GPU comparison · 1080p benchmark
RX 6900 XT 16GB recorded 368 FPS against 136 FPS for RTX 2060 12GB. These are continuous 1080p benchmark averages, not predicted FPS in any particular game.
RTX 2060 12GB
136Benchmark FPS at 1080p- Our rating
- 54.2 / 100
- Graphics memory
- 12GB
- Released
- December 2021
- GPUsed cards tested
- 10
RX 6900 XT 16GB
368Benchmark FPS at 1080p- Our rating
- 76.7 / 100
- Graphics memory
- 16GB
- Released
- December 2020
- GPUsed cards tested
- 22
Change either GPU in the comparison tool
What does this comparison mean?
Moving from RTX 2060 12GB to RX 6900 XT 16GB increases the recorded result from 136 to 368 FPS and graphics memory from 12GB to 16GB. The uplift is 170.6% in this workload with 4GB more capacity; the benchmark cannot tell us how much of the difference comes from memory rather than the rest of the GPU.
RTX 2060 12GB has 12GB and RX 6900 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
RTX 2060 12GB
This is the later 12GB GDDR6 RTX 2060, retaining Turing architecture. MSI documented a December 2021 release for its 12GB board.
RX 6900 XT 16GB
The RX 6900 XT arrived in December 2020 with RDNA 2 architecture and 16GB of GDDR6. It uses the full Navi 21 configuration, rather than the reduced configuration of the RX 6800 XT.
Release and feature sources: RTX 2060 12GB source · RX 6900 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.