NVIDIA GeForce GTX 1650 SUPER vs NVIDIA GeForce GTX 590 Comparison

Head-to-Head Benchmarks

The only direct comparison available in the database is the Geekbench OpenCL compute test. This is a significant matchup because it measures raw general-purpose computing throughput, not just graphics rendering. The results are lopsided in favor of the newer card.

The NVIDIA GeForce GTX 1650 SUPER scores 43,875 points in Geekbench OpenCL. The NVIDIA GeForce GTX 590 scores 12,830 points. That is a delta of negative 70.8 percent for the GTX 590, meaning the GTX 1650 SUPER is roughly 3.4 times faster in this workload. The GTX 590's score sits at the 52nd percentile of all GPUs in the database, while the GTX 1650 SUPER sits at the 50th percentile, a curious situation where the older flagship falls behind in raw compute but remains statistically near its rival in overall standing due to the distribution of scores across the database.

Context is important here. The GTX 590's nearest rivals in the database are the AMD Radeon Pro 455 at 12,831 points (a 0 percent delta), the AMD FirePro W5100 at 12,847 points (negative 0.1 percent), the AMD Radeon 740M at 12,870 points (negative 0.3 percent), and the NVIDIA GeForce GTX 670 at 12,773 points (positive 0.4 percent). Those deltas are tiny, indicating that the GTX 590 performs almost exactly in line with those cards in this test. Meanwhile, the GTX 1650 SUPER's nearest rivals are the AMD Radeon RX 550 at 11,075 points (negative 0.2 percent), the NVIDIA RTX PRO 6000D Blackwell Max-Q at 11,088 points (negative 0.4 percent), the NVIDIA RTX PRO 6000 Blackwell Max-Q at 11,088 points (negative 0.4 percent), and the NVIDIA GeForce MX350 at 10,883 points (positive 1.5 percent). Again, the deltas are narrow, showing the GTX 1650 SUPER clusters tightly with those products. This grouping reinforces the gap between the two cards: each belongs to a different performance tier in the database.

The GTX 590 has no other benchmark entries beyond Geekbench OpenCL, so its average benchmark score is identical to that single result: 12,830. The GTX 1650 SUPER has a broader benchmark portfolio, including 3DMark Steel Nomad DX12 at 352 points, Passmark DirectX 9 at 148 points, Passmark DirectX 11 at 73 points, Passmark DirectX 10 at 50 points, Passmark DirectX 12 at 45 points, Passmark G2D at 749 points, Passmark G3D at 10,179 points, Passmark GPU Compute at 4,477 points, Geekbench Vulkan at 50,519 points, and the aforementioned Geekbench OpenCL result. Its average benchmark score across all entries is 11,047, which is lower than its OpenCL score alone due to the inclusion of lighter DirectX and 2D tests. The GTX 590 has no data for those other workloads, so a full head-to-head across multiple APIs is not possible from the recorded measurements.

What the data shows is a clear generational shift in compute capability. The GTX 590 was designed for a different era of software and APIs, while the GTX 1650 SUPER benefits from architectural advancements that show up strongly in OpenCL. The single head-to-head result is decisive, but it also leaves questions about gaming performance unanswered, since no DirectX gaming benchmark compares the two directly.

FAQ

Q: Which GPU scores higher in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1650 SUPER scores 43,875 points, while the NVIDIA GeForce GTX 590 scores 12,830 points. The GTX 1650 SUPER leads by 70.8 percent in this test.

Q: How does the GTX 590 compare to its nearest rivals?

A: Its nearest rival is the AMD Radeon Pro 455 at 12,831 points with a 0 percent delta. The AMD FirePro W5100 is at 12,847 points with a negative 0.1 percent delta, the AMD Radeon 740M is at 12,870 points with a negative 0.3 percent delta, and the NVIDIA GeForce GTX 670 is at 12,773 points with a positive 0.4 percent delta.

Q: Does the GTX 1650 SUPER have more benchmark entries than the GTX 590?

A: Yes. The GTX 1650 SUPER has ten recorded benchmark scores, including Geekbench OpenCL, Geekbench Vulkan, multiple Passmark tests, and 3DMark Steel Nomad DX12. The GTX 590 has only one recorded benchmark score, the Geekbench OpenCL result.

Q: What is the GTX 1650 SUPER's average benchmark score?

A: The average benchmark score for the GTX 1650 SUPER is 11,047, which reflects all ten of its recorded benchmarks. Its highest single score is Geekbench Vulkan at 50,519 points.

Q: What is the GTX 590's average benchmark score?

A: The average benchmark score for the GTX 590 is 12,830, which is the same as its single Geekbench OpenCL result because no other benchmarks are recorded for it.

Q: Are the two cards close in overall database percentile?

A: They are close. The GTX 590 sits at the 52nd percentile of all GPUs, and the GTX 1650 SUPER sits at the 50th percentile, despite the large gap in OpenCL compute scores.

Where Each One Wins

The GTX 1650 SUPER wins the only direct head-to-head benchmark, Geekbench OpenCL, by a wide margin of 70.8 percent. That makes it the clear choice for compute-oriented workloads that rely on OpenCL acceleration, such as general-purpose GPU tasks, physics simulations, and certain content creation pipelines. Its higher shading unit count and modern architecture translate directly into better raw throughput. The GTX 1650 SUPER also has a full suite of benchmark data across multiple APIs, including Geekbench Vulkan at 50,519 points, Passmark G3D at 10,179 points, and Passmark GPU Compute at 4,477 points. Those results indicate a card that handles a wide range of modern workloads, from DirectX 9 legacy titles to DirectX 12 and Vulkan applications.

The GTX 590 has no recorded wins in any head-to-head test because the database only contains one comparison, and it loses that one. However, the GTX 590 is not without merit in the broader context. Its percentile ranking is slightly higher than the GTX 1650 SUPER's, at 52 versus 50, and its nearest rivals include professional workstation cards like the AMD FirePro W5100 and AMD Radeon Pro 455, which suggests it still holds its own among older compute-oriented products. The GTX 590's 384-bit memory bus and 164.0 GB/s bandwidth give it a memory throughput profile that differs from the GTX 1650 SUPER, though the database does not include a benchmark that isolates memory-bound performance. For users running very old software that was optimized for Fermi-era hardware, the GTX 590 may still function adequately, but the recorded data offers no benchmark result where it beats the GTX 1650 SUPER.

In practical terms, the GTX 1650 SUPER is the better choice for anyone who needs modern API support, higher compute throughput, and a proven track record across multiple benchmark types. The GTX 590 is a historical product whose only recorded benchmark places it far behind the newer card. There is no use case in the data where the GTX 590 comes out ahead.

Specification Differences

The two cards differ in nearly every major specification category. The GTX 590 uses a 40 nm process node, while the GTX 1650 SUPER uses a 12 nm node. The GTX 590 has 3,000 million transistors on a 520 mm² die, giving a transistor density of 5.8 million per square millimeter. The GTX 1650 SUPER has 6,600 million transistors on a 284 mm² die, giving a density of 23.2 million per square millimeter. The newer card packs more than twice the transistors into a much smaller die.

Memory configurations also diverge sharply. The GTX 590 has 1,536 MB of GDDR5 memory on a 384-bit bus, yielding 164.0 GB/s of bandwidth. The GTX 1650 SUPER has 4 GB of GDDR6 memory on a 128-bit bus, yielding 192.0 GB/s of bandwidth. Despite the narrower bus, the GTX 1650 SUPER achieves higher memory bandwidth because of the faster GDDR6 memory running at 12 Gbps effective, compared to the GTX 590's 3.4 Gbps effective GDDR5.

Compute resources differ as well. The GTX 590 has 512 shading units, 64 texture mapping units, and 48 render output units. The GTX 1650 SUPER has 1,280 shading units, 80 texture mapping units, and 32 render output units. Pixel rate favors the GTX 1650 SUPER at 55.20 GPixel/s versus 19.46 GPixel/s for the GTX 590. Texture rate also favors the newer card at 138.0 GTexel/s versus 38.91 GTexel/s. Floating-point performance follows the same trend: the GTX 1650 SUPER delivers 4.416 TFLOPS in FP32, while the GTX 590 delivers 1,244.2 GFLOPS. The GTX 1650 SUPER also has FP16 capability at 8.832 TFLOPS with a 2:1 ratio, a feature the GTX 590 does not list.

Power requirements are dramatically different. The GTX 590 has a TDP of 365 W, requires two 8-pin power connectors, and suggests a 750 W power supply. The GTX 1650 SUPER has a TDP of 100 W, requires a single 6-pin connector, and suggests a 300 W power supply. Physical dimensions also differ: the GTX 590 is 279 mm long, 111 mm high, and 40 mm wide, while the GTX 1650 SUPER is 229 mm long, 111 mm high, and 35 mm wide. Both are dual-slot cards.

The bus interface differs as well. The GTX 590 uses PCIe 2.0 x16, while the GTX 1650 SUPER uses PCIe 3.0 x16. Display outputs are different: the GTX 590 has three DVI ports and one mini-DisplayPort, while the GTX 1650 SUPER has one DVI, one HDMI 2.0, and one DisplayPort 1.4a. The GTX 590 supports DirectX 12 (11_0) and OpenGL 4.6, with no Vulkan support listed. The GTX 1650 SUPER supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The architectural gap between these two GPUs is substantial. The GTX 590 is built on Fermi 2.0 with the GF110 chip, part of the GeForce 500 generation. Fermi was designed around 2010-2011 and was NVIDIA's attempt at a scalable compute architecture, but it was power-hungry and complex. The GTX 590 is essentially a dual-GPU card, which explains its 365 W TDP and dual 8-pin power connectors. The GTX 1650 SUPER uses the Turing architecture with the TU116 chip, part of the GeForce 16 series. Turing introduced major efficiency gains over older architectures, including improved shader execution and support for modern APIs.

The transistor counts tell the story. The GTX 590 packs 3,000 million transistors into a 520 mm² die at 40 nm. The GTX 1650 SUPER packs 6,600 million transistors into a 284 mm² die at 12 nm. That means the newer card has more than double the transistor count in roughly half the die area. The transistor density difference is stark: 5.8 million per square millimeter for the GTX 590 versus 23.2 million per square millimeter for the GTX 1650 SUPER. This is the fundamental reason the GTX 1650 SUPER delivers higher performance with a fraction of the power draw.

Shader architecture also differs. The GTX 590 has 512 shading units, while the GTX 1650 SUPER has 1,280. The GTX 1650 SUPER also has more texture mapping units (80 versus 64) but fewer render output units (32 versus 48). The FP32 compute difference is enormous: 4.416 TFLOPS versus 1,244.2 GFLOPS. The GTX 1650 SUPER also supports FP16 at 8.832 TFLOPS, which the GTX 590 does not list at all. Neither card has ray tracing cores or tensor cores, so both are rasterization and compute-only products.

Memory architecture reflects the generational shift. The GTX 590 uses GDDR5 on a 384-bit bus with 164.0 GB/s bandwidth. The GTX 1650 SUPER uses GDDR6 on a 128-bit bus with 192.0 GB/s bandwidth. The newer memory type and higher effective speed (12 Gbps versus 3.4 Gbps) compensate for the narrower bus. The GTX 590's larger bus width was a product of its dual-GPU design and era, while the GTX 1650 SUPER's smaller bus is offset by faster memory.

API support also differs. The GTX 590 supports DirectX 12 (11_0), which is the feature level 11_0 implementation of DirectX 12. The GTX 1650 SUPER supports DirectX 12 (12_1), which includes additional features like conservative rasterization and rasterizer-ordered views. Both support OpenGL 4.6, but only the GTX 1650 SUPER lists Vulkan 1.4 support; the GTX 590 lists no Vulkan support at all. This makes the GTX 1650 SUPER far more compatible with modern games and applications that rely on Vulkan.

The Verdict

The data supports a straightforward conclusion. The GTX 1650 SUPER is the superior GPU in every measurable way within this database. It wins the only direct head-to-head benchmark by 70.8 percent in Geekbench OpenCL, has more shading units, higher clock speeds, faster memory, better API support, and consumes 100 W instead of 365 W. Its launch MSRP was 159 USD, while the GTX 590 launched at 699 USD, though pricing should not be the deciding factor given the performance gap.

Users who need modern compute performance, Vulkan support, DirectX 12_1 features, and lower power consumption should choose the GTX 1650 SUPER. It also offers a much smaller physical footprint at 229 mm versus 279 mm, and it requires only a 300 W power supply instead of 750 W. The GTX 1650 SUPER is the practical choice for nearly any workload represented in the database.

The GTX 590 remains an interesting historical artifact. Its single benchmark score of 12,830 places it at the 52nd percentile, slightly above the GTX 1650 SUPER's 50th percentile, but that ranking is based on only one test while the GTX 1650 SUPER's ranking is averaged across ten tests. The GTX 590's nearest rivals are professional cards like the AMD FirePro W5100 and AMD Radeon Pro 455, which suggests it retains some relevance in legacy compute environments. However, there is no benchmark result where the GTX 590 wins against the GTX 1650 SUPER. For anyone building a system today or upgrading from an older card, the GTX 1650 SUPER is the only choice supported by the recorded data.