GeForce RTX 2080 Ti vs GeForce RTX 3090: specs and benchmark comparison
BNVIDIA · Ampere
NVIDIA GeForce RTX 3090
- 24 GB GDDR6X
- 350 W
- PSU 750 W+
September 24, 2020 · $1,499 at launch
Short verdict
NVIDIA GeForce RTX 3090 leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.
Compare with AIRendering and compute
B +186.7%NVIDIA GeForce RTX 3090 leads in this scenario (up to 186.7% in comparable benchmarks).
No comparable benchmarks yet: gaming: rasterization, gaming: ray tracing, power efficiency.
Advantages
Only measured and rated values: a noticeable benchmark gap and specs where more is better.
Where GeForce RTX 2080 Ti is better1
Launch price $500 lower$999 vs $1,499
Where GeForce RTX 3090 is better15
Blender Benchmark 2.93.1 100.4% lower17 s vs 34 s
Blender Benchmark 2.93.1 137.4% lower9 s vs 22 s
Blender Benchmark 2.93.1 72.8% lower80 s vs 137 s
Blender Benchmark 2.93.1 157.5% lower33 s vs 86 s
Blender Benchmark 2.93.1 87.7% lower34 s vs 65 s
Blender Benchmark 2.93.1 86.7% lower18 s vs 33 s
Blender Benchmark 2.93.1 87.8% lower55 s vs 102 s
Blender Benchmark 2.93.1 67.2% lower38 s vs 63 s
Blender Benchmark 2.93.1 109.5% lower99 s vs 208 s
Blender Benchmark 2.93.1 133% lower45 s vs 105 s
Blender Benchmark 2.93.1 103.3% lower139 s vs 282 s
Blender Benchmark 2.93.1 128.2% lower60 s vs 138 s
Blender Benchmark 4.5.0 90.6% faster5,424 samples/min vs 2,845 samples/min
Video memory 13 GB more24 GB vs 11 GB
Memory bus 32 bit more384 bit vs 352 bit
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- B ahead by 100.4%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce RTX 2080 Ti33.9 sGeForce RTX 309016.9 sPosition among tested models (31, CUDA)
B · 17A · 340100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 100.4% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
33.9 s · community measurement, sample 53 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 53 submissions (8 outliers excluded), interquartile range 33.42–34.68; submissions 2021-07-15 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
16.9 s · community measurement, sample 279 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 279 submissions (58 outliers excluded), interquartile range 16.76–17.19; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 137.4%
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce RTX 2080 Ti22.1 sGeForce RTX 30909.3 sPosition among tested models (20, OptiX)
B · 9A · 22050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 137.4% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
22.1 s · community measurement, sample 39 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 39 submissions (1 outliers excluded), interquartile range 20.82–22.62; submissions 2021-07-18 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
9.3 s · community measurement, sample 244 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 244 submissions (56 outliers excluded), interquartile range 9.17–9.43; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 72.8%
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce RTX 2080 Ti137.4 sGeForce RTX 309079.5 sPosition among tested models (26, CUDA)
B · 80A · 1370200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 72.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
137.4 s · community measurement, sample 45 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 45 submissions (5 outliers excluded), interquartile range 133.31–141.35; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
79.5 s · community measurement, sample 260 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 260 submissions (43 outliers excluded), interquartile range 78.58–81; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 157.5%
Blender Benchmark 2.93.1
GPU, classroom (OPTIX) · s, lower is better
GeForce RTX 2080 Ti86.2 sGeForce RTX 309033.5 sPosition among tested models (14, OptiX)
B · 33A · 86050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 157.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
86.2 s · community measurement, sample 31 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 31 submissions (3 outliers excluded), interquartile range 83.91–91.02; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
33.5 s · community measurement, sample 182 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 182 submissions (15 outliers excluded), interquartile range 32.84–34.67; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 87.7%
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce RTX 2080 Ti64.6 sGeForce RTX 309034.4 sPosition among tested models (21, CUDA)
B · 34A · 650100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 87.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
64.6 s · community measurement, sample 37 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 37 submissions (7 outliers excluded), interquartile range 63.21–66.02; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
34.4 s · community measurement, sample 213 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 213 submissions (51 outliers excluded), interquartile range 34.13–34.9; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 86.7%
Blender Benchmark 2.93.1
GPU, fishy_cat (OPTIX) · s, lower is better
GeForce RTX 2080 Ti33.5 sGeForce RTX 309017.9 sPosition among tested models (13, OptiX)
B · 18A · 33020406080Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 86.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
33.5 s · community measurement, sample 29 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 29 submissions (2 outliers excluded), interquartile range 32.62–35.12; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
17.9 s · community measurement, sample 141 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 141 submissions (40 outliers excluded), interquartile range 17.77–18.14; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 87.8%
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce RTX 2080 Ti102.5 sGeForce RTX 309054.6 sPosition among tested models (20, CUDA)
B · 55A · 1020200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 87.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
102.5 s · community measurement, sample 36 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 36 submissions (6 outliers excluded), interquartile range 100.68–104.8; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
54.6 s · community measurement, sample 216 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 216 submissions (47 outliers excluded), interquartile range 54.03–55.35; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 67.2%
Blender Benchmark 2.93.1
GPU, koro (OPTIX) · s, lower is better
GeForce RTX 2080 Ti63.5 sGeForce RTX 309037.9 sPosition among tested models (13, OptiX)
B · 38A · 63050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 67.2% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
63.5 s · community measurement, sample 24 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 24 submissions (6 outliers excluded), interquartile range 62.26–67.16; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
37.9 s · community measurement, sample 143 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 143 submissions (36 outliers excluded), interquartile range 37.49–38.45; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 109.5%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce RTX 2080 Ti208.1 sGeForce RTX 309099.3 sPosition among tested models (21, CUDA)
B · 99A · 2080200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 109.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
208.1 s · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (4 outliers excluded), interquartile range 200.44–213.46; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
99.3 s · community measurement, sample 215 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 215 submissions (50 outliers excluded), interquartile range 98.46–100.87; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 133%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (OPTIX) · s, lower is better
GeForce RTX 2080 Ti105.1 sGeForce RTX 309045.1 sPosition among tested models (13, OptiX)
B · 45A · 1050100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 133% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
105.1 s · community measurement, sample 38 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 38 submissions (2 outliers excluded), interquartile range 102.5–110.4; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
45.1 s · community measurement, sample 145 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 145 submissions (26 outliers excluded), interquartile range 44.57–45.81; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 103.3%
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce RTX 2080 Ti282 sGeForce RTX 3090138.7 sPosition among tested models (19, CUDA)
B · 139A · 28202505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 103.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
282 s · community measurement, sample 34 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 34 submissions (7 outliers excluded), interquartile range 274.18–287.61; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
138.7 s · community measurement, sample 217 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 217 submissions (43 outliers excluded), interquartile range 137.5–140.78; submissions 2021-07-09 to 2022-03-01; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 128.2%
Blender Benchmark 2.93.1
GPU, victor (OPTIX) · s, lower is better
GeForce RTX 2080 Ti137.9 sGeForce RTX 309060.4 sPosition among tested models (13, OptiX)
B · 60A · 1380100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 128.2% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
137.9 s · community measurement, sample 28 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 28 submissions (2 outliers excluded), interquartile range 132.73–144.53; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
60.4 s · community measurement, sample 144 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 144 submissions (24 outliers excluded), interquartile range 59.46–61.01; submissions 2021-07-10 to 2022-02-28; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 90.6%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 2080 Ti2,845.2 samples/minGeForce RTX 30905,423.6 samples/minPosition among tested models (67, OptiX)
A · 2,845B · 5,42405,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce RTX 3090 is ahead by 90.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
2,845.2 samples/min · community measurement, sample 131 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 131 submissions (5 outliers excluded), interquartile range 2732.17–2950.36; submissions 2025-07-18 to 2026-03-23; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
5,423.6 samples/min · community measurement, sample 596 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 596 submissions (34 outliers excluded), interquartile range 5240.15–5558.47; submissions 2025-07-17 to 2026-10-19; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Cycles render in Blender Benchmark. Median of the sum of samples per minute over three scenes after removing outliers.
Other comparable benchmarks (43)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 40.1 | 21.5 | B +86.4% |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 38.8 | 18.5 | B +109.6% |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 39.1 | 18.5 | B +111.6% |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 19 | 8.9 | B +112.4% |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 19.8 | 9.1 | B +117.7% |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 151.7 | 70.6 | B +114.8% |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 154.7 | 58.8 | B +163.1% |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 159.2 | 55.5 | B +186.7% |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | 82.1 | 35.2 | B +133.2% |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 84.2 | 34.4 | B +144.8% |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 72.9 | 39 | B +86.8% |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 67.6 | 33.9 | B +99.2% |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 70.9 | 34.8 | B +104% |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 30.2 | 16.5 | B +82.8% |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 33.1 | 18.4 | B +80.6% |
| Blender Benchmark 2.90GPU, koro (CUDA) | 116.5 | 58 | B +101% |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 108.6 | 57.5 | B +88.9% |
| Blender Benchmark 2.92GPU, koro (CUDA) | 111.1 | 58 | B +91.4% |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 59.4 | 36.5 | B +62.9% |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 98.4 | 57.1 | B +72.1% |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 242.3 | 119.6 | B +102.6% |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 223.3 | 108.5 | B +105.7% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 225.1 | 109.3 | B +106.1% |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 98 | 45.4 | B +116% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 100.2 | 45.1 | B +122.5% |
| Blender Benchmark 2.90GPU, victor (CUDA) | 277.9 | 159.1 | B +74.7% |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 270.2 | 124.3 | B +117.5% |
| Blender Benchmark 2.92GPU, victor (CUDA) | 330 | 178.3 | B +85.1% |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 116.6 | 52.8 | B +121.1% |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 137.1 | 62.5 | B +119.1% |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,799.5 | 5,354.8 | B +91.3% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,835.9 | 5,253.3 | B +85.2% |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,373.2 | 5,841.8 | B +73.2% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,084.5 | 6,560.4 | B +112.7% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,235.5 | 5,625.7 | B +73.9% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,223 | 6,018.2 | B +86.7% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,218.9 | 6,014.6 | B +86.9% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,362.6 | 6,296.9 | B +87.3% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,343.5 | 6,305.5 | B +88.6% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,872.1 | 5,536.1 | B +92.8% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,903.2 | 5,536.4 | B +90.7% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,818.4 | 5,347.6 | B +89.7% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,792.6 | 5,333 | B +91% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (89)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81GPU, barbershop_interior (CUDA) | 521.2 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 514 | — | no pair |
| Blender Benchmark 2.81GPU, barbershop_interior (OPTIX) | 860.1 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (OPTIX) | 866.3 | — | no pair |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 37.5 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 37.4 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 37.7 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 38.2 | — | no pair |
| Blender Benchmark 2.81GPU, bmw27 (OPTIX) | 19.5 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (OPTIX) | 20.4 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (OPTIX) | 20.3 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (OPTIX) | 19.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 19.3 | 9.2 | reference |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 153.5 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 153.6 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 147.3 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 151.1 | — | no pair |
| Blender Benchmark 2.81GPU, classroom (OPTIX) | 81.1 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (OPTIX) | 82.6 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (OPTIX) | 81.4 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (OPTIX) | 82.5 | — | no pair |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 84.5 | 37.1 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 66.4 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 67.1 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 68.4 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 71 | — | no pair |
| Blender Benchmark 2.81GPU, fishy_cat (OPTIX) | 30.4 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (OPTIX) | 31.2 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (OPTIX) | 31.9 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (OPTIX) | 31.4 | — | no pair |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 30.5 | 16.7 | reference |
| Blender Benchmark 2.81GPU, koro (CUDA) | 112.9 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 114.5 | — | no pair |
| Blender Benchmark 2.82GPU, koro (CUDA) | 113.4 | — | no pair |
| Blender Benchmark 2.83GPU, koro (CUDA) | 120.2 | — | no pair |
| Blender Benchmark 2.81GPU, koro (OPTIX) | 56.1 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (OPTIX) | 55.4 | — | no pair |
| Blender Benchmark 2.82GPU, koro (OPTIX) | 53.5 | — | no pair |
| Blender Benchmark 2.83GPU, koro (OPTIX) | 53.1 | — | no pair |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 59.2 | 36.3 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 234.9 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 236.4 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 234.3 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 236 | — | no pair |
| Blender Benchmark 2.81GPU, pavillon_barcelona (OPTIX) | 99.5 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (OPTIX) | 101.3 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (OPTIX) | 101.6 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (OPTIX) | 99.5 | — | no pair |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 99.5 | 46.9 | reference |
| Blender Benchmark 2.81GPU, victor (CUDA) | 288.3 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 290 | — | no pair |
| Blender Benchmark 2.82GPU, victor (CUDA) | 282.3 | — | no pair |
| Blender Benchmark 2.83GPU, victor (CUDA) | 290.2 | — | no pair |
| Blender Benchmark 2.81GPU, victor (OPTIX) | 131.2 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (OPTIX) | 132.5 | — | no pair |
| Blender Benchmark 2.82GPU, victor (OPTIX) | 129.3 | — | no pair |
| Blender Benchmark 2.83GPU, victor (OPTIX) | 128.9 | — | no pair |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 118.1 | 53.9 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,112.4 | 3,418.3 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,233.4 | 3,729.7 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,339.9 | 3,797.9 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,461.2 | 3,864 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,495.4 | 4,060.8 | reference |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,225.7 | 3,735.6 | reference |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,330 | 3,798 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,754.3 | 5,093.8 | reference |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,011.2 | 5,826.5 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,108.3 | 6,566.2 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,627.7 | 4,875.8 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,749.3 | 5,266.1 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (CUDA) | — | 20.5 | no pair |
| Blender Benchmark 2.90.1GPU, bmw27 (OPTIX) | — | 8.9 | no pair |
| Blender Benchmark 2.90.1GPU, classroom (CUDA) | — | 67.4 | no pair |
| Blender Benchmark 2.90.1GPU, classroom (OPTIX) | — | 38.9 | no pair |
| Blender Benchmark 2.90.1GPU, fishy_cat (CUDA) | — | 37.3 | no pair |
| Blender Benchmark 2.90.1GPU, fishy_cat (OPTIX) | — | 16.8 | no pair |
| Blender Benchmark 2.90.1GPU, koro (CUDA) | — | 57.5 | no pair |
| Blender Benchmark 2.90.1GPU, koro (OPTIX) | — | 37.1 | no pair |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (CUDA) | — | 108.8 | no pair |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (OPTIX) | — | 46.6 | no pair |
| Blender Benchmark 2.90.1GPU, victor (CUDA) | — | 148.7 | no pair |
| Blender Benchmark 2.90.1GPU, victor (OPTIX) | — | 57.7 | no pair |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,696.5 | no pair |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,138.2 | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,448.2 | no pair |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,724.8 | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,699.3 | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,730.8 | no pair |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 5,143.8 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 2080 Ti | B · GeForce RTX 3090 | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | TU102-300A-K1-A1 | no data | no data for B |
| Architecture | Turing | Ampere | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 4,352 (CUDA cores) | 10,496 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,350 MHz | 1,400 MHz | B: 50 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,545 MHz | 1,700 MHz | B: 155 MHz more |
| Memory | |||
| Video memory | 11 GB | 24 GB | B: 13 GB more |
| Memory type | GDDR6 | GDDR6X | differs |
| Memory bus | 352 bit | 384 bit | B: 32 bit more |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 616 GB/s | no data | no data for B |
| Power and dimensions | |||
| Board powerTGP (NVIDIA) and TBP (AMD/Intel) are calculated differently; higher is not better. For laptops, the chip maker sets the range and the laptop maker picks the value, so the same chip behaves differently in different laptops. | 250 W (TDP) | 350 W (board power) | not directly comparable |
| Recommended PSU | no data | 750 W | no data for A |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | no data | 313 mm | no data for A |
| Thickness (slots) | no data | 3 | no data for A |
| Power connectors (reference) | no data | 2x 8-pin (adapter to 1x 12-pin included) — FE | no data for A |
Chip
GPU chip
ATU102-300A-K1-A1
Bno data
no data for BArchitecture
ATuring
BAmpere
differsShader units
A4,352 (CUDA cores)
B10,496 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,350 MHz
B1,400 MHz
B: 50 MHz moreBoost clock
A1,545 MHz
B1,700 MHz
B: 155 MHz moreClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit.
Memory
Video memory
A11 GB
B24 GB
B: 13 GB moreMemory type
AGDDR6
BGDDR6X
differsMemory bus
A352 bit
B384 bit
B: 32 bit moreMemory bandwidth
A616 GB/s
Bno data
no data for BExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A250 W (TDP)
B350 W (board power)
not directly comparableTGP (NVIDIA) and TBP (AMD/Intel) are calculated differently; higher is not better. For laptops, the chip maker sets the range and the laptop maker picks the value, so the same chip behaves differently in different laptops.
Recommended PSU
Ano data
B750 W
no data for ALength (reference / Founders Edition)
Ano data
B313 mm
no data for APartner cards have different dimensions; check the specific SKU.
Thickness (slots)
Ano data
B3
no data for APower connectors (reference)
Ano data
B2x 8-pin (adapter to 1x 12-pin included) — FE
no data for A
“More” does not always mean “better”: higher power draw or size is a system requirement, not an advantage (such bars are dimmed).
Compare with AI
An AI model reviews the specs and benchmarks of this pair and gives a plain-language verdict on who each model suits.
Questions and answers
How much video memory do NVIDIA GeForce RTX 2080 Ti and NVIDIA GeForce RTX 3090 have?
NVIDIA GeForce RTX 2080 Ti: 11 GB GDDR6, 352-bit bus. NVIDIA GeForce RTX 3090: 24 GB GDDR6X, 384-bit bus.
Which is faster: NVIDIA GeForce RTX 2080 Ti or NVIDIA GeForce RTX 3090?
NVIDIA GeForce RTX 3090 leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.
See also
Data sources (3)
- Wikipedia (English) — specifications of NVIDIA GeForce RTX 2080 Ti, release date and launch pricechecked November 14, 2026
- NVIDIA — specifications of NVIDIA GeForce RTX 3090checked November 7, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 2.81, benchmark Blender Benchmark 2.81a, benchmark Blender Benchmark 2.90, benchmark Blender Benchmark 2.90.1, benchmark Blender Benchmark 2.91.2, benchmark Blender Benchmark 2.92, benchmark Blender Benchmark 2.93.1, benchmark Blender Benchmark 2.82, benchmark Blender Benchmark 2.83, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.1.2, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 5.3.0checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.