AMD Radeon R9 370X vs NVIDIA GeForce RTX 2070 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 2070 has an average benchmark score of 18789, which places it in the 63rd percentile of all GPUs. The AMD Radeon R9 370X has an average score of 15862, placing it in the 58th percentile.

Q: How far ahead is the RTX 2070 in OpenCL performance?

A: In the Geekbench OpenCL test, the RTX 2070 scores 79966 versus 25893 for the R9 370X. This is a 208.8% lead for the NVIDIA card, meaning it delivers more than triple the compute performance in this workload.

Q: What is the largest performance gap between the two cards?

A: The largest recorded gap appears in Geekbench Vulkan, where the RTX 2070 scores 82521 against the R9 370X's 9018. That is an 815.1% difference, making the NVIDIA card over nine times faster in this specific API test.

Q: Do both cards support the same DirectX version?

A: No. The RTX 2070 supports DirectX 12 Ultimate (12_2), while the R9 370X supports DirectX 12 (11_1). The NVIDIA card also supports Vulkan 1.4, whereas the AMD card supports Vulkan 1.2.170.

Q: Which card has more memory bandwidth?

A: The RTX 2070 has 448.0 GB/s of bandwidth with 8 GB of GDDR6 memory on a 256-bit bus. The R9 370X has 179.2 GB/s with 2 GB of GDDR5 memory on the same 256-bit bus width.

Q: Are both cards still in production?

A: No, both are end-of-life products. The RTX 2070 was released in October 2018, and the R9 370X was released in August 2015.

Architecture Differences

The two cards come from entirely different architectural eras. The NVIDIA GeForce RTX 2070 uses the TU106 chip built on Turing architecture, manufactured by TSMC on a 12 nm process. It contains 10,800 million transistors on a 445 mm² die, giving a transistor density of 24.3 million per mm². The AMD Radeon R9 370X uses the Trinidad chip based on GCN 1.0 architecture, also from TSMC but on an older 28 nm process. It has 2,800 million transistors on a 212 mm² die, with a much lower density of 13.2 million per mm².

The RTX 2070 is a modern feature-rich design. It includes 36 ray tracing cores and 288 tensor cores, which are absent entirely from the R9 370X. The NVIDIA card has 2304 shading units, 144 texture mapping units, and 64 ROPs. The AMD card has 1280 shading units, 80 TMUs, and 32 ROPs. These raw resource counts explain much of the performance difference.

Clock speeds also differ significantly. The RTX 2070 has a base clock of 1410 MHz and a boost clock of 1620 MHz. The R9 370X runs at 980 MHz base and 1030 MHz boost. Memory technology is another divider: the RTX 2070 uses GDDR6 at 1750 MHz (14 Gbps effective), while the R9 370X uses GDDR5 at 1400 MHz (5.6 Gbps effective).

The feature set reflects the gap in generation. The RTX 2070 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The R9 370X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Display outputs differ as well: the RTX 2070 has 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C, while the R9 370X has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2.

Power consumption is surprisingly close. The RTX 2070 is rated at 175 W TDP with a single 8-pin connector, while the R9 370X is rated at 180 W TDP with two 6-pin connectors. Both recommend a 450 W power supply.

Head-to-Head Benchmarks

The database records two head-to-head benchmark comparisons between these cards, and the RTX 2070 wins both decisively.

In Geekbench OpenCL, the RTX 2070 scores 79966, while the R9 370X scores 25893. This is a 208.8% advantage for the NVIDIA card. What does this mean in practice? OpenCL workloads that stress raw compute throughput, such as physics simulations, video encoding, or general-purpose GPU tasks, will complete in roughly one-third of the time on the RTX 2070. The R9 370X is not competitive here; its older GCN architecture and lower shader count simply cannot match the Turing design.

The Vulkan test is even more lopsided. The RTX 2070 scores 82521, versus 9018 for the R9 370X, a delta of 815.1%. Vulkan is a low-overhead API that benefits from modern hardware features and driver optimization. The RTX 2070's support for Vulkan 1.4, combined with its newer architecture, results in a score that is over nine times higher. This suggests that any Vulkan-based game or application will run dramatically better on the NVIDIA card, assuming the rest of the system can keep up.

The R9 370X has no recorded wins in any head-to-head test. The RTX 2070 wins 2 out of 2 comparisons. In absolute terms, the RTX 2070's average benchmark score of 18789 is 18.4% higher than the R9 370X's 15862. The percentile rankings reflect this: 63rd versus 58th among all GPUs.

Looking at the nearest rivals for context, the RTX 2070 sits very close to the NVIDIA Tesla K80 (delta of -0.4%) and the AMD Radeon Pro 5700 XT (delta of 0.6%). The R9 370X sits near the AMD Radeon RX 7700 (delta of 0.1%) and the NVIDIA GeForce RTX 3060 Ti (delta of -1.7%). This shows that the R9 370X, despite its age, lands in a similar performance bracket to much newer cards, but that bracket is far below the RTX 2070's.

The Verdict

The data is unambiguous. The NVIDIA GeForce RTX 2070 is the faster card in every measured category. Its average benchmark score is 18789, compared to 15862 for the AMD Radeon R9 370X. The RTX 2070 wins the OpenCL test by 208.8% and the Vulkan test by 815.1%. There is no scenario in the recorded benchmarks where the R9 370X comes out ahead.

For a builder choosing between these two today, the RTX 2070 is the only reasonable pick if performance is the priority. It offers more than double the compute performance in OpenCL, and its Vulkan performance is in a different league entirely. The R9 370X is a much older design with a smaller feature set, less memory, and lower bandwidth. While both cards are end-of-life, the RTX 2070 clearly belongs to a higher performance tier.

That said, the R9 370X is not without a place. Its lower launch MSRP of 199 USD (versus 499 USD for the RTX 2070) reflects its more modest capabilities. For workloads that do not stress the GPU heavily, or for systems where the rest of the hardware is equally dated, the R9 370X could still function. But the benchmark data gives no reason to prefer it over the RTX 2070 in any performance-sensitive task.

Specification Differences

| Specification | NVIDIA GeForce RTX 2070 | AMD Radeon R9 370X |

|----------------|--------------------------|---------------------|

| Architecture | Turing | GCN 1.0 |

| Process Node | 12 nm | 28 nm |

| Transistors | 10,800 million | 2,800 million |

| Die Size | 445 mm² | 212 mm² |

| Base Clock | 1410 MHz | 980 MHz |

| Boost Clock | 1620 MHz | 1030 MHz |

| Memory Size | 8 GB GDDR6 | 2 GB GDDR5 |

| Memory Clock | 1750 MHz (14 Gbps effective) | 1400 MHz (5.6 Gbps effective) |

| Memory Bandwidth | 448.0 GB/s | 179.2 GB/s |

| Shading Units | 2304 | 1280 |

| TMUs | 144 | 80 |

| ROPs | 64 | 32 |

| RT Cores | 36 | None |

| Tensor Cores | 288 | None |

| Pixel Rate | 103.7 GPixel/s | 32.96 GPixel/s |

| Texture Rate | 233.3 GTexel/s | 82.40 GTexel/s |

| FP32 | 7.465 TFLOPS | 2.637 TFLOPS |

| FP16 | 14.93 TFLOPS (2:1) | None |

| TDP | 175 W | 180 W |

| Power Connectors | 1x 8-pin | 2x 6-pin |

| DirectX | 12 Ultimate (12_2) | 12 (11_1) |

| Vulkan | 1.4 | 1.2.170 |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, 1x USB Type-C | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 |

| Length | 229 mm (9 inches) | 221 mm (8.7 inches) |

| Height | 113 mm (4.4 inches) | 111 mm (4.4 inches) |

Where Each One Wins

The NVIDIA GeForce RTX 2070 wins in every head-to-head benchmark recorded in the database. Its strengths are most pronounced in Vulkan workloads, where it scores 82521 versus 9018, an 815.1% lead. This makes it the clear choice for any application that uses the Vulkan API, which includes many modern games and compute frameworks. The RTX 2070 also dominates OpenCL with a 208.8% advantage, making it far better suited for general-purpose GPU compute tasks.

The RTX 2070 also has significant advantages in memory capacity and bandwidth. With 8 GB of GDDR6 and 448.0 GB/s, it can handle larger textures, higher resolutions, and more complex scenes than the R9 370X's 2 GB of GDDR5 at 179.2 GB/s. The RTX 2070's pixel rate of 103.7 GPixel/s and texture rate of 233.3 GTexel/s are more than triple the R9 370X's 32.96 GPixel/s and 82.40 GTexel/s, indicating far better fill-rate performance.

The AMD Radeon R9 370X has no recorded wins in the head-to-head data. Its closest rival comparisons show it performing near the AMD Radeon RX 7700 (delta 0.1%) and the AMD Radeon Pro W5500 (delta 1.2%), but those are still far below the RTX 2070's performance tier. The R9 370X does have a lower TDP in practice despite the similar 180 W rating versus 175 W, and its smaller 221 mm length could fit in tighter cases, but these are minor physical advantages, not performance wins.

For a builder with a strict need for modern features like ray tracing, tensor cores, or DirectX 12 Ultimate, the RTX 2070 is the only option. For a system where the GPU is not the bottleneck, the R9 370X might suffice, but the data shows no workload where it outperforms the RTX 2070. The RTX 2070 is the recommended choice for gaming, compute, and any future-proofing considerations.