GeForce RTX 2070 SUPER vs GeForce RTX 2080 SUPER: specs and benchmark comparison

ANVIDIA · Turing

NVIDIA GeForce RTX 2070 SUPER

8 GB GDDR6
215 W

July 9, 2019 · $499 at launch

BNVIDIA · Turing

NVIDIA GeForce RTX 2080 SUPER

8 GB GDDR6
250 W

July 23, 2019 · $699 at launch

Short verdict

NVIDIA GeForce RTX 2080 SUPER leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Compare with AI

← GeForce RTX 2070 SUPERGeForce RTX 2080 SUPER →

Rendering and compute
B +23.8%
NVIDIA GeForce RTX 2080 SUPER leads in this scenario (up to 23.8% 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 better2

Board power 35 W lower215 W (TDP) vs 250 W (TDP)
Launch price $200 lower$499 vs $699

Where GeForce RTX 2080 SUPER is better7

Blender Benchmark 2.90 12% lower90 s vs 101 s
Blender Benchmark 2.90 14.6% lower40 s vs 45 s
Blender Benchmark 2.92 23.8% lower139 s vs 173 s
Blender Benchmark 2.90 8.5% lower119 s vs 129 s
Blender Benchmark 2.90 15.4% lower133 s vs 153 s
Shader units 512 more3,072 (CUDA cores) vs 2,560 (CUDA cores)
Memory bandwidth 47.9 GB/s more495.9 GB/s vs 448 GB/s

Benchmarks

Results are compared within one benchmark, one version and the same conditions.

Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
2% difference, within the threshold
GeForce RTX 2070 SUPER45.2 s
GeForce RTX 2080 SUPER46.1 s
Position among tested models (31, CUDA)
A · 45B · 46
0100200300
Each 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 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 2080 SUPER
46.1 s · community measurement, sample 33 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 33 submissions (3 outliers excluded), interquartile range 45.46–47.66; submissions 2021-07-11 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.
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
1.3% difference, within the threshold
GeForce RTX 2070 SUPER29.2 s
GeForce RTX 2080 SUPER28.8 s
Position among tested models (20, OptiX)
B · 29A · 29
050100150
Each 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 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 2080 SUPER
28.8 s · community measurement, sample 22 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 22 submissions (0 outliers excluded), interquartile range 27.21–29.41; submissions 2021-07-19 to 2022-02-21; 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.
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
4.4% difference, within the threshold
GeForce RTX 2070 SUPER155.8 s
GeForce RTX 2080 SUPER149.3 s
Position among tested models (26, CUDA)
B · 149A · 156
0200400600800
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
The 4.4% difference is below the noticeable threshold (5%).
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 2080 SUPER
149.3 s · community measurement, sample 22 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 22 submissions (1 outliers excluded), interquartile range 148.22–154.89; submissions 2021-07-11 to 2022-02-21; 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.
Blender Benchmark 2.90
GPU, classroom (OPTIX) · s, lower is better
B ahead by 12%
GeForce RTX 2070 SUPER101 s
GeForce RTX 2080 SUPER90.2 s
Position among tested models (15, OptiX)
B · 90A · 101
0100200300400
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
NVIDIA GeForce RTX 2080 SUPER is ahead by 12% in this benchmark.
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
101 s · community measurement, sample 148 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 148 submissions (17 outliers excluded), interquartile range 99.16–102.19; submissions 2020-09-02 to 2021-01-30; OPTIX backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
90.2 s · community measurement, sample 81 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 81 submissions (10 outliers excluded), interquartile range 89.4–91.43; submissions 2020-09-02 to 2021-01-31; 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.
Blender Benchmark 2.90
GPU, fishy_cat (CUDA) · s, lower is better
0.8% difference, within the threshold
GeForce RTX 2070 SUPER99 s
GeForce RTX 2080 SUPER99.8 s
Position among tested models (22, CUDA)
A · 99B · 100
0200400600
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
The 0.8% difference is below the noticeable threshold (5%).
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
99 s · community measurement, sample 257 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 257 submissions (37 outliers excluded), interquartile range 97.7–100.66; submissions 2020-09-02 to 2021-05-18; CUDA backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
99.8 s · community measurement, sample 121 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 121 submissions (25 outliers excluded), interquartile range 97.95–101.06; submissions 2020-09-02 to 2021-02-01; 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.
Blender Benchmark 2.90
GPU, fishy_cat (OPTIX) · s, lower is better
B ahead by 14.6%
GeForce RTX 2070 SUPER45.5 s
GeForce RTX 2080 SUPER39.7 s
Position among tested models (13, OptiX)
B · 40A · 45
0100200300
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
NVIDIA GeForce RTX 2080 SUPER is ahead by 14.6% in this benchmark.
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
45.5 s · community measurement, sample 115 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 115 submissions (24 outliers excluded), interquartile range 44.86–45.95; submissions 2020-09-02 to 2021-01-30; OPTIX backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
39.7 s · community measurement, sample 61 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 61 submissions (11 outliers excluded), interquartile range 39.27–40.2; submissions 2020-09-02 to 2021-01-31; 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.
Blender Benchmark 2.90
GPU, koro (CUDA) · s, lower is better
1.1% difference, within the threshold
GeForce RTX 2070 SUPER165.1 s
GeForce RTX 2080 SUPER163.3 s
Position among tested models (22, CUDA)
B · 163A · 165
0200400600800
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
The 1.1% difference is below the noticeable threshold (5%).
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
165.1 s · community measurement, sample 244 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 244 submissions (30 outliers excluded), interquartile range 163.17–168.48; submissions 2020-09-02 to 2021-05-18; CUDA backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
163.3 s · community measurement, sample 112 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 112 submissions (21 outliers excluded), interquartile range 161.87–166.92; submissions 2020-09-02 to 2021-02-01; 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.
Blender Benchmark 2.92
GPU, koro (OPTIX) · s, lower is better
B ahead by 23.8%
GeForce RTX 2070 SUPER172.6 s
GeForce RTX 2080 SUPER139.5 s
Position among tested models (10, OptiX)
B · 139A · 173
0100200300
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
NVIDIA GeForce RTX 2080 SUPER is ahead by 23.8% in this benchmark.
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
172.6 s · community measurement, sample 28 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 28 submissions (0 outliers excluded), interquartile range 103.09–177.12; submissions 2021-03-20 to 2021-07-03; OPTIX backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
139.5 s · community measurement, sample 20 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 20 submissions (0 outliers excluded), interquartile range 89.37–144.85; submissions 2021-03-15 to 2021-09-16; 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.
Blender Benchmark 2.90
GPU, pavillon_barcelona (CUDA) · s, lower is better
1.2% difference, within the threshold
GeForce RTX 2070 SUPER305.5 s
GeForce RTX 2080 SUPER301.9 s
Position among tested models (23, CUDA)
B · 302A · 306
05001,0001,500
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
The 1.2% difference is below the noticeable threshold (5%).
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
305.5 s · community measurement, sample 252 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 252 submissions (35 outliers excluded), interquartile range 301.65–311.75; submissions 2020-09-02 to 2021-05-18; CUDA backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
301.9 s · community measurement, sample 117 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 117 submissions (17 outliers excluded), interquartile range 298.38–309.39; submissions 2020-09-02 to 2021-02-01; 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.
Blender Benchmark 2.90
GPU, pavillon_barcelona (OPTIX) · s, lower is better
B ahead by 8.5%
GeForce RTX 2070 SUPER128.8 s
GeForce RTX 2080 SUPER118.7 s
Position among tested models (13, OptiX)
B · 119A · 129
0200400600
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
NVIDIA GeForce RTX 2080 SUPER is ahead by 8.5% in this benchmark.
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
128.8 s · community measurement, sample 134 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 134 submissions (12 outliers excluded), interquartile range 126.86–131.25; submissions 2020-09-02 to 2021-01-30; OPTIX backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
118.7 s · community measurement, sample 70 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 70 submissions (13 outliers excluded), interquartile range 117.98–120.42; submissions 2020-09-02 to 2021-01-31; 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.
Blender Benchmark 2.90
GPU, victor (CUDA) · s, lower is better
1.4% difference, within the threshold
GeForce RTX 2070 SUPER376.9 s
GeForce RTX 2080 SUPER371.7 s
Position among tested models (20, CUDA)
B · 372A · 377
05001,0001,500
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
The 1.4% difference is below the noticeable threshold (5%).
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
376.9 s · community measurement, sample 243 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 243 submissions (40 outliers excluded), interquartile range 371.55–382.32; submissions 2020-09-02 to 2021-05-18; CUDA backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
371.7 s · community measurement, sample 111 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 111 submissions (18 outliers excluded), interquartile range 366.17–380.44; submissions 2020-09-02 to 2021-02-01; 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.
Blender Benchmark 2.90
GPU, victor (OPTIX) · s, lower is better
B ahead by 15.4%
GeForce RTX 2070 SUPER153.3 s
GeForce RTX 2080 SUPER132.8 s
Position among tested models (13, OptiX)
B · 133A · 153
0200400600800
Each dot is one model’s median in this benchmark. The scale starts at zero, s.
NVIDIA GeForce RTX 2080 SUPER is ahead by 15.4% in this benchmark.
About the measurement and source
A · NVIDIA GeForce RTX 2070 SUPER
153.3 s · community measurement, sample 115 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 115 submissions (9 outliers excluded), interquartile range 150.54–157.53; submissions 2020-09-02 to 2021-01-30; OPTIX backend. Snapshot 2026-11-14.
B · NVIDIA GeForce RTX 2080 SUPER
132.8 s · community measurement, sample 81 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 81 submissions (16 outliers excluded), interquartile range 132.15–134.59; submissions 2020-09-02 to 2021-01-31; 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.
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
2.6% difference, within the threshold
GeForce RTX 2070 SUPER2,234.5 samples/min
GeForce RTX 2080 SUPER2,292.6 samples/min
Position among tested models (67, OptiX)
A · 2,235B · 2,293
05,00010,00015,000
Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min.
The 2.6% difference is below the noticeable threshold (5%).
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 2080 SUPER
2,292.6 samples/min · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (3 outliers excluded), interquartile range 2221.12–2330.97; submissions 2025-07-24 to 2026-09-26; 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 (51)

Benchmark	A	B	Difference
Blender Benchmark 2.81aGPU, bmw27 (CUDA)	49.1	49.9	A +1.5%
Blender Benchmark 2.82GPU, bmw27 (CUDA)	49.9	50.6	A +1.3%
Blender Benchmark 2.83GPU, bmw27 (CUDA)	50.5	50.7	A +0.4%
Blender Benchmark 2.90GPU, bmw27 (CUDA)	54.4	55.6	A +2.1%
Blender Benchmark 2.92GPU, bmw27 (CUDA)	52.2	53.2	A +1.9%
Blender Benchmark 2.81aGPU, bmw27 (OPTIX)	27.1	25.4	B +6.5%
Blender Benchmark 2.82GPU, bmw27 (OPTIX)	26.7	25.4	B +5.1%
Blender Benchmark 2.83GPU, bmw27 (OPTIX)	25.8	25.2	B +2.4%
Blender Benchmark 2.90GPU, bmw27 (OPTIX)	25.8	25.1	B +2.6%
Blender Benchmark 2.92GPU, bmw27 (OPTIX)	26.5	26.1	B +1.4%
Blender Benchmark 2.81aGPU, classroom (CUDA)	169.4	163.2	B +3.8%
Blender Benchmark 2.82GPU, classroom (CUDA)	165.2	158.6	B +4.2%
Blender Benchmark 2.83GPU, classroom (CUDA)	168	159.1	B +5.6%
Blender Benchmark 2.90GPU, classroom (CUDA)	171.7	163.3	B +5.2%
Blender Benchmark 2.81aGPU, classroom (OPTIX)	101.2	91.2	B +10.9%
Blender Benchmark 2.82GPU, classroom (OPTIX)	100.4	90.8	B +10.5%
Blender Benchmark 2.83GPU, classroom (OPTIX)	100	90.1	B +11.1%
Blender Benchmark 2.81aGPU, fishy_cat (CUDA)	88.1	88	B +0.1%
Blender Benchmark 2.82GPU, fishy_cat (CUDA)	90.9	90.8	B +0.2%
Blender Benchmark 2.83GPU, fishy_cat (CUDA)	93.7	92.8	B +1%
Blender Benchmark 2.81aGPU, fishy_cat (OPTIX)	43.7	38.5	B +13.6%
Blender Benchmark 2.82GPU, fishy_cat (OPTIX)	44.6	39.6	B +12.5%
Blender Benchmark 2.83GPU, fishy_cat (OPTIX)	43.7	38.8	B +12.6%
Blender Benchmark 2.81aGPU, koro (CUDA)	154	150.6	B +2.3%
Blender Benchmark 2.82GPU, koro (CUDA)	153.3	149.5	B +2.6%
Blender Benchmark 2.83GPU, koro (CUDA)	161.1	156.7	B +2.8%
Blender Benchmark 2.81aGPU, koro (OPTIX)	83.3	68.3	B +21.8%
Blender Benchmark 2.82GPU, koro (OPTIX)	80.7	67.7	B +19.2%
Blender Benchmark 2.83GPU, koro (OPTIX)	79.6	67	B +18.8%
Blender Benchmark 2.90GPU, koro (OPTIX)	98.8	80.5	B +22.7%
Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA)	288.2	283.9	B +1.5%
Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA)	290.1	284.6	B +1.9%
Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA)	290.6	283.5	B +2.5%
Blender Benchmark 2.81aGPU, pavillon_barcelona (OPTIX)	132.8	119.3	B +11.3%
Blender Benchmark 2.82GPU, pavillon_barcelona (OPTIX)	131.7	123.3	B +6.8%
Blender Benchmark 2.83GPU, pavillon_barcelona (OPTIX)	128.7	120.5	B +6.8%
Blender Benchmark 2.81aGPU, victor (CUDA)	383.5	380.6	B +0.8%
Blender Benchmark 2.82GPU, victor (CUDA)	377.2	372	B +1.4%
Blender Benchmark 2.83GPU, victor (CUDA)	383.5	376.7	B +1.8%
Blender Benchmark 2.82GPU, victor (OPTIX)	161.2	141.5	B +13.9%
Blender Benchmark 2.83GPU, victor (OPTIX)	160.2	140.8	B +13.8%
Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,189.4	2,234.5	B +2.1%
Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,427.4	2,431.9	B +0.2%
Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,467.7	2,485.1	B +0.7%
Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,394.9	2,462.5	B +2.8%
Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,619	2,644.5	B +1%
Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,604.6	2,634.8	B +1.2%
Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,374.9	2,282.1	A +4.1%
Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,262.8	2,327.6	B +2.9%
Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,228.4	2,253.2	B +1.1%
Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,225.8	2,571.2	B +15.5%

Each benchmark version has its own scale: numbers are compared only within a row.

Reference results (63)

Benchmark	A	B	Difference
Blender Benchmark 2.81GPU, barbershop_interior (CUDA)	574.1	518.7	reference
Blender Benchmark 2.81aGPU, barbershop_interior (CUDA)	559.4	522.6	reference
Blender Benchmark 2.81GPU, barbershop_interior (OPTIX)	970.4	917.2	reference
Blender Benchmark 2.81aGPU, barbershop_interior (OPTIX)	979.6	885.7	reference
Blender Benchmark 2.81GPU, bmw27 (CUDA)	49.3	50.7	reference
Blender Benchmark 2.91.2GPU, bmw27 (CUDA)	51.6	51.7	reference
Blender Benchmark 2.81GPU, bmw27 (OPTIX)	26.7	28.1	reference
Blender Benchmark 2.91.2GPU, bmw27 (OPTIX)	26.2	25.5	reference
Blender Benchmark 2.81GPU, classroom (CUDA)	168.4	160.8	reference
Blender Benchmark 2.91.2GPU, classroom (CUDA)	172.6	165.6	reference
Blender Benchmark 2.92GPU, classroom (CUDA)	177.3	166.3	reference
Blender Benchmark 2.81GPU, classroom (OPTIX)	101.3	96.2	reference
Blender Benchmark 2.91.2GPU, classroom (OPTIX)	100.2	91.1	reference
Blender Benchmark 2.92GPU, classroom (OPTIX)	103	94	reference
Blender Benchmark 2.93.1GPU, classroom (OPTIX)	104.5	95.3	reference
Blender Benchmark 2.81GPU, fishy_cat (CUDA)	88	87	reference
Blender Benchmark 2.91.2GPU, fishy_cat (CUDA)	91.3	89.9	reference
Blender Benchmark 2.92GPU, fishy_cat (CUDA)	96.4	96.9	reference
Blender Benchmark 2.93.1GPU, fishy_cat (CUDA)	90.4	90.9	reference
Blender Benchmark 2.81GPU, fishy_cat (OPTIX)	43.3	40.4	reference
Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX)	45.5	—	no pair
Blender Benchmark 2.92GPU, fishy_cat (OPTIX)	51.5	44.7	reference
Blender Benchmark 2.93.1GPU, fishy_cat (OPTIX)	50.8	44.7	reference
Blender Benchmark 2.81GPU, koro (CUDA)	153.5	149.8	reference
Blender Benchmark 2.91.2GPU, koro (CUDA)	154.6	150.6	reference
Blender Benchmark 2.92GPU, koro (CUDA)	157.8	155.3	reference
Blender Benchmark 2.93.1GPU, koro (CUDA)	147.7	147.3	reference
Blender Benchmark 2.81GPU, koro (OPTIX)	82	71.4	reference
Blender Benchmark 2.91.2GPU, koro (OPTIX)	98.4	—	no pair
Blender Benchmark 2.93.1GPU, koro (OPTIX)	104.1	86	reference
Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA)	287.5	282.8	reference
Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA)	283.7	277.9	reference
Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA)	285.3	279	reference
Blender Benchmark 2.93.1GPU, pavillon_barcelona (CUDA)	256.6	253.5	reference
Blender Benchmark 2.81GPU, pavillon_barcelona (OPTIX)	130.3	129.1	reference
Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX)	129.8	120.9	reference
Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX)	130.6	122.6	reference
Blender Benchmark 2.93.1GPU, pavillon_barcelona (OPTIX)	135.5	127.4	reference
Blender Benchmark 2.81GPU, victor (CUDA)	382.7	378.4	reference
Blender Benchmark 2.91.2GPU, victor (CUDA)	360.5	356.8	reference
Blender Benchmark 2.92GPU, victor (CUDA)	434.6	432	reference
Blender Benchmark 2.93.1GPU, victor (CUDA)	384.8	385.3	reference
Blender Benchmark 2.81GPU, victor (OPTIX)	167.1	409.6	reference
Blender Benchmark 2.81aGPU, victor (OPTIX)	166.4	194.8	reference
Blender Benchmark 2.91.2GPU, victor (OPTIX)	152	134.1	reference
Blender Benchmark 2.92GPU, victor (OPTIX)	192	165	reference
Blender Benchmark 2.93.1GPU, victor (OPTIX)	183.9	159.7	reference
Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA)	1,556.4	1,631.8	reference
Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA)	1,531.1	1,646.2	reference
Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA)	1,580.6	1,769.3	reference
Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA)	1,546.7	1,667.7	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 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,143.1	2,171.8	reference
Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,079.7	2,202.7	reference
Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,522.5	2,537.9	reference
Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,413.7	2,425.3	reference
Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,447.3	2,430.7	reference
Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,072.4	—	no pair
Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,123.5	2,168.2	reference
Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)	2,338.4	—	no pair
Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA)	—	1,755.1	no pair

Each benchmark version has its own scale: numbers are compared only within a row.

Specifications

Specification	A · GeForce RTX 2070 SUPER	B · GeForce RTX 2080 SUPER	Difference
Chip
GPU chip	TU104-410-A1	TU104-450-A1	differs
Architecture	Turing	Turing	equal
Shader unitsShader unit counts are comparable only within one architecture.	2,560 (CUDA cores)	3,072 (CUDA cores)	B: 512 more
Clocks
Base clock	1,605 MHz	1,650 MHz	B: 45 MHz more
Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit.	1,770 MHz	1,815 MHz	B: 45 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	495.9 GB/s	B: 47.9 GB/s more
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)	250 W (TDP)	B: 35 W higher

Chip

GPU chip
ATU104-410-A1
BTU104-450-A1
differs
Architecture
ATuring
BTuring
equal
Shader units
A2,560 (CUDA cores)
B3,072 (CUDA cores)
B: 512 more
Shader unit counts are comparable only within one architecture.

Clocks

Base clock
A1,605 MHz
B1,650 MHz
B: 45 MHz more
Boost clock
A1,770 MHz
B1,815 MHz
B: 45 MHz more
Clocks 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
equal
Memory type
AGDDR6
BGDDR6
equal
Memory bus
A256 bit
B256 bit
equal
Memory bandwidth
A448 GB/s
B495.9 GB/s
B: 47.9 GB/s more
Excludes cache (Infinity Cache / L2), which affects effective bandwidth differently.

Power and dimensions

Board power
A215 W (TDP)
B250 W (TDP)
B: 35 W higher
TGP (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.

AI verdict

Questions and answers

How much video memory do NVIDIA GeForce RTX 2070 SUPER and NVIDIA GeForce RTX 2080 SUPER have?

NVIDIA GeForce RTX 2070 SUPER: 8 GB GDDR6, 256-bit bus. NVIDIA GeForce RTX 2080 SUPER: 8 GB GDDR6, 256-bit bus.

Which is faster: NVIDIA GeForce RTX 2070 SUPER or NVIDIA GeForce RTX 2080 SUPER?

NVIDIA GeForce RTX 2080 SUPER leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Data sources (2)

Wikipedia (English) — specifications of NVIDIA GeForce RTX 2070 SUPER, specifications of NVIDIA GeForce RTX 2080 SUPER, 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 2.91.2, 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 3.0.1, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 3.6.0, 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 5.3.0checked November 14, 2026

How we compare: methodology. Where the data comes from: sources.

Telegram VK

GeForce RTX 2070 SUPER vs GeForce RTX 2080 SUPER: specs and benchmark comparison

NVIDIA GeForce RTX 2070 SUPER

NVIDIA GeForce RTX 2080 SUPER

Short verdict

Rendering and compute

Advantages

AWhere GeForce RTX 2070 SUPER is better2

BWhere GeForce RTX 2080 SUPER is better7

Benchmarks

Blender Benchmark 2.93.1

Blender Benchmark 2.93.1

Blender Benchmark 2.93.1

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 2.92

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 2.90

Blender Benchmark 4.5.0

Specifications

Chip

Clocks

Memory

Power and dimensions

Compare with AI

Questions and answers

How much video memory do NVIDIA GeForce RTX 2070 SUPER and NVIDIA GeForce RTX 2080 SUPER have?

Which is faster: NVIDIA GeForce RTX 2070 SUPER or NVIDIA GeForce RTX 2080 SUPER?

See also

Where GeForce RTX 2070 SUPER is better2

Where GeForce RTX 2080 SUPER is better7