NVIDIA GeForce RTX 5090 Performance Boost: 37% Faster Than RTX 4090 in Vulkan, 16% Faster in OpenCL Benchmarks

The upcoming NVIDIA GeForce RTX 5090 GPU has recently been evaluated using the Geekbench OpenCL and Vulkan APIs, revealing a notable performance enhancement of up to 37% in Vulkan applications, compared to its predecessor, the RTX 4090.

NVIDIA GeForce RTX 5090 “Blackwell Flagship”GPU Performance Insights

Set to launch soon, the next-generation GeForce RTX 5090 promises significant advancements in graphics performance. Early independent benchmark leaks suggest a substantial uplift, particularly with NVIDIA’s DLSS technology. Initial claims by NVIDIA indicate a potential twofold increase in performance over the RTX 4090, although these figures mainly reflect projections using DLSS 4. In real-time (RT, native) scenarios, performance improvements hover around 30%.

NVIDIA GeForce RTX 5090 OpenCL Benchmark — Image Source: Geekbench 6

Exploring the benchmark results, the RTX 5090 recorded an impressive score of 367,740 points in the OpenCL API, which is 16% superior to the RTX 4090. In the Vulkan API tests, it achieved a score of 359,742 points. While this figure appears lower than the OpenCL score, it actually represents a remarkable 37% increase over the RTX 4090’s results.

NVIDIA GeForce RTX 5090 Vulkan Benchmark — Image Source: Geekbench 6

However, it is crucial to consider some limitations surrounding these benchmarks. For optimal performance, a powerful CPU is essential. The Core i9-12900K utilized during testing is not the absolute top model available, and it also employs older DDR4-3600 memory. This leaves room for enhancing overall performance outcomes.

Comparison with Existing Enthusiast-Grade Graphics Cards

The following table summarizes how the NVIDIA GeForce RTX 5090 compares against leading GPUs in the market:

Graphics Card Name	NVIDIA GeForce RTX 5090	NVIDIA GeForce RTX 4090	NVIDIA GeForce RTX 4080 SUPER	NVIDIA GeForce RTX 4080	NVIDIA GeForce RTX 4070 Ti SUPER	RX 7900 XTX
Benchmark Score	367740	317365	247567	239844	223106	211584

Drawing closer to its official release, expected within the next few weeks, the NVIDIA GeForce RTX 5090 is set to be the flagship model in the RTX 50 “Blackwell”Gaming series. It is rumored to retail at an MSRP of $1999 USD, which is a $400 premium above the RTX 4090. In addition to its enhanced performance, the RTX 5090 will incorporate cutting-edge features including DLSS 4 technology with Multi-Frame Generation support. Various AIBs (Add-in-Board partners) will provide custom variants, alongside NVIDIA’s sleek Founders Edition that features a dual-slot, dual-fan design.

Preliminary Specifications for NVIDIA GeForce RTX 50 GPUs

Graphics Card Name	NVIDIA GeForce RTX 5090	NVIDIA GeForce RTX 5080	NVIDIA GeForce RTX 5070 Ti	NVIDIA GeForce RTX 5070	NVIDIA GeForce RTX 5060 Ti	NVIDIA GeForce RTX 5060
GPU Name	Blackwell GB202-300	Blackwell GB203-400	Blackwell GB203-300-A1	Blackwell GB205-300-A1	Blackwell GB206?	Blackwell GB206?
GPU SMs	170 (192 Full)	84 (84 Full)	70 (84 Full)	50 (50 SM Full)	TBD	TBD
GPU Cores	21760 (+33%)	10752 (+11%)	8960 (+16%)	6144	TBD	TBD
Clock Speeds	2.41 GHz	2.62 GHz	2.45 GHz	2.51 GHz	TBD	TBD
L2 Cache	TBD	TBD	TBD	TBD	TBD	TBD
Memory Capacity	32 GB GDDR7 (+33%)	16 GB GDDR7 (0%)	16 GB GDDR7	12 GB GDDR7	16 GB GDDR7	8 GB GDDR7
Memory Bus	512-bit (+33%)	256-bit (0%)	256-bit (0%)	192-bit (0%)	128-bit (0%)	128-bit (0%)
Memory Speed	28 Gbps	30 Gbps	28 Gbps	28 Gbps	28 Gbps?	28 Gbps?
Bandwidth	1792 GB/s	960GB/s	896 GB/s	672 GB/s	448 GB/s	448 GB/s
TBP	575W (+27%)	360W (+12.5%)	300W (+10.5%)	250W (+14%)	TBD	TBD
Power Interface	1 12V-2×6 (16-Pin)	1 12V-2×6 (16-Pin)	1 12V-2×6 (16-Pin)	1 12VHPWR (16-Pin)	1 12VHPWR (16-Pin)	1 12VHPWR (16-Pin)
Launch	January 2025	January 2025	February 2025	February 2025	March-April 2025	March-April 2025
Price	$1999 USD	$999 USD	$749 USD	$549 USD	TBD	TBD