GPU comparison · 1080p benchmark
RX 6700 XT 12GB recorded 195 FPS against 79 FPS for RX 580 8GB. These are continuous 1080p benchmark averages, not predicted FPS in any particular game.
RX 580 8GB
79Benchmark FPS at 1080p- Our rating
- 44.8 / 100
- Graphics memory
- 8GB
- Released
- April 2017
- GPUsed cards tested
- 100
RX 6700 XT 12GB
195Benchmark FPS at 1080p- Our rating
- 61.4 / 100
- Graphics memory
- 12GB
- Released
- March 2021
- GPUsed cards tested
- 72
Change either GPU in the comparison tool
What does this comparison mean?
The RX 6700 XT raises capacity from the RX 580's 8GB to 12GB and records a much higher average. Keep the XT suffix: the non-XT RX 6700 is a different 10GB model.
RX 580 8GB has 8GB and RX 6700 XT 12GB has 12GB 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 580 8GB
The RX 580 8GB is a Polaris-generation Radeon introduced in April 2017. This comparison uses the 8GB variant, rather than the separate 4GB card.
RX 6700 XT 12GB
AMD introduced the RX 6700 XT in March 2021 with RDNA 2 architecture and 12GB of GDDR6.
Release and feature sources: RX 580 8GB source · RX 6700 XT 12GB 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.