Skip to content
RU

NVIDIA · Maxwell

NVIDIA GeForce GTX 980 Ti: specs, benchmarks and comparison

  • 6 GB GDDR5
  • 250 W
Illustration, not a product photo
Launch price
$649
MSRP, US
Release
June 2, 2015

Performance

Rank among models tested in the same benchmark on the same render backend.

Blender Benchmark 2.81a

GPU, barbershop_interior (CUDA)

1,009.48 s

lower is better

Median of 4 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Blender Benchmark 2.90

GPU, bmw27 (CUDA)

95.8 s

lower is better

Rank 15 of 27 tested on CUDA22% of the leader
96
0100200300400
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 38 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (8)
BenchmarkResultRank
Blender Benchmark 2.93.174.95 s · small sample—
Blender Benchmark 2.92115.85 s · small sample—
Blender Benchmark 2.91.2109.3 s · small sample—
Blender Benchmark 2.90.1104.53 s · small sample—
Blender Benchmark 2.8394.21 s13 of 20
Blender Benchmark 2.8292.18 s14 of 23
Blender Benchmark 2.8194.16 s · small sample—
Blender Benchmark 2.81a92.89 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.93.1

GPU, bmw27 (OPTIX)

100.91 s

lower is better

Median of 4 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (2)
BenchmarkResultRank
Blender Benchmark 2.9294.7 s · small sample—
Blender Benchmark 2.90104.63 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, classroom (CUDA)

308.47 s

lower is better

Rank 13 of 25 tested on CUDA23% of the leader
308
0200400600800
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 33 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (8)
BenchmarkResultRank
Blender Benchmark 2.93.1257.56 s · small sample—
Blender Benchmark 2.92296.65 s · small sample—
Blender Benchmark 2.91.2291.56 s · small sample—
Blender Benchmark 2.90.1339.91 s · small sample—
Blender Benchmark 2.83303.77 s10 of 18
Blender Benchmark 2.82295.8 s · small sample—
Blender Benchmark 2.81303.79 s · small sample—
Blender Benchmark 2.81a299.43 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.93.1

GPU, classroom (OPTIX)

469.05 s

lower is better

Median of 1 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (2)
BenchmarkResultRank
Blender Benchmark 2.92400.85 s · small sample—
Blender Benchmark 2.90347.5 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, fishy_cat (CUDA)

195.44 s

lower is better

Rank 17 of 22 tested on CUDA20% of the leader
195
0200400600
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 30 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (7)
BenchmarkResultRank
Blender Benchmark 2.93.1243.74 s · small sample—
Blender Benchmark 2.92280.85 s · small sample—
Blender Benchmark 2.91.2233.37 s · small sample—
Blender Benchmark 2.83201.21 s · small sample—
Blender Benchmark 2.82202.39 s · small sample—
Blender Benchmark 2.81199.75 s · small sample—
Blender Benchmark 2.81a204.2 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.93.1

GPU, fishy_cat (OPTIX)

273.2 s

lower is better

Median of 1 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (2)
BenchmarkResultRank
Blender Benchmark 2.92222.68 s · small sample—
Blender Benchmark 2.90214.64 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, koro (CUDA)

368.07 s

lower is better

Rank 19 of 22 tested on CUDA16% of the leader
368
0200400600800
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 27 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (6)
BenchmarkResultRank
Blender Benchmark 2.93.1432.4 s · small sample—
Blender Benchmark 2.92704.41 s · small sample—
Blender Benchmark 2.91.2433.77 s · small sample—
Blender Benchmark 2.83448.09 s · small sample—
Blender Benchmark 2.82441.75 s · small sample—
Blender Benchmark 2.81a452.88 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, koro (OPTIX)

218.8 s

lower is better

Median of 3 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Blender Benchmark 2.90

GPU, pavillon_barcelona (CUDA)

497.77 s

lower is better

Rank 13 of 23 tested on CUDA24% of the leader
498
05001,0001,500
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 27 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (6)
BenchmarkResultRank
Blender Benchmark 2.93.1424.79 s · small sample—
Blender Benchmark 2.92622.54 s · small sample—
Blender Benchmark 2.91.2553.62 s · small sample—
Blender Benchmark 2.83498.5 s · small sample—
Blender Benchmark 2.82482.72 s · small sample—
Blender Benchmark 2.81a501.65 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, pavillon_barcelona (OPTIX)

504.7 s

lower is better

Median of 3 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Blender Benchmark 2.90

GPU, victor (CUDA)

1,018.49 s

lower is better

Rank 19 of 20 tested on CUDA16% of the leader
1,018
05001,0001,500
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 24 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (6)
BenchmarkResultRank
Blender Benchmark 2.93.11,351.18 s · small sample—
Blender Benchmark 2.921,290.81 s · small sample—
Blender Benchmark 2.91.2997.4 s · small sample—
Blender Benchmark 2.831,105.11 s · small sample—
Blender Benchmark 2.821,235.29 s · small sample—
Blender Benchmark 2.81a1,256.33 s · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 2.90

GPU, victor (OPTIX)

898.57 s

lower is better

Median of 3 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Blender Benchmark 3.6.0

GPU, sum of scenes monster + junkshop + classroom (CUDA)

706 samples/min

higher is better

Median of 1 runs · small sample · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (1)
BenchmarkResultRank
Blender Benchmark 3.1.0597 samples/min · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Blender Benchmark 3.4.0

GPU, sum of scenes monster + junkshop + classroom (OptiX)

560 samples/min

higher is better

Rank 40 of 43 tested on OptiX4% of the leader
560
05,00010,00015,000
Each dot is one catalog model in this benchmark; GeForce GTX 980 Ti is highlighted.

Median of 20 runs · Blender Open Data (Blender Foundation) · November 14, 2026

Other benchmark versions (17)
BenchmarkResultRank
Blender Benchmark 5.3.0189 samples/min · small sample—
Blender Benchmark 5.2.0443 samples/min · small sample—
Blender Benchmark 5.1.1405 samples/min · small sample—
Blender Benchmark 5.1.0449 samples/min · small sample—
Blender Benchmark 4.5.0505 samples/min · small sample—
Blender Benchmark 4.4.0483 samples/min · small sample—
Blender Benchmark 4.3.0505 samples/min · small sample—
Blender Benchmark 4.2.0533 samples/min · small sample—
Blender Benchmark 4.1.0502 samples/min · small sample—
Blender Benchmark 4.0.0533 samples/min · small sample—
Blender Benchmark 3.6.0576 samples/min · small sample—
Blender Benchmark 3.5.0549 samples/min · small sample—
Blender Benchmark 3.3.0527 samples/min · small sample—
Blender Benchmark 3.2.1542 samples/min · small sample—
Blender Benchmark 3.2.0553 samples/min · small sample—
Blender Benchmark 3.1.0545 samples/min33 of 38
Blender Benchmark 3.0.1592 samples/min · small sample—

Each benchmark version has its own scale; results from different versions are not compared.

Specifications

Reference values for the chip. Clocks, length and connectors depend on the card model.

Chip

GPU chip
GM200-310-A1
Architecture
Maxwell
Shader units
2,816 (CUDA cores)

Clocks

Base clock
1,000 MHz
Boost clock
1,076 MHz

Memory

Video memory
6 GB
Memory type
GDDR5
Memory bus
384 bit
Memory bandwidth
336.6 GB/s

Power and dimensions

Board power
250 W (TDP)

Specifications: Wikipedia (English), checked November 14, 2026. Release date and launch price: Wikipedia (CC BY-SA 4.0).

Will it fit your system

Checks the power supply, case length and PCIe slot.

  • Needs checkingPower supply. The manufacturer did not list a recommended PSU wattage (or it is not in the database).
  • Needs checkingCard length and case. Length depends on the specific partner model (ASUS, MSI, Palit and others), so pick the exact SKU.
  • Needs checkingPCIe interface. The card’s PCIe version is unknown.