NVIDIA GeForce RTX 2070 SUPER vs NVIDIA P106-100 Comparison

Head-to-Head Benchmarks

The recorded data is unambiguous: the NVIDIA GeForce RTX 2070 SUPER wins every single head-to-head benchmark against the NVIDIA P106-100. Out of three compared tests, the RTX 2070 SUPER takes all three, with deltas ranging from roughly 46% to 64%. There is no benchmark in the database where the P106-100 comes out ahead.

In 3DMark Steel Nomad DX12, the RTX 2070 SUPER scores 1651 against the P106-100's 899. That is a 45.5% deficit for the P106-100, meaning the RTX 2070 SUPER delivers nearly double the performance in this DirectX 12 workload. This is the closest of the three head-to-head results, yet it still represents a commanding lead.

The gap widens considerably in compute-oriented tests. In Geekbench OpenCL, the RTX 2070 SUPER records 83,358 points while the P106-100 manages only 35,951. The delta here is 56.9% in favor of the RTX 2070 SUPER. The P106-100 trails by more than half in raw compute throughput, which aligns with its much lower FP32 rating.

The largest margin appears in Geekbench Vulkan. The RTX 2070 SUPER posts 90,637, while the P106-100 scores 32,897. That is a 63.7% deficit for the P106-100, the biggest spread across all three tests. Vulkan workloads appear to amplify the architectural gap between the two cards, favoring the newer Turing design substantially.

It is worth placing these results in context with the database's broader measurements. The P106-100 has an average benchmark score of 23,249 across all recorded tests, while the RTX 2070 SUPER averages 20,282. Interestingly, the P106-100 actually holds a higher average, despite losing every head-to-head matchup, because the RTX 2070 SUPER's score is pulled down by additional test results, including PassMark DirectX 9 (223), DirectX 10 (132), DirectX 11 (151), DirectX 12 (67), and G2D (878) scores that are not part of the head-to-head comparison.

The percentile rankings tell a similar story. The P106-100 sits at the 68th percentile among all GPUs, while the RTX 2070 SUPER sits at the 65th percentile. Both cards are firmly mid-pack in the overall database, but the RTX 2070 SUPER's lower percentile reflects its inclusion of more diverse, and sometimes less demanding, test workloads.

FAQ

Q: Which card wins in 3DMark Steel Nomad DX12?

A: The NVIDIA GeForce RTX 2070 SUPER wins decisively with a score of 1651 versus the P106-100's 899, a 45.5% advantage.

Q: How large is the performance gap in Geekbench OpenCL?

A: The RTX 2070 SUPER scores 83,358 against the P106-100's 35,951, a 56.9% lead for the RTX 2070 SUPER.

Q: Is there any benchmark where the P106-100 beats the RTX 2070 SUPER?

A: No. The database records zero wins for the P106-100 across all three head-to-head tests (3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan).

Q: What is the average benchmark score for each card?

A: The P106-100 has an average benchmark score of 23,249, while the RTX 2070 SUPER averages 20,282. The P106-100's higher average comes from a different mix of tests, not from beating the RTX 2070 SUPER in any direct comparison.

Q: How do these cards rank against all other GPUs?

A: The P106-100 sits at the 68th percentile, while the RTX 2070 SUPER sits at the 65th percentile. Both are mid-range performers in the overall database.

Q: Which card has a higher boost clock?

A: The RTX 2070 SUPER has a boost clock of 1770 MHz, compared to the P106-100's 1709 MHz.

Architecture Differences

The two cards come from different NVIDIA architectures and generations. The P106-100 uses the GP106 chip on the Pascal architecture, released as part of the Mining GPUs generation. The RTX 2070 SUPER uses the TU104 chip on the Turing architecture, belonging to the GeForce 20 series. The RTX 2070 SUPER is built on a 12 nm process at TSMC, while the P106-100 uses a 16 nm process, also at TSMC. This node difference is significant: the RTX 2070 SUPER packs 13,600 million transistors onto a 545 mm² die, whereas the P106-100 contains 4,400 million transistors on a 200 mm² die. Transistor density favors the RTX 2070 SUPER at 25.0M per mm² versus 22.0M per mm² for the P106-100.

The most consequential architectural difference is the inclusion of dedicated hardware on the RTX 2070 SUPER. It features 40 RT cores and 320 tensor cores, neither of which exist on the P106-100. These enable hardware-accelerated ray tracing and AI-driven features, which the Pascal-based P106-100 cannot perform in hardware at all. The RTX 2070 SUPER also doubles the shading units (2560 versus 1280), TMUs (160 versus 80), and adds more ROPs (64 versus 48).

API support also differs. The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), while the P106-100 supports only DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4, so those are not differentiating factors. The Pascal card is limited to a PCIe 1.0 x16 bus interface, while the Turing card uses PCIe 3.0 x16, which affects bandwidth to the host system.

The P106-100 is a mining-oriented product with no display outputs at all. The RTX 2070 SUPER, by contrast, has a full set of display outputs: 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C. This is a fundamental difference in intended use case.

Specification Differences

The two cards differ across nearly every major specification field. The P106-100 has 6 GB of GDDR5 memory on a 192-bit bus, delivering 192.2 GB/s of bandwidth. The RTX 2070 SUPER has 8 GB of GDDR6 memory on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The RTX 2070 SUPER more than doubles memory bandwidth, which directly benefits higher resolutions and texture-heavy workloads.

Clock speeds are closer than other specs. The P106-100 has a base clock of 1506 MHz and a boost clock of 1709 MHz. The RTX 2070 SUPER has a base clock of 1605 MHz and a boost clock of 1770 MHz. Memory clocks differ substantially: the P106-100 runs at 2002 MHz (8 Gbps effective), while the RTX 2070 SUPER runs at 1750 MHz (14 Gbps effective). The effective data rate is much higher on the RTX 2070 SUPER.

Compute throughput shows a clear hierarchy. The P106-100 delivers 4.375 TFLOPS of FP32 performance and 68.36 GFLOPS of FP16 (at a 1:64 ratio). The RTX 2070 SUPER delivers 9.062 TFLOPS of FP32 and 18.12 TFLOPS of FP16 (at a 2:1 ratio). The FP16 gap is enormous, over 265 times in favor of the RTX 2070 SUPER, because the Turing card has dedicated tensor cores that accelerate half-precision work. Pixel rate and texture rate also favor the RTX 2070 SUPER: 113.3 GPixel/s versus 82.03 GPixel/s, and 283.2 GTexel/s versus 136.7 GTexel/s, respectively.

Power and physical specs differ too. The P106-100 has a TDP of 120 W with a single 6-pin power connector and a suggested PSU of 300 W. The RTX 2070 SUPER has a TDP of 215 W with one 6-pin and one 8-pin connector, and a suggested PSU of 550 W. Both are dual-slot cards. The P106-100 is 250 mm (9.8 inches) long, while the RTX 2070 SUPER is 267 mm (10.5 inches) long, 116 mm (4.6 inches) tall, and 35 mm (1.4 inches) wide.

Release dates also differ. The P106-100 launched on 2017-06-18, while the RTX 2070 SUPER launched on 2019-07-08. Both are now end-of-life. The RTX 2070 SUPER has a predecessor in the GeForce 10 series and a successor in the GeForce 30 series; the P106-100 has neither recorded. The RTX 2070 SUPER had a launch MSRP of 499 USD; the P106-100 has no recorded launch MSRP.

Where Each One Wins

The RTX 2070 SUPER wins every measurable benchmark category. In 3DMark Steel Nomad DX12, it leads by 45.5%. In Geekbench OpenCL, it leads by 56.9%. In Geekbench Vulkan, it leads by 63.7%. There is no test in the database where the P106-100 takes the lead.

The RTX 2070 SUPER is the clear choice for any workload that benefits from raw compute throughput, ray tracing, or AI acceleration. Its 40 RT cores and 320 tensor cores enable features the P106-100 simply cannot provide. Its double FP32 throughput (9.062 TFLOPS versus 4.375 TFLOPS) and vastly higher FP16 throughput (18.12 TFLOPS versus 68.36 GFLOPS) make it suitable for compute-intensive tasks like rendering, simulation, and machine learning inference.

The P106-100 does have one notable advantage: efficiency. Its 120 W TDP is nearly half the RTX 2070 SUPER's 215 W. It also requires a smaller PSU (300 W versus 550 W) and a single 6-pin connector versus the RTX 2070 SUPER's 6-pin plus 8-pin setup. For a system with limited power delivery or a constrained chassis, the P106-100 is easier to accommodate physically.

The P106-100's higher average benchmark score (23,249 versus 20,282) and higher percentile (68 versus 65) suggest that in certain undemanding workloads, the Pascal card can hold its own relative to the broader GPU landscape. However, this is not evidence of superiority over the RTX 2070 SUPER; it reflects the different test sets recorded for each card.

For gaming and general-purpose graphics, the RTX 2070 SUPER is the only viable option of the two, because the P106-100 has no display outputs. It cannot drive a monitor at all. The RTX 2070 SUPER, with its HDMI 2.0, DisplayPort 1.4a, and USB Type-C outputs, is a fully functional graphics card.

The Verdict

The data points to one conclusion: the NVIDIA GeForce RTX 2070 SUPER is the superior product in every head-to-head comparison. It wins all three benchmark tests, with margins ranging from 45.5% to 63.7%. Its architectural advantages, including RT cores, tensor cores, double the shading units, and more than double the memory bandwidth, translate directly into higher scores across the board.

The P106-100 is a mining-specific card with no display outputs, a 120 W TDP, and Pascal-era specifications. It was never designed for general-purpose graphics use. Its only advantages are lower power consumption and a smaller physical footprint, which matter only in specialized mining or compute scenarios where display output is irrelevant.

For anyone choosing between these two based on the database measurements, the RTX 2070 SUPER is the clear pick for gaming, content creation, or any workload requiring display output or modern feature support. The P106-100 is only relevant for niche use cases where its lower power draw is the priority and where its lack of display output is acceptable.

The RTX 2070 SUPER's launch MSRP was 499 USD. Its end-of-life status means it is no longer in production, but its benchmark performance remains competitive in the mid-range tier of the database. The P106-100, also end-of-life, offers no benchmark win and no functional display capability, making it a poor general-purpose choice.

Ultimately, the recorded data shows a decisive victory for the RTX 2070 SUPER across every metric that matters for a graphics card. The P106-100's sole advantages are power and size, which do not compensate for its complete lack of display outputs and its substantial performance deficits.