no recorded predecessor or successor.