GeForce RTX 2060 SUPER vs GeForce RTX 2070: specs and benchmark comparison
Short verdict
NVIDIA GeForce RTX 2060 SUPER 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
A +6.1%NVIDIA GeForce RTX 2060 SUPER leads in this scenario (up to 6.1% 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 2060 SUPER is better1
Launch price $100 lower$399 vs $499
Where GeForce RTX 2070 is better1
Shader units 128 more2,304 (CUDA cores) vs 2,176 (CUDA cores)
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- 3.2% difference, within the threshold
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce RTX 2060 SUPER57 sGeForce RTX 207058.8 sPosition among tested models (31, CUDA)
A · 57B · 590100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 3.2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
57 s · community measurement, sample 32 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 32 submissions (4 outliers excluded), interquartile range 56.4–57.77; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
58.8 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (1 outliers excluded), interquartile range 57.49–61.43; submissions 2021-07-12 to 2022-02-10; 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.
- 3.3% difference, within the threshold
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER31.9 sGeForce RTX 207033 sPosition among tested models (20, OptiX)
A · 32B · 33050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 3.3% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
31.9 s · community measurement, sample 21 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 21 submissions (0 outliers excluded), interquartile range 31.4–33.3; submissions 2021-07-27 to 2022-02-23; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
33 s · community measurement, sample 20 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 20 submissions (5 outliers excluded), interquartile range 32.03–33.24; submissions 2021-07-22 to 2022-02-27; 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.
- 2% difference, within the threshold
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce RTX 2060 SUPER276.9 sGeForce RTX 2070282.3 sPosition among tested models (26, CUDA)
A · 277B · 2820200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
276.9 s · community measurement, sample 31 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 31 submissions (4 outliers excluded), interquartile range 272.42–281.42; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
282.3 s · community measurement, sample 28 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 28 submissions (2 outliers excluded), interquartile range 276.74–290.98; submissions 2021-07-12 to 2022-02-03; 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.
- 2.8% difference, within the threshold
Blender Benchmark 2.90
GPU, classroom (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER161.8 sGeForce RTX 2070166.4 sPosition among tested models (15, OptiX)
A · 162B · 1660100200300400Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 2.8% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
161.8 s · community measurement, sample 37 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 37 submissions (9 outliers excluded), interquartile range 160.24–163.89; submissions 2020-09-02 to 2021-01-25; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
166.4 s · community measurement, sample 61 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 61 submissions (1 outliers excluded), interquartile range 160.19–171.32; submissions 2020-09-02 to 2022-01-09; 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.
- 1.9% difference, within the threshold
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce RTX 2060 SUPER109.5 sGeForce RTX 2070111.6 sPosition among tested models (21, CUDA)
A · 110B · 1120100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 1.9% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
109.5 s · community measurement, sample 26 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 26 submissions (4 outliers excluded), interquartile range 107.85–111.2; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
111.6 s · community measurement, sample 27 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 27 submissions (2 outliers excluded), interquartile range 108.46–119.84; submissions 2021-07-12 to 2022-02-03; 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.
- 1.7% difference, within the threshold
Blender Benchmark 2.90
GPU, fishy_cat (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER55.7 sGeForce RTX 207054.8 sPosition among tested models (13, OptiX)
B · 55A · 560100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 1.7% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
55.7 s · community measurement, sample 30 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 30 submissions (6 outliers excluded), interquartile range 55.02–56.53; submissions 2020-09-02 to 2021-01-12; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
54.8 s · community measurement, sample 43 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 43 submissions (9 outliers excluded), interquartile range 54.03–56.24; submissions 2020-09-03 to 2021-06-14; 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.
- 1.3% difference, within the threshold
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce RTX 2060 SUPER180.7 sGeForce RTX 2070183.1 sPosition among tested models (20, CUDA)
A · 181B · 1830200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 1.3% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
180.7 s · community measurement, sample 27 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 27 submissions (2 outliers excluded), interquartile range 178.65–186.28; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
183.1 s · community measurement, sample 27 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 27 submissions (2 outliers excluded), interquartile range 178.97–197.3; submissions 2021-07-12 to 2022-02-03; 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.
- 2.4% difference, within the threshold
Blender Benchmark 2.90
GPU, koro (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER118 sGeForce RTX 2070115.2 sPosition among tested models (13, OptiX)
B · 115A · 1180100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 2.4% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
118 s · community measurement, sample 30 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 30 submissions (6 outliers excluded), interquartile range 116.65–119.66; submissions 2020-09-02 to 2021-01-12; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
115.2 s · community measurement, sample 45 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 45 submissions (6 outliers excluded), interquartile range 111.3–119.47; submissions 2020-09-03 to 2021-06-14; 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.
- 4.1% difference, within the threshold
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce RTX 2060 SUPER394 sGeForce RTX 2070410.2 sPosition among tested models (21, CUDA)
A · 394B · 4100200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 4.1% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
394 s · community measurement, sample 24 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 24 submissions (4 outliers excluded), interquartile range 388.05–403.3; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
410.2 s · community measurement, sample 25 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 25 submissions (5 outliers excluded), interquartile range 397.21–415.04; submissions 2021-07-12 to 2022-02-03; 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.
- 2% difference, within the threshold
Blender Benchmark 2.90
GPU, pavillon_barcelona (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER189.4 sGeForce RTX 2070193.2 sPosition among tested models (13, OptiX)
A · 189B · 1930200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
189.4 s · community measurement, sample 34 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 34 submissions (5 outliers excluded), interquartile range 186.85–192.12; submissions 2020-09-02 to 2021-01-25; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
193.2 s · community measurement, sample 45 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 45 submissions (8 outliers excluded), interquartile range 189.69–197.47; submissions 2020-09-03 to 2022-01-09; 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.
- 3% difference, within the threshold
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce RTX 2060 SUPER503.2 sGeForce RTX 2070518.5 sPosition among tested models (19, CUDA)
A · 503B · 51802505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 3% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
503.2 s · community measurement, sample 25 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 25 submissions (2 outliers excluded), interquartile range 497.18–522.26; submissions 2021-07-10 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
518.5 s · community measurement, sample 27 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 27 submissions (2 outliers excluded), interquartile range 503.35–553.61; submissions 2021-07-12 to 2022-02-03; 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.
- 0.2% difference, within the threshold
Blender Benchmark 2.90
GPU, victor (OPTIX) · s, lower is better
GeForce RTX 2060 SUPER230.1 sGeForce RTX 2070230.6 sPosition among tested models (13, OptiX)
A · 230B · 2310200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 0.2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
230.1 s · community measurement, sample 26 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 26 submissions (8 outliers excluded), interquartile range 228.62–231.78; submissions 2020-09-02 to 2021-01-12; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
230.6 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (6 outliers excluded), interquartile range 225.65–237.11; submissions 2020-09-03 to 2021-06-14; 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.
- 2% difference, within the threshold
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 2060 SUPER2,067.3 samples/minGeForce RTX 20702,108.7 samples/minPosition among tested models (67, OptiX)
A · 2,067B · 2,10905,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. The 2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2060 SUPER
2,067.3 samples/min · community measurement, sample 102 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 102 submissions (7 outliers excluded), interquartile range 2005.87–2124.27; submissions 2025-07-17 to 2026-03-07; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 2070
2,108.7 samples/min · community measurement, sample 64 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 64 submissions (2 outliers excluded), interquartile range 1999.79–2175.31; submissions 2025-07-22 to 2026-07-07; 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 (42)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 63.6 | 64.2 | A +0.9% |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 65.7 | 67.6 | A +2.9% |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 66.3 | 67.8 | A +2.3% |
| Blender Benchmark 2.82GPU, bmw27 (OPTIX) | 30.6 | 30.8 | A +0.7% |
| Blender Benchmark 2.83GPU, bmw27 (OPTIX) | 29.6 | 30.6 | A +3.2% |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 30.6 | 30.5 | B +0.5% |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 292.8 | 297.9 | A +1.8% |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 299.2 | 306.1 | A +2.3% |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 300.7 | 310.5 | A +3.2% |
| Blender Benchmark 2.82GPU, classroom (OPTIX) | 159.9 | 165 | A +3.2% |
| Blender Benchmark 2.83GPU, classroom (OPTIX) | 158.6 | 168.2 | A +6.1% |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 119.7 | 119.9 | A +0.2% |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 126 | 129.7 | A +3% |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 123.7 | 126.2 | A +2% |
| Blender Benchmark 2.82GPU, fishy_cat (OPTIX) | 58.1 | 58.2 | A +0.2% |
| Blender Benchmark 2.83GPU, fishy_cat (OPTIX) | 56.5 | 59.1 | A +4.5% |
| Blender Benchmark 2.82GPU, koro (CUDA) | 210.8 | 211.6 | A +0.4% |
| Blender Benchmark 2.83GPU, koro (CUDA) | 220.1 | 226.1 | A +2.7% |
| Blender Benchmark 2.90GPU, koro (CUDA) | 191.3 | 195 | A +1.9% |
| Blender Benchmark 2.82GPU, koro (OPTIX) | 106 | 103.5 | B +2.4% |
| Blender Benchmark 2.83GPU, koro (OPTIX) | 101.9 | 105.7 | A +3.7% |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 450.2 | 456.1 | A +1.3% |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 449.2 | 461.6 | A +2.8% |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 461.2 | 472.6 | A +2.5% |
| Blender Benchmark 2.82GPU, pavillon_barcelona (OPTIX) | 190.3 | 196.2 | A +3.1% |
| Blender Benchmark 2.83GPU, pavillon_barcelona (OPTIX) | 183.7 | 194.8 | A +6% |
| Blender Benchmark 2.82GPU, victor (CUDA) | 522.2 | 532.1 | A +1.9% |
| Blender Benchmark 2.83GPU, victor (CUDA) | 538.5 | 560.2 | A +4% |
| Blender Benchmark 2.90GPU, victor (CUDA) | 510.2 | 532.1 | A +4.3% |
| Blender Benchmark 2.82GPU, victor (OPTIX) | 250.5 | 258.5 | A +3.2% |
| Blender Benchmark 2.83GPU, victor (OPTIX) | 245.2 | 260.1 | A +6.1% |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,099.4 | 2,072.7 | A +1.3% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,307.1 | 2,282.5 | A +1.1% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,180.5 | 2,245.7 | B +3% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,288.4 | 2,322.6 | B +1.5% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,315.7 | 2,275.9 | A +1.7% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,378.7 | 2,452.8 | B +3.1% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,450.3 | 2,450.5 | B +0% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,138.1 | 2,159.9 | B +1% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,158.4 | 2,222.6 | B +3% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,049 | 2,085.9 | B +1.8% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,113.6 | 2,131.7 | B +0.9% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (86)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81GPU, barbershop_interior (CUDA) | 1,076.9 | 1,086.1 | reference |
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 1,070.2 | 1,072.6 | reference |
| Blender Benchmark 2.81GPU, barbershop_interior (OPTIX) | 1,716.3 | 1,907.1 | reference |
| Blender Benchmark 2.81aGPU, barbershop_interior (OPTIX) | 1,792.2 | 1,721.5 | reference |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 63.1 | 64 | reference |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 61.9 | 64.9 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (CUDA) | 71.5 | 70.1 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 66 | 69.8 | reference |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 69.1 | 67.8 | reference |
| Blender Benchmark 2.81GPU, bmw27 (OPTIX) | 26.5 | 30.9 | reference |
| Blender Benchmark 2.81aGPU, bmw27 (OPTIX) | 30.2 | 30.5 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (OPTIX) | 31.6 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 30.7 | 31.6 | reference |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 31.4 | 30 | reference |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 298.5 | 309.9 | reference |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 299.4 | 312.4 | reference |
| Blender Benchmark 2.90.1GPU, classroom (CUDA) | 350.2 | 340.3 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 305.3 | 321.4 | reference |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 320.8 | 318.4 | reference |
| Blender Benchmark 2.81GPU, classroom (OPTIX) | 167.9 | 159.4 | reference |
| Blender Benchmark 2.81aGPU, classroom (OPTIX) | 161.7 | 164.5 | reference |
| Blender Benchmark 2.90.1GPU, classroom (OPTIX) | 169.6 | — | no pair |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 166.7 | 170.4 | reference |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 171.4 | 168.1 | reference |
| Blender Benchmark 2.93.1GPU, classroom (OPTIX) | 170.5 | 177.3 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 115.3 | 118.1 | reference |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 115.4 | 119.3 | reference |
| Blender Benchmark 2.90.1GPU, fishy_cat (CUDA) | 143.6 | 131.1 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 113 | 122.6 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 120.2 | 117.9 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (OPTIX) | 57.1 | 55.1 | reference |
| Blender Benchmark 2.81aGPU, fishy_cat (OPTIX) | 56 | 56.3 | reference |
| Blender Benchmark 2.90.1GPU, fishy_cat (OPTIX) | 57.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 55.8 | 61.8 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 63.3 | 62.1 | reference |
| Blender Benchmark 2.93.1GPU, fishy_cat (OPTIX) | 60.8 | 63.4 | reference |
| Blender Benchmark 2.81GPU, koro (CUDA) | 207.7 | 209.7 | reference |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 209.1 | 212.8 | reference |
| Blender Benchmark 2.90.1GPU, koro (CUDA) | 222.1 | 213.3 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 179.3 | 196.1 | reference |
| Blender Benchmark 2.92GPU, koro (CUDA) | 188.6 | 186.9 | reference |
| Blender Benchmark 2.81GPU, koro (OPTIX) | 103.4 | 102.4 | reference |
| Blender Benchmark 2.81aGPU, koro (OPTIX) | 110.8 | 105.6 | reference |
| Blender Benchmark 2.90.1GPU, koro (OPTIX) | 123.1 | — | no pair |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 119.8 | 123 | reference |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 206.2 | 133.3 | reference |
| Blender Benchmark 2.93.1GPU, koro (OPTIX) | 124.3 | 126.5 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 439.5 | 458.6 | reference |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 446.9 | 457.8 | reference |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (CUDA) | 543.8 | 505.9 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 417 | 445.3 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 430.7 | 429.3 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (OPTIX) | 192.4 | 192.5 | reference |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (OPTIX) | 189.9 | 194.8 | reference |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (OPTIX) | 193.6 | — | no pair |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 193.2 | 196.3 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 195.3 | 197.3 | reference |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (OPTIX) | 196.7 | 205.1 | reference |
| Blender Benchmark 2.81GPU, victor (CUDA) | 520.3 | 545.7 | reference |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 528.8 | 548.4 | reference |
| Blender Benchmark 2.90.1GPU, victor (CUDA) | 604.2 | 528.8 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 481.9 | 554.3 | reference |
| Blender Benchmark 2.92GPU, victor (CUDA) | 566.8 | 574.2 | reference |
| Blender Benchmark 2.81GPU, victor (OPTIX) | 260.1 | 255.7 | reference |
| Blender Benchmark 2.81aGPU, victor (OPTIX) | 260.2 | 261.9 | reference |
| Blender Benchmark 2.90.1GPU, victor (OPTIX) | 244 | — | no pair |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 232.2 | 252.2 | reference |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 276.1 | 268.9 | reference |
| Blender Benchmark 2.93.1GPU, victor (OPTIX) | 264.5 | 273.2 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,408 | 1,404.9 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,445.8 | — | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,328.5 | — | no pair |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,442.8 | 1,467.2 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,380.9 | 1,433.1 | reference |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 1,993.1 | 1,829.9 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 1,928.2 | 1,926.6 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,487.8 | 2,300.4 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,259.4 | 2,266 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 1,879.9 | 1,896.1 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 1,883.9 | 2,031.8 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,401.3 | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,347.9 | no pair |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,375.7 | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,406.2 | no pair |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,246.1 | no pair |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 2,178.6 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 2060 SUPER | B · GeForce RTX 2070 | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | TU106-410-A1 | TU106-400A-A1 | differs |
| Architecture | Turing | Turing | equal |
| Shader unitsShader unit counts are comparable only within one architecture. | 2,176 (CUDA cores) | 2,304 (CUDA cores) | B: 128 more |
| Clocks | |||
| Base clock | 1,470 MHz | 1,410 MHz | A: 60 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,650 MHz | 1,620 MHz | A: 30 MHz more |
| Memory | |||
| Video memory | 8 GB | 8 GB | equal |
| Memory type | GDDR6 | GDDR6 | equal |
| Memory bus | 256 bit | 256 bit | equal |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 448 GB/s | 448 GB/s | equal |
| 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. | 175 W (TDP) | 175 W (TDP) | equal |
Chip
GPU chip
ATU106-410-A1
BTU106-400A-A1
differsArchitecture
ATuring
BTuring
equalShader units
A2,176 (CUDA cores)
B2,304 (CUDA cores)
B: 128 moreShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,470 MHz
B1,410 MHz
A: 60 MHz moreBoost clock
A1,650 MHz
B1,620 MHz
A: 30 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
A8 GB
B8 GB
equalMemory type
AGDDR6
BGDDR6
equalMemory bus
A256 bit
B256 bit
equalMemory bandwidth
A448 GB/s
B448 GB/s
equalExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A175 W (TDP)
B175 W (TDP)
equalTGP (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.
“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 2060 SUPER and NVIDIA GeForce RTX 2070 have?
NVIDIA GeForce RTX 2060 SUPER: 8 GB GDDR6, 256-bit bus. NVIDIA GeForce RTX 2070: 8 GB GDDR6, 256-bit bus.
Which is faster: NVIDIA GeForce RTX 2060 SUPER or NVIDIA GeForce RTX 2070?
NVIDIA GeForce RTX 2060 SUPER leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.
See also
Data sources (2)
- Wikipedia (English) — specifications of NVIDIA GeForce RTX 2060 SUPER, specifications of NVIDIA GeForce RTX 2070, release date and launch pricechecked November 14, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 2.81, benchmark Blender Benchmark 2.81a, benchmark Blender Benchmark 2.82, benchmark Blender Benchmark 2.83, 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 3.1.0, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 3.1.2checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.