GeForce RTX 2070 SUPER vs GeForce RTX 3070 Laptop GPU: specs and benchmark comparison
Short verdict
NVIDIA GeForce RTX 3070 Laptop GPU 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 +77.9%NVIDIA GeForce RTX 3070 Laptop GPU leads in this scenario (up to 77.9% 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 2070 SUPER is better0
No advantages found in our data.
Where GeForce RTX 3070 Laptop GPU is better13
Blender Benchmark 2.93.1 57.3% lower29 s vs 45 s
Blender Benchmark 2.93.1 68.9% lower17 s vs 29 s
Blender Benchmark 2.93.1 16% lower134 s vs 156 s
Blender Benchmark 2.93.1 69.8% lower62 s vs 105 s
Blender Benchmark 2.93.1 42% lower64 s vs 90 s
Blender Benchmark 2.93.1 32.9% lower38 s vs 51 s
Blender Benchmark 2.93.1 40% lower106 s vs 148 s
Blender Benchmark 2.93.1 27.1% lower82 s vs 104 s
Blender Benchmark 2.93.1 43.8% lower178 s vs 257 s
Blender Benchmark 2.93.1 64.2% lower82 s vs 135 s
Blender Benchmark 2.93.1 47.1% lower262 s vs 385 s
Blender Benchmark 2.93.1 51.3% lower122 s vs 184 s
Blender Benchmark 4.5.0 23.5% faster2,761 samples/min vs 2,235 samples/min
Benchmarks
Results are compared within one benchmark, one version and the same conditions. Laptop chip results depend on the laptop model: its maker sets the power limit and cooling.
- B ahead by 57.3%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce RTX 2070 SUPER45.2 sGeForce RTX 3070 Laptop GPU28.7 sPosition among tested models (31, CUDA)
B · 29A · 450100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 57.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
45.2 s · community measurement, sample 98 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 98 submissions (11 outliers excluded), interquartile range 44.61–45.89; submissions 2021-07-09 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
28.7 s · community measurement, sample 116 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 116 submissions (3 outliers excluded), interquartile range 27.25–32.03; submissions 2021-07-12 to 2022-02-27; 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 68.9%
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER29.2 sGeForce RTX 3070 Laptop GPU17.3 sPosition among tested models (20, OptiX)
B · 17A · 29050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 68.9% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
29.2 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (4 outliers excluded), interquartile range 28.79–29.82; submissions 2021-07-09 to 2022-02-11; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
17.3 s · community measurement, sample 101 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 101 submissions (5 outliers excluded), interquartile range 16.84–19.15; submissions 2021-07-09 to 2022-02-25; 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 16%
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce RTX 2070 SUPER155.8 sGeForce RTX 3070 Laptop GPU134.3 sPosition among tested models (26, CUDA)
B · 134A · 1560200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 16% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
155.8 s · community measurement, sample 80 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 80 submissions (6 outliers excluded), interquartile range 153.23–158.95; submissions 2021-07-12 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
134.3 s · community measurement, sample 91 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 91 submissions (4 outliers excluded), interquartile range 127.14–146.92; submissions 2021-07-12 to 2022-02-27; 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 69.8%
Blender Benchmark 2.93.1
GPU, classroom (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER104.5 sGeForce RTX 3070 Laptop GPU61.5 sPosition among tested models (14, OptiX)
B · 62A · 105050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 69.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
104.5 s · community measurement, sample 38 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 38 submissions (3 outliers excluded), interquartile range 102.59–107.68; submissions 2021-07-09 to 2022-02-10; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
61.5 s · community measurement, sample 87 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 87 submissions (3 outliers excluded), interquartile range 59.14–66.25; submissions 2021-07-09 to 2022-02-25; 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 42%
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce RTX 2070 SUPER90.4 sGeForce RTX 3070 Laptop GPU63.7 sPosition among tested models (21, CUDA)
B · 64A · 900100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 42% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
90.4 s · community measurement, sample 68 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 68 submissions (9 outliers excluded), interquartile range 88.69–91.7; submissions 2021-07-12 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
63.7 s · community measurement, sample 70 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 70 submissions (1 outliers excluded), interquartile range 61–70.98; submissions 2021-07-12 to 2022-02-27; 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 32.9%
Blender Benchmark 2.93.1
GPU, fishy_cat (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER50.8 sGeForce RTX 3070 Laptop GPU38.2 sPosition among tested models (13, OptiX)
B · 38A · 51020406080Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 32.9% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
50.8 s · community measurement, sample 29 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 29 submissions (4 outliers excluded), interquartile range 49.98–51.74; submissions 2021-07-16 to 2022-02-10; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
38.2 s · community measurement, sample 73 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 73 submissions (3 outliers excluded), interquartile range 36.93–40.92; submissions 2021-07-09 to 2022-02-25; 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 40%
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce RTX 2070 SUPER147.7 sGeForce RTX 3070 Laptop GPU105.5 sPosition among tested models (20, CUDA)
B · 106A · 1480200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 40% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
147.7 s · community measurement, sample 69 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 69 submissions (9 outliers excluded), interquartile range 145.41–149.78; submissions 2021-07-12 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
105.5 s · community measurement, sample 64 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 64 submissions (1 outliers excluded), interquartile range 100.91–115.04; submissions 2021-07-12 to 2022-02-27; 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 27.1%
Blender Benchmark 2.93.1
GPU, koro (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER104.1 sGeForce RTX 3070 Laptop GPU81.9 sPosition among tested models (13, OptiX)
B · 82A · 104050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 27.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
104.1 s · community measurement, sample 29 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 29 submissions (4 outliers excluded), interquartile range 103.53–106.27; submissions 2021-07-16 to 2022-02-20; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
81.9 s · community measurement, sample 66 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 66 submissions (11 outliers excluded), interquartile range 79.76–87.28; submissions 2021-07-09 to 2022-02-25; 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 43.8%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce RTX 2070 SUPER256.6 sGeForce RTX 3070 Laptop GPU178.5 sPosition among tested models (21, CUDA)
B · 178A · 2570200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 43.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
256.6 s · community measurement, sample 68 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 68 submissions (9 outliers excluded), interquartile range 254.13–262.18; submissions 2021-07-12 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
178.5 s · community measurement, sample 74 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 74 submissions (2 outliers excluded), interquartile range 169.45–196.61; submissions 2021-07-12 to 2022-02-27; 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 64.2%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER135.5 sGeForce RTX 3070 Laptop GPU82.5 sPosition among tested models (13, OptiX)
B · 82A · 1350100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 64.2% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
135.5 s · community measurement, sample 29 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 29 submissions (6 outliers excluded), interquartile range 134.34–137.84; submissions 2021-07-16 to 2022-02-10; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
82.5 s · community measurement, sample 78 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 78 submissions (6 outliers excluded), interquartile range 80.04–88.43; submissions 2021-07-09 to 2022-02-25; 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 47.1%
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce RTX 2070 SUPER384.8 sGeForce RTX 3070 Laptop GPU261.6 sPosition among tested models (19, CUDA)
B · 262A · 38502505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 47.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
384.8 s · community measurement, sample 71 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 71 submissions (9 outliers excluded), interquartile range 379–393.16; submissions 2021-07-12 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
261.6 s · community measurement, sample 66 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 66 submissions (1 outliers excluded), interquartile range 249.25–285.23; submissions 2021-07-12 to 2022-02-27; 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 51.3%
Blender Benchmark 2.93.1
GPU, victor (OPTIX) · s, lower is better
GeForce RTX 2070 SUPER183.9 sGeForce RTX 3070 Laptop GPU121.5 sPosition among tested models (13, OptiX)
B · 122A · 1840100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 51.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
183.9 s · community measurement, sample 30 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 30 submissions (3 outliers excluded), interquartile range 180.06–189.97; submissions 2021-07-16 to 2022-02-10; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
121.5 s · community measurement, sample 70 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 70 submissions (4 outliers excluded), interquartile range 117.1–128.44; submissions 2021-07-09 to 2022-02-25; 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 23.5%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 2070 SUPER2,234.5 samples/minGeForce RTX 3070 Laptop GPU2,760.6 samples/minPosition among tested models (67, OptiX)
A · 2,235B · 2,76105,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 23.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2070 SUPER
2,234.5 samples/min · community measurement, sample 101 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 101 submissions (7 outliers excluded), interquartile range 2150.53–2296.29; submissions 2025-07-18 to 2026-11-02; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
2,760.6 samples/min · community measurement, sample 118 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 118 submissions (5 outliers excluded), interquartile range 2251.76–2939.6; submissions 2025-07-17 to 2026-08-15; 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 (25)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 52.2 | 30.2 | B +72.5% |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 26.5 | 16.5 | B +61% |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 177.3 | 99.7 | B +77.9% |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 103 | 60.6 | B +69.9% |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 96.4 | 67.4 | B +43.1% |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 51.5 | 38.4 | B +34.4% |
| Blender Benchmark 2.92GPU, koro (CUDA) | 157.8 | 114.7 | B +37.6% |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 172.6 | 122.2 | B +41.3% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 285.3 | 204.6 | B +39.5% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 130.6 | 80.8 | B +61.7% |
| Blender Benchmark 2.92GPU, victor (CUDA) | 434.6 | 324.6 | B +33.9% |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 192 | 123.6 | B +55.3% |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,189.4 | 2,914.8 | B +33.1% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,143.1 | 2,804.4 | B +30.9% |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,079.7 | 2,551.9 | B +22.7% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,427.4 | 3,003.3 | B +23.7% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,447.3 | 2,946.5 | B +20.4% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,467.7 | 3,287.6 | B +33.2% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,394.9 | 3,248.3 | B +35.6% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,619 | 3,486.4 | B +33.1% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,604.6 | 3,241.2 | B +24.4% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,374.9 | 2,872.2 | B +20.9% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,262.8 | 3,005.4 | B +32.8% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,228.4 | 2,905.5 | B +30.4% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,225.8 | 2,692.5 | B +21% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (91)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81GPU, barbershop_interior (CUDA) | 574.1 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 559.4 | — | no pair |
| Blender Benchmark 2.81GPU, barbershop_interior (OPTIX) | 970.4 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (OPTIX) | 979.6 | — | no pair |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 49.3 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 49.1 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 49.9 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 50.5 | — | no pair |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 54.4 | 31.9 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 51.6 | 31.1 | reference |
| Blender Benchmark 2.81GPU, bmw27 (OPTIX) | 26.7 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (OPTIX) | 27.1 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (OPTIX) | 26.7 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (OPTIX) | 25.8 | — | no pair |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 25.8 | 15.6 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 26.2 | 17.8 | reference |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 168.4 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 169.4 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 165.2 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 168 | — | no pair |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 171.7 | 95.2 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 172.6 | 102.9 | reference |
| Blender Benchmark 2.81GPU, classroom (OPTIX) | 101.3 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (OPTIX) | 101.2 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (OPTIX) | 100.4 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (OPTIX) | 100 | — | no pair |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | 101 | 57.4 | reference |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 100.2 | 65.5 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 88 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 88.1 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 90.9 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 93.7 | — | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 99 | 62.4 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 91.3 | 61.3 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (OPTIX) | 43.3 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (OPTIX) | 43.7 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (OPTIX) | 44.6 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (OPTIX) | 43.7 | — | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 45.5 | 33.3 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 45.5 | 36.7 | reference |
| Blender Benchmark 2.81GPU, koro (CUDA) | 153.5 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 154 | — | no pair |
| Blender Benchmark 2.82GPU, koro (CUDA) | 153.3 | — | no pair |
| Blender Benchmark 2.83GPU, koro (CUDA) | 161.1 | — | no pair |
| Blender Benchmark 2.90GPU, koro (CUDA) | 165.1 | 100.6 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 154.6 | 105.4 | reference |
| Blender Benchmark 2.81GPU, koro (OPTIX) | 82 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (OPTIX) | 83.3 | — | no pair |
| Blender Benchmark 2.82GPU, koro (OPTIX) | 80.7 | — | no pair |
| Blender Benchmark 2.83GPU, koro (OPTIX) | 79.6 | — | no pair |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 98.8 | 74.8 | reference |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 98.4 | 82.6 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 287.5 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 288.2 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 290.1 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 290.6 | — | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 305.5 | 181.1 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 283.7 | 190.4 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (OPTIX) | 130.3 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (OPTIX) | 132.8 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (OPTIX) | 131.7 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (OPTIX) | 128.7 | — | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 128.8 | 76.5 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 129.8 | 86.9 | reference |
| Blender Benchmark 2.81GPU, victor (CUDA) | 382.7 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 383.5 | — | no pair |
| Blender Benchmark 2.82GPU, victor (CUDA) | 377.2 | — | no pair |
| Blender Benchmark 2.83GPU, victor (CUDA) | 383.5 | — | no pair |
| Blender Benchmark 2.90GPU, victor (CUDA) | 376.9 | 254.4 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 360.5 | 231.7 | reference |
| Blender Benchmark 2.81GPU, victor (OPTIX) | 167.1 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (OPTIX) | 166.4 | — | no pair |
| Blender Benchmark 2.82GPU, victor (OPTIX) | 161.2 | — | no pair |
| Blender Benchmark 2.83GPU, victor (OPTIX) | 160.2 | — | no pair |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 153.3 | 94.1 | reference |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 152 | 104.6 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,556.4 | 1,644.5 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,531.1 | 1,639.8 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,580.6 | 1,712.4 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,546.7 | 1,667.8 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,562.2 | — | no pair |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,569.9 | — | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 1,460.8 | — | no pair |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,522.5 | 3,023.2 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,413.7 | 3,213.5 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,072.4 | 2,685.1 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,123.5 | 2,370.4 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,338.4 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 2,168.1 | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,780.2 | no pair |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 2,976 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
Chip maker values. The laptop maker sets the power limit and clocks in each laptop.
| Specification | A · GeForce RTX 2070 SUPER | B · GeForce RTX 3070 Laptop GPU | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | TU104-410-A1 | no data | no data for B |
| Architecture | Turing | Ampere | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 2,560 (CUDA cores) | 5,120 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,605 MHz | no data | no data for B |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,770 MHz | 1,290–1,620 MHz | not directly comparable |
| 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 | 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. | 215 W (TDP) | no data | no data for B |
Chip
GPU chip
ATU104-410-A1
Bno data
no data for BArchitecture
ATuring
BAmpere
differsShader units
A2,560 (CUDA cores)
B5,120 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,605 MHz
Bno data
no data for BBoost clock
A1,770 MHz
B1,290–1,620 MHz
not directly comparableClocks 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
Bno data
no data for BExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A215 W (TDP)
Bno data
no data for BTGP (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 2070 SUPER and NVIDIA GeForce RTX 3070 Laptop GPU have?
NVIDIA GeForce RTX 2070 SUPER: 8 GB GDDR6, 256-bit bus. NVIDIA GeForce RTX 3070 Laptop GPU: 8 GB GDDR6, 256-bit bus.
Which is faster: NVIDIA GeForce RTX 2070 SUPER or NVIDIA GeForce RTX 3070 Laptop GPU?
NVIDIA GeForce RTX 3070 Laptop GPU 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 2070 SUPER, release date and launch pricechecked November 14, 2026
- NVIDIA — specifications of NVIDIA GeForce RTX 3070 Laptop GPUchecked November 7, 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 2.91.2, benchmark Blender Benchmark 2.92, benchmark Blender Benchmark 2.93.1, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.5.0, 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 5.3.0, benchmark Blender Benchmark 3.1.2checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.