GPU comparison · 1080p benchmark
RX 6950 XT 16GB recorded 384 FPS against 152 FPS for RX 5700 XT 8GB. These are continuous 1080p benchmark averages, not predicted FPS in any particular game.
RX 5700 XT 8GB
152Benchmark FPS at 1080p- Our rating
- 56.3 / 100
- Graphics memory
- 8GB
- Released
- July 2019
- GPUsed cards tested
- 72
RX 6950 XT 16GB
384Benchmark FPS at 1080p- Our rating
- 77.9 / 100
- Graphics memory
- 16GB
- Released
- May 2022
- GPUsed cards tested
- 14
Change either GPU in the comparison tool
What does this comparison mean?
The RX 6950 XT doubles the RX 5700 XT's memory to 16GB and records a large lead. The later refresh is distinct from the RX 6900 XT; use the exact board and result when evaluating the replacement.
RX 5700 XT 8GB has 8GB and RX 6950 XT 16GB has 16GB of graphics memory. Memory capacity, board dimensions, power connectors and the price of a particular used card are separate from this benchmark. Compare the exact item before deciding whether to upgrade.
The two GPUs in context
RX 5700 XT 8GB
The RX 5700 XT is an 8GB Radeon model introduced with the first RDNA generation in July 2019.
RX 6950 XT 16GB
The RX 6950 XT is a 16GB GDDR6 RDNA 2 card introduced in AMD's May 2022 Radeon refresh.
Release and feature sources: RX 5700 XT 8GB source · RX 6950 XT 16GB source.
How the figures are compared
Both FPS figures come from the owner-supplied GPUsed benchmark dataset. GPUsed reports a continuous FurMark run at 1080p for its physical-card checks. The percentage compares the higher model average with the lower one using the original FPS values. Our rating uses a compressed scale, with the fastest GPU at 100; it is separate from the percentage difference. A benchmark result does not predict gaming FPS.
GPUsed reports its physical-card checks typically last 30 to 60 minutes while temperature and stability are checked. The owner supplied the model-level FPS workbook on 2 October 2026; this benchmark dataset was last reconciled 3 October 2026. Historical cards tested are separate from the number of FPS runs behind a model average. Full benchmark method.