NVIDIA GeForce RTX 4070 Mobile vs NVIDIA GeForce RTX 5070 SUPER Comparison

The Verdict

The recorded data presents an unusual comparison. The NVIDIA GeForce RTX 4070 Mobile has a substantial benchmark history, with an average score of 27,435 across nine tests, placing it at the 73rd percentile of all GPUs. The NVIDIA GeForce RTX 5070 SUPER, by contrast, has only a single recorded benchmark result, a 3DMark Steel Nomad DX12 score of 2,690, which places it at the 18th percentile. This single score is not directly comparable to the 4070 Mobile's average, as they use different test suites.

Based strictly on the database, the RTX 4070 Mobile is the more established performer with a wide range of DirectX and compute scores. The RTX 5070 SUPER's lone result cannot be used to declare a winner in overall performance. The 4070 Mobile is suitable for users seeking a proven mobile GPU, while the 5070 SUPER appears to be a new desktop part with limited benchmark coverage. The data does not support a definitive performance hierarchy between these two.

Architecture Differences

The two GPUs come from different generations and architectures. The RTX 4070 Mobile is based on the AD106 chip using the Ada Lovelace architecture, fabricated on a 5 nm process at TSMC. It integrates 22,900 million transistors on a 188 mm² die, yielding a transistor density of 121.8M per mm². Its feature set includes 4,608 shading units, 144 texture mapping units, 48 raster output units, 36 RT cores, and 144 tensor cores.

The RTX 5070 SUPER uses the GB205 chip with the Blackwell 2.0 architecture, also on a 5 nm TSMC process. It contains 31,100 million transistors on a 263 mm² die, with a transistor density of 118.3M per mm². Its configuration is larger: 6,400 shading units, 200 texture mapping units, 80 raster output units, 50 RT cores, and 200 tensor cores. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The memory subsystems differ substantially. The 4070 Mobile uses 8 GB of GDDR6 on a 128-bit bus, with a memory clock of 2000 MHz (16 Gbps effective) and bandwidth of 256.0 GB/s. The 5070 SUPER uses 18 GB of GDDR7 on a 192-bit bus, with a memory clock of 1750 MHz (28 Gbps effective) and bandwidth of 672.0 GB/s. The 5070 SUPER also has a wider PCIe interface, using PCIe 5.0 x16 versus the 4070 Mobile's PCIe 4.0 x8.

Physical and power characteristics also diverge. The 4070 Mobile is an IGP (integrated graphics processor) with no power connectors and a 115 W TDP. The 5070 SUPER is a dual-slot card with a 1x 16-pin power connector, a 275 W TDP, and dimensions of 245 mm in length, 115 mm in height, and 40 mm in width. The 4070 Mobile's display outputs are listed as portable device dependent, while the 5070 SUPER has 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark results shared between the two GPUs. The headToHeadBenchmarks field is empty, and the wins counter shows zero for both sides. This absence of direct comparison data means the only available evidence is their separate benchmark listings.

The RTX 4070 Mobile has nine recorded benchmarks. Its Geekbench OpenCL score is 109,197, and its Geekbench Vulkan score is 108,367. In Passmark tests, it scores 116 in DirectX 10, 179 in DirectX 11, 85 in DirectX 12, 223 in DirectX 9, 763 in G2D, 19,587 in G3D, and 8,399 in GPU Compute. Its average benchmark score across all tests is 27,435.

The RTX 5070 SUPER has one recorded benchmark: a 3DMark Steel Nomad DX12 score of 2,690. Its average benchmark score is 2,690. This single result is not comparable to the 4070 Mobile's average, because the 3DMark Steel Nomad test is a different workload than the Geekbench and Passmark suites. The data does not permit a direct numerical comparison of their performance.

The nearest rivals data provides context for each GPU individually. The 4070 Mobile's closest competitor is the AMD Radeon RX 6700 XT with an average score of 27,425 and a delta of 0%. It is also near the NVIDIA GeForce RTX 3090 (27,565, delta -0.5%), the NVIDIA RTX PRO 4000 Blackwell (27,135, delta 1.1%), and the AMD Radeon Pro Vega 20 (27,839, delta -1.5%). The 5070 SUPER's nearest rivals are all lower-tier cards: the NVIDIA Quadro K1100M (2,664, delta 1%), the NVIDIA GeForce GT 1030 (2,662, delta 1.1%), the Intel Arc Pro B50 (2,660, delta 1.1%), and the NVIDIA GeForce GT 440 (2,645, delta 1.7%).

FAQ

Q: Which GPU has the higher average benchmark score?

A: The RTX 4070 Mobile has an average benchmark score of 27,435 across nine tests. The RTX 5070 SUPER has an average score of 2,690 from a single test, so their averages are not directly comparable.

Q: What is the memory configuration of each GPU?

A: The RTX 4070 Mobile uses 8 GB of GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth. The RTX 5070 SUPER uses 18 GB of GDDR7 on a 192-bit bus with 672.0 GB/s bandwidth.

Q: How do their power requirements differ?

A: The RTX 4070 Mobile has a 115 W TDP and uses no power connectors. The RTX 5070 SUPER has a 275 W TDP and uses a single 16-pin power connector.

Q: What architecture does each GPU use?

A: The RTX 4070 Mobile uses the Ada Lovelace architecture with the AD106 chip. The RTX 5070 SUPER uses the Blackwell 2.0 architecture with the GB205 chip.

Q: Which GPU has more shading units?

A: The RTX 5070 SUPER has 6,400 shading units, while the RTX 4070 Mobile has 4,608 shading units.

Q: What is the release date for each product?

A: The RTX 4070 Mobile was released on January 2, 2023. The RTX 5070 SUPER has a release date of December 31, 2025.

Where Each One Wins

The RTX 4070 Mobile wins in the breadth of benchmark coverage. Its nine recorded tests span multiple DirectX versions, OpenCL, Vulkan, and compute workloads, giving it a comprehensive performance profile. Its 73rd percentile ranking among all GPUs indicates it sits above the majority of recorded hardware. Its nearest rivals include mid-range and high-end cards like the RTX 3090 and RX 6700 XT, which places its performance in that general range.

The RTX 5070 SUPER wins in raw hardware specifications. It has more shading units (6,400 vs 4,608), more texture mapping units (200 vs 144), more raster output units (80 vs 48), more RT cores (50 vs 36), and more tensor cores (200 vs 144). Its memory capacity of 18 GB is more than double the 4070 Mobile's 8 GB, and its 672.0 GB/s bandwidth is substantially higher. Its boost clock of 2512 MHz exceeds the 4070 Mobile's 1695 MHz. Its FP32 performance of 32.15 TFLOPS is more than double the 4070 Mobile's 15.62 TFLOPS.

The 5070 SUPER also wins on connectivity and expandability. It uses PCIe 5.0 x16, while the 4070 Mobile uses PCIe 4.0 x8. It has a defined set of display outputs (1x HDMI 2.1b and 3x DisplayPort 2.1b), while the 4070 Mobile's outputs depend on the portable device. The 5070 SUPER's pixel rate of 201.0 GPixel/s and texture rate of 502.4 GTexel/s are both higher than the 4070 Mobile's 81.36 GPixel/s and 244.1 GTexel/s.

The 4070 Mobile wins on power efficiency and form factor. Its 115 W TDP is less than half of the 5070 SUPER's 275 W. As an IGP with no power connectors, it can fit into thin portable devices, whereas the 5070 SUPER is a dual-slot card measuring 245 mm by 115 mm by 40 mm. The 4070 Mobile also has a higher transistor density (121.8M per mm²) compared to the 5070 SUPER (118.3M per mm²).

Specification Differences

The two GPUs differ in nearly every measurable specification. The RTX 4070 Mobile uses the AD106 chip with Ada Lovelace architecture, while the RTX 5070 SUPER uses the GB205 chip with Blackwell 2.0 architecture. Both use a 5 nm TSMC process, but the 5070 SUPER has more transistors (31,100 million vs 22,900 million) and a larger die (263 mm² vs 188 mm²).

Clock speeds favor the 5070 SUPER. Its base clock is 2325 MHz and boost clock is 2512 MHz, compared to the 4070 Mobile's 1395 MHz base and 1695 MHz boost. The 5070 SUPER's memory runs at 1750 MHz with 28 Gbps effective speed, while the 4070 Mobile's memory runs at 2000 MHz with 16 Gbps effective speed.

Memory capacity and bandwidth favor the 5070 SUPER. It has 18 GB of GDDR7 on a 192-bit bus with 672.0 GB/s bandwidth. The 4070 Mobile has 8 GB of GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth. The 5070 SUPER also has more of every compute unit type: 6,400 shading units, 200 TMUs, 80 ROPs, 50 RT cores, and 200 tensor cores, versus 4,608, 144, 48, 36, and 144 respectively.

Power and physical specifications differ significantly. The 4070 Mobile has a 115 W TDP, is an IGP, uses no power connectors, and has portable device dependent outputs. The 5070 SUPER has a 275 W TDP, is dual-slot, uses a 1x 16-pin connector, and has 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs. The 5070 SUPER uses PCIe 5.0 x16, while the 4070 Mobile uses PCIe 4.0 x8. The 5070 SUPER measures 245 mm by 115 mm by 40 mm, while the 4070 Mobile has no listed dimensions. Release dates also differ: the 4070 Mobile from January 2023, the 5070 SUPER from December 2025.