AMD Radeon HD 8970M vs NVIDIA GeForce RTX 2070 SUPER Comparison

The benchmark data positions the NVIDIA GeForce RTX 2070 SUPER as the overwhelming performance leader, with the AMD Radeon HD 8970M trailing by a significant margin in the only directly comparable test. The RTX 2070 SUPER’s score of 83,358 in Geekbench OpenCL dwarfs the HD 8970M’s 21,237, a difference of 74.5% in favor of the NVIDIA part. While the HD 8970M holds a slight edge in percentile ranking (66th vs 65th), this is a statistical artifact of its age and the pool of GPUs it is compared against, not an indicator of real-world capability. The data unequivocally shows that the RTX 2070 SUPER is in a different performance class.

Head-to-Head Benchmarks

The single head-to-head benchmark available, Geekbench OpenCL, delivers a decisive verdict. The NVIDIA GeForce RTX 2070 SUPER scores 83,358, while the AMD Radeon HD 8970M scores 21,237. This translates to a delta of -74.5% for the AMD part, meaning the RTX 2070 SUPER is roughly four times faster in this compute workload. The result is not a close contest; it is a categorical win for the newer architecture.

Looking at the broader benchmark suite for the RTX 2070 SUPER, its dominance extends across various APIs. Its Geekbench Vulkan score of 90,637 is even higher than its OpenCL result, indicating strong performance in modern, low-level graphics APIs. In contrast, the HD 8970M has no Vulkan score listed, and its DirectX support is limited to 12 (11_1), a feature level that predates the full DirectX 12 Ultimate feature set. The RTX 2070 SUPER also posts a Passmark G3D score of 18,169, a figure that places it far beyond what the older AMD part could achieve, though no direct comparison is possible from the provided data.

The RTX 2070 SUPER’s closest rivals further contextualize its performance. It sits within 1.5% of the Intel Arc A750 and just 1.2% behind the NVIDIA GeForce RTX 3070 Mobile, showing it remains competitive with more recent mid-range options. The HD 8970M, by contrast, is bracketed by the AMD Radeon RX Vega M GL (0.4% ahead) and the NVIDIA RTX A4000 Mobile (0.7% behind), placing it in a performance tier that is now several generations old. The data does not support any scenario where the HD 8970M wins a benchmark; the wins column is 0 for the AMD part and 1 for the NVIDIA part.

Architecture Differences

The two GPUs are separated by six years of architectural evolution, which is the root cause of the performance gap. The AMD Radeon HD 8970M is built on GCN 1.0 architecture using a 28 nm process at TSMC, with a die size of 212 mm² and 2,800 million transistors. In contrast, the NVIDIA GeForce RTX 2070 SUPER uses the Turing architecture on a more advanced 12 nm process, also at TSMC, but with a much larger die of 545 mm² and 13,600 million transistors. This translates to a transistor density of 25.0M / mm² for the NVIDIA chip versus 13.2M / mm² for the AMD chip, highlighting the density advantage of the newer node.

The compute resources are starkly different. The RTX 2070 SUPER features 2,560 shading units, 160 texture mapping units (TMUs), and 64 render output units (ROPs). The HD 8970M has 1,280 shading units, 80 TMUs, and 32 ROPs. Furthermore, the RTX 2070 SUPER introduces dedicated hardware that the AMD part lacks entirely: 40 RT cores for ray tracing and 320 tensor cores for AI acceleration. These are not present in the GCN 1.0 architecture, which predates these features.

Clock speeds and memory technology also favor the NVIDIA part. The RTX 2070 SUPER has a base clock of 1605 MHz and a boost clock of 1770 MHz, while the HD 8970M operates at 850 MHz base and 900 MHz boost. Memory is another major differentiator: the RTX 2070 SUPER uses 8 GB of GDDR6 at 14 Gbps effective, delivering 448.0 GB/s of bandwidth over a 256-bit bus. The HD 8970M uses 4 GB of GDDR5 at 4.8 Gbps effective, yielding only 153.6 GB/s on the same 256-bit bus. The bandwidth deficit alone hampers the older card in texture-heavy and high-resolution workloads.

The feature set reflects the generational leap. The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the HD 8970M is limited to DirectX 12 (11_1) and Vulkan 1.2.170. The NVIDIA card also includes display outputs like HDMI 2.0 and DisplayPort 1.4a, whereas the AMD card’s outputs are listed as "Portable Device Dependent," reflecting its mobile MXM Module form factor. The RTX 2070 SUPER is a dual-slot desktop card with a 267 mm length, while the HD 8970M is a mobile module.

Where Each One Wins

Based strictly on the data, the NVIDIA GeForce RTX 2070 SUPER wins in every measurable category. Its advantages are not marginal; they are structural. In compute performance, the OpenCL score of 83,358 versus 21,237 means the RTX 2070 SUPER is the only choice for GPU-accelerated tasks like rendering, scientific simulation, or machine learning inference. The presence of tensor cores and RT cores gives it capabilities in AI workloads and ray-traced gaming that the HD 8970M cannot access at all.

The HD 8970M’s only "win" is its percentile ranking of 66th versus the RTX 2070 SUPER’s 65th. This is a narrow statistical quirk, likely because the HD 8970M is compared against a database of GPUs that includes many older, slower parts, whereas the RTX 2070 SUPER is compared against a more modern field. This does not translate to a practical advantage in any workload. The HD 8970M also has a lower TDP of 100 W versus 215 W, making it more power-efficient in absolute terms, but this is a design constraint of its mobile form factor, not a performance feature.

For gaming, the RTX 2070 SUPER’s Passmark DirectX 9, 10, 11, and 12 scores (223, 132, 151, and 67 respectively) show it handles legacy APIs well, while its DirectX 12 Ultimate support ensures it is ready for current titles. The HD 8970M’s DirectX 11_1 feature level means it lacks support for modern features like mesh shaders and variable rate shading, which are integral to newer games. In any scenario requiring modern graphics features or high compute throughput, the RTX 2070 SUPER is the definitive winner.

FAQ

Q: Which GPU has a higher Geekbench OpenCL score?

A: The NVIDIA GeForce RTX 2070 SUPER scores 83,358, while the AMD Radeon HD 8970M scores 21,237, a difference of 74.5% in favor of the NVIDIA card.

Q: Does the AMD Radeon HD 8970M support ray tracing?

A: No. The HD 8970M has no RT cores listed in its specifications, while the RTX 2070 SUPER includes 40 RT cores for ray tracing.

Q: What is the memory bandwidth of each GPU?

A: The RTX 2070 SUPER has a memory bandwidth of 448.0 GB/s using 8 GB of GDDR6, while the HD 8970M has 153.6 GB/s using 4 GB of GDDR5.

Q: Which GPU has a higher transistor count?

A: The NVIDIA GeForce RTX 2070 SUPER has 13,600 million transistors, compared to 2,800 million for the AMD Radeon HD 8970M.

Q: What DirectX version does each GPU support?

A: The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), whereas the HD 8970M supports DirectX 12 (11_1).

Q: How do their nearest rivals compare?

A: The RTX 2070 SUPER is 1.3% behind the Intel Arc B570 and 1.5% behind the Intel Arc A750. The HD 8970M is 0.4% ahead of the AMD Radeon RX Vega M GL and 0.7% behind the NVIDIA RTX A4000 Mobile.

Specification Differences

The following specifications differ between the two GPUs:

• Process Node: 28 nm (AMD) vs 12 nm (NVIDIA)
• Transistors: 2,800 million vs 13,600 million
• Die Size: 212 mm² vs 545 mm²
• Transistor Density: 13.2M / mm² vs 25.0M / mm²
• Base Clock: 850 MHz vs 1605 MHz
• Boost Clock: 900 MHz vs 1770 MHz
• Memory Clock: 1200 MHz (4.8 Gbps effective) vs 1750 MHz (14 Gbps effective)
• Memory Size: 4 GB vs 8 GB
• Memory Type: GDDR5 vs GDDR6
• Memory Bandwidth: 153.6 GB/s vs 448.0 GB/s
• Shading Units: 1280 vs 2560
• TMUs: 80 vs 160
• ROPs: 32 vs 64
• RT Cores: None vs 40
• Tensor Cores: None vs 320
• Pixel Rate: 28.80 GPixel/s vs 113.3 GPixel/s
• Texture Rate: 72.00 GTexel/s vs 283.2 GTexel/s
• FP32: 2.304 TFLOPS vs 9.062 TFLOPS
• FP16: None vs 18.12 TFLOPS (2:1)
• TDP: 100 W vs 215 W
• Slot Width: MXM Module vs Dual-slot
• Power Connectors: None vs 1x 6-pin + 1x 8-pin
• Suggested PSU: None vs 550 W
• Display Outputs: Portable Device Dependent vs 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C
• DirectX: 12 (11_1) vs 12 Ultimate (12_2)
• Vulkan: 1.2.170 vs 1.4
• Dimensions: None vs 267 mm (length), 116 mm (height), 35 mm (width)
• Release Date: 2013-05-13 vs 2019-07-08
• Launch MSRP: None vs 499 USD

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 2070 SUPER is the superior product by every performance metric. Its 74.5% lead in OpenCL compute, combined with its modern feature set (RT cores, tensor cores, DirectX 12 Ultimate), makes it the only rational choice for any workload involving current games, content creation, or GPU compute. The HD 8970M’s higher percentile rank is a statistical quirk that does not reflect real capability.

Users who require maximum performance should pick the RTX 2070 SUPER without hesitation. The AMD Radeon HD 8970M is only relevant for legacy systems where its 100 W TDP and MXM form factor are a requirement, and even then, its performance is severely limited by its 2013-era architecture. For any new build or upgrade, the RTX 2070 SUPER is the definitive winner.