NVIDIA GeForce RTX 2080 SUPER vs NVIDIA GeForce RTX 3070 Ti Mobile Comparison

Head-to-Head Benchmarks

The benchmark data splits this comparison into two clear narratives. The NVIDIA GeForce RTX 3070 Ti Mobile dominates the modern DirectX 12 and compute-oriented tests, while the older RTX 2080 SUPER sweeps nearly every legacy and general-purpose workload. Of the ten head-to-head results, the 2080 SUPER wins eight, but the two losses are decisive.

The largest margin belongs to the RTX 3070 Ti Mobile in 3DMark Steel Nomad DX12, scoring 2572 against 1882 for the 2080 SUPER — a 26.8% advantage. That is a substantial gap in a next-generation API workload, and it aligns with the mobile card's Ampere architecture being built around modern rendering paths. The second win for the 3070 Ti Mobile comes in Geekbench OpenCL, where it scores 106022 versus 99226, a 6.4% lead. That result suggests the mobile part handles general compute shaders better, likely due to its much higher FP32 throughput.

The 2080 SUPER counters with a commanding 11.3% win in Geekbench Vulkan, scoring 111284 against 100027. That is a notable reversal — the newer card loses in one cross-platform graphics API while winning in another. The pattern continues across PassMark tests. In DirectX 10, the 2080 SUPER leads 140 to 124, a 12.9% margin. DirectX 11 shows a 7.8% advantage (165 vs 153), and even DirectX 12, where the 3070 Ti Mobile is expected to shine, the 2080 SUPER edges ahead 75 to 73, just 2.7%. Legacy DirectX 9 is a 15.8% blowout (227 vs 196). The 2080 SUPER also wins the 2D test by 17.5% (920 vs 783), the G3D test by 9.9% (19490 vs 17727), and GPU compute by 10.5% (8290 vs 7504).

These results tell a consistent story. The RTX 3070 Ti Mobile is built for the future, with its biggest win in the most modern benchmark. The RTX 2080 SUPER, despite being older, is more consistent across a broad range of workloads, particularly in driver-optimized legacy APIs and 2D performance. The average benchmark scores reflect this: the 2080 SUPER averages 24170, while the 3070 Ti Mobile averages 23518 — a 2.7% overall edge for the desktop card. Both sit at the 69th percentile among all GPUs, meaning they are effectively peers in the broader performance landscape.

FAQ

Q: Which card wins in modern DirectX 12 workloads?

A: The NVIDIA GeForce RTX 3070 Ti Mobile wins decisively in 3DMark Steel Nomad DX12, scoring 2572 versus 1882 for the RTX 2080 SUPER — a 26.8% advantage. However, in PassMark DirectX 12, the 2080 SUPER narrowly wins 75 to 73, a 2.7% margin.

Q: How do the two compare in raw compute performance?

A: In Geekbench OpenCL, the RTX 3070 Ti Mobile leads 106022 to 99226, a 6.4% win. But in PassMark GPU Compute, the RTX 2080 SUPER wins 8290 to 7504, a 10.5% margin. The FP32 figures explain this split: the 3070 Ti Mobile is rated at 16.60 TFLOPS versus 11.15 TFLOPS for the 2080 SUPER.

Q: Which card has better Vulkan performance?

A: The RTX 2080 SUPER is clearly ahead in Geekbench Vulkan, scoring 111284 against 100027 for the 3070 Ti Mobile — an 11.3% advantage. Both cards support Vulkan 1.4, but the older desktop part performs better in this specific test.

Q: Are these cards in the same performance tier overall?

A: Yes. The RTX 2080 SUPER has an average benchmark score of 24170, while the RTX 3070 Ti Mobile averages 23518 — a 2.7% difference. Both occupy the 69th percentile among all GPUs, and each sits within 1.1% of its nearest rivals in the database.

Q: What do the nearest rival comparisons reveal?

A: The RTX 2080 SUPER's closest rival is the AMD Radeon RX 6600 XT at 24442 (1.1% higher), followed by the GTX 1630 at 24277 (0.4% lower) and the GTX 780 Ti at 24236 (0.3% lower). The RTX 3070 Ti Mobile's nearest competitor is the RTX 3080 Mobile at 23628 (0.5% higher), with the GTX TITAN Z at 23736 (0.9% higher) close behind.

Q: Which card is better for legacy DirectX titles?

A: The RTX 2080 SUPER wins every legacy PassMark test. It leads DirectX 9 by 15.8% (227 vs 196), DirectX 10 by 12.9% (140 vs 124), and DirectX 11 by 7.8% (165 vs 153). For older game libraries, the 2080 SUPER is the stronger choice.

Where Each One Wins

The RTX 3070 Ti Mobile is the pick for advanced rendering and compute-heavy workloads. Its 26.8% win in 3DMark Steel Nomad DX12 signals strong performance in modern game engines that leverage DirectX 12 Ultimate features. The 6.4% Geekbench OpenCL advantage reinforces this, making it the better option for GPU-accelerated compute tasks like video encoding, machine learning inference, or physics simulations that use OpenCL. The sheer compute headroom — 16.60 TFLOPS FP32 versus 11.15 TFLOPS — gives it a clear edge in raw number-crunching when software is built for Ampere's execution model.

The RTX 2080 SUPER is the more versatile card across a broader software ecosystem. It wins in Vulkan by 11.3%, which covers a growing number of AAA titles and emulators. It dominates legacy DirectX APIs, with margins from 2.7% in DX12 to 15.8% in DX9, making it the safer bet for older game libraries that haven't been optimized for newer architectures. The 17.5% win in PassMark G2D and 9.9% in G3D indicate better general desktop responsiveness and overall rasterization consistency. For users who play a mix of old and new titles, the 2080 SUPER's eight-out-of-ten win rate in these benchmarks makes it the more reliable all-rounder.

There is also a practical hardware consideration. The 2080 SUPER is a desktop card with a 250 W TDP and dual-slot cooling, while the 3070 Ti Mobile is a laptop part rated at 115 W. That power difference means the mobile card achieves its performance in a fraction of the power envelope, which matters for portable systems. The 2080 SUPER, by contrast, is designed for a desktop chassis with a 600 W suggested PSU and 1x 6-pin plus 1x 8-pin power connectors.

Specification Differences

The two cards diverge sharply on process technology and transistor budgets. The RTX 2080 SUPER uses a 12 nm TSMC process, packing 13,600 million transistors into a 545 mm² die for a density of 25.0M / mm². The RTX 3070 Ti Mobile uses Samsung's 8 nm node, fitting 17,400 million transistors into a smaller 392 mm² die, achieving a much higher 44.4M / mm² density. That density advantage is a direct result of the newer manufacturing process.

Clock speeds favor the desktop card. The 2080 SUPER runs at 1650 MHz base and 1815 MHz boost, while the 3070 Ti Mobile operates at 915 MHz base and 1410 MHz boost. Memory clocks also differ: the 2080 SUPER uses 1937 MHz (15.5 Gbps effective) versus 1750 MHz (14 Gbps effective) for the mobile part. Both have 8 GB of GDDR6 on a 256-bit bus, but the 2080 SUPER's higher memory clock gives it 495.9 GB/s bandwidth versus 448.0 GB/s for the 3070 Ti Mobile.

The compute configurations are fundamentally different. The 3070 Ti Mobile has 5888 shading units, 184 TMUs, and 96 ROPs. The 2080 SUPER has 3072 shading units, 192 TMUs, and 64 ROPs. That means the mobile card has nearly double the shader count but fewer texture units and more ROPs. Ray tracing cores are close: 48 for the 2080 SUPER versus 46 for the 3070 Ti Mobile. Tensor cores differ significantly: 384 for the 2080 SUPER versus 184 for the mobile card. FP32 throughput favors the 3070 Ti Mobile at 16.60 TFLOPS, while the 2080 SUPER delivers 11.15 TFLOPS. FP16 is a different story: the 2080 SUPER achieves 22.30 TFLOPS with 2:1 ratio, while the 3070 Ti Mobile matches its FP32 at 16.60 TFLOPS with 1:1 ratio.

Pixel and texture rates also differ. The 3070 Ti Mobile has a higher pixel rate at 135.4 GPixel/s versus 116.2 GPixel/s for the 2080 SUPER, but the desktop card wins texture rate at 348.5 GTexel/s versus 259.4 GTexel/s. The 2080 SUPER uses PCIe 3.0 x16, while the 3070 Ti Mobile supports PCIe 4.0 x16. Display outputs differ as well: the 2080 SUPER has 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C, while the 3070 Ti Mobile's outputs are portable device dependent.

Architecture Differences

The RTX 2080 SUPER is built on Turing architecture, while the RTX 3070 Ti Mobile uses Ampere. This is a generational leap: Turing introduced the first generation of RT and Tensor cores, while Ampere refines them for better efficiency and throughput. The 2080 SUPER's TU104 chip is a large, power-hungry desktop die. The 3070 Ti Mobile's GA104 is denser and more compact, designed for laptops.

The transistor density difference is striking: 25.0M / mm² for Turing on 12 nm versus 44.4M / mm² for Ampere on 8 nm. That nearly 78% density improvement allows Ampere to pack 17,400 million transistors into a die that is 153 mm² smaller. The architectural changes translate into different compute ratios. Ampere's shader design doubles FP32 throughput per clock compared to Turing, which explains how a card with a much lower boost clock (1410 MHz versus 1815 MHz) can still deliver 16.60 TFLOPS FP32 versus 11.15 TFLOPS. The FP16 capability also changed: Turing uses a 2:1 ratio to reach 22.30 TFLOPS, while Ampere runs at 1:1, capping FP16 at 16.60 TFLOPS.

Both architectures support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature sets are identical. The core difference is efficiency and execution model. Turing's Tensor cores number 384, while Ampere uses 184 — but Ampere's Tensor cores are more capable per unit, which is why the mobile card still competes despite fewer of them. The RT core counts are nearly identical (48 vs 46), suggesting ray tracing performance is comparable, though Ampere's RT cores are generally more efficient. The 3070 Ti Mobile also benefits from PCIe 4.0, doubling the bus bandwidth available to the 2080 SUPER's PCIe 3.0 connection.

The Verdict

The data points to a clear split based on use case. The NVIDIA GeForce RTX 3070 Ti Mobile is the better choice for anyone running modern DirectX 12 Ultimate games and OpenCL-based compute workloads. Its 26.8% lead in 3DMark Steel Nomad DX12 is the single largest performance gap in this comparison, and it demonstrates that Ampere's architecture is significantly better at executing the rendering paths used by current and upcoming titles. The 6.4% OpenCL win reinforces this as a compute-capable part, and the 115 W TDP means it delivers this performance in a mobile form factor.

The NVIDIA GeForce RTX 2080 SUPER is the more consistent performer across a wide range of software. Winning eight of ten benchmarks, including every PassMark test and Vulkan, it offers superior legacy API performance, better 2D responsiveness, and higher memory bandwidth (495.9 GB/s versus 448.0 GB/s). The 11.3% Vulkan win is particularly relevant for cross-platform titles and emulators. Its higher boost clock (1815 MHz versus 1410 MHz) and larger texture rate (348.5 GTexel/s versus 259.4 GTexel/s) contribute to its rasterization strength.

For a desktop builder focused on a diverse game library, especially older titles or Vulkan-based games, the 2080 SUPER is the safer pick — its 2.7% higher average benchmark score and eight wins speak to its versatility. For a laptop buyer prioritizing modern game performance and compute throughput, the 3070 Ti Mobile is the obvious choice, provided the software in question is built for Ampere's strengths. The 69th percentile ranking for both cards confirms they are peers overall; the decision comes down to workload compatibility rather than raw capability.