NVIDIA GeForce GTX 980 Ti vs NVIDIA RTX PRO 2000 Blackwell Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GTX 980 Ti

CORE STATE GM200
VRAM 6 GB
CLOCK SPEED 1076 MHz
TDP 250 W
BUS WIDTH 384 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
NVIDIA
GEFORCE

RTX PRO 2000 Blackwell

CORE STATE GB206
VRAM 16 GB
CLOCK SPEED 1957 MHz
TDP 70 W
BUS WIDTH 128 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,321
2,374.5
geekbench_metal
19,520
N/A
geekbench_opencl
43,513
106,087
geekbench_vulkan
47,724
113,865
passmark_directx_10
N/A
122
passmark_directx_11
N/A
174
passmark_directx_12
N/A
80
passmark_directx_9
N/A
241
passmark_g2d
N/A
1,303
passmark_g3d
N/A
20,049
passmark_gpu_compute
N/A
8,396

Analysis: NVIDIA GeForce GTX 980 Ti vs NVIDIA RTX PRO 2000 Blackwell

Head-to-Head Benchmarks

The recorded data shows a decisive victory for the NVIDIA RTX PRO 2000 Blackwell across every shared benchmark test. In the 3DMark Steel Nomad DX12 test, the RTX PRO 2000 Blackwell scores 2374.5, while the GTX 980 Ti manages 1321. This represents a 44.4% advantage for the newer card, a substantial margin that reflects the generational gap between the two architectures. The RTX PRO 2000 Blackwell is nearly double the performance of the GTX 980 Ti in this modern DirectX 12 workload, which is particularly telling given that the Steel Nomad test is designed to stress contemporary GPU features.

The gap widens considerably in compute-oriented benchmarks. In Geekbench OpenCL, the RTX PRO 2000 Blackwell records 106087 points against the GTX 980 Ti's 43513, a 59% delta in favor of the Blackwell card. This is more than double the raw compute output, aligning with the substantial difference in FP32 throughput between the two cards. The Geekbench Vulkan result follows a similar pattern: the RTX PRO 2000 Blackwell achieves 113865 points, while the GTX 980 Ti scores 47724, a 58.1% advantage. Vulkan is a low-level API that can expose architectural efficiencies, and the Blackwell architecture clearly benefits from its newer design.

The head-to-head data shows winsA equal to 0 and winsB equal to 3, meaning the RTX PRO 2000 Blackwell wins every single comparison where both cards have recorded scores. There is no benchmark in the shared set where the GTX 980 Ti comes out ahead. The closest margin is the Steel Nomad test at 44.4%, which is still a commanding lead. In the compute benchmarks, the margins exceed 58%, indicating that the Blackwell card's advantage is not merely in rasterization but extends deeply into general-purpose GPU compute.

Looking at the broader database context, the GTX 980 Ti holds a 73rd percentile ranking among all GPUs, while the RTX PRO 2000 Blackwell sits at the 70th percentile. This is noteworthy: despite losing every head-to-head benchmark, the GTX 980 Ti actually ranks slightly higher in the overall percentile distribution. This is because the percentile is computed against the entire database of GPUs, and the GTX 980 Ti's average benchmark score of 28020 is higher than the RTX PRO 2000 Blackwell's 25269 average. The RTX PRO 2000 Blackwell's average is dragged down by its inclusion of additional benchmark tests, such as the Passmark DX9, DX10, DX11, DX12, G2D, G3D, and GPU compute tests, where it records lower scores that pull its average down.

The nearest rivals for the GTX 980 Ti in the database include the AMD Radeon Pro W5500X with an average score of 27973 (0.2% delta), the AMD FirePro S7150 at 28117 (-0.3% delta), the AMD Radeon RX 7800M at 27883 (0.5% delta), and the AMD Radeon Pro Vega 20 at 27839 (0.7% delta). The RTX PRO 2000 Blackwell's nearest rivals are the AMD Radeon RX 6700M at 25633 (-1.4% delta), the AMD Radeon Pro W5700 at 25726 (-1.8% delta), the NVIDIA GeForce RTX 3080 Ti Mobile at 25740 (-1.8% delta), and the NVIDIA RTX A5000 Mobile at 24763 (2% delta). These rival deltas show that the GTX 980 Ti sits in a slightly higher performance tier on average, even though it loses to the RTX PRO 2000 Blackwell in direct comparisons.

Architecture Differences

The two cards represent opposite ends of NVIDIA's GPU design timeline. The GTX 980 Ti uses the GM200 chip built on Maxwell 2.0 architecture, fabricated on a 28 nm process at TSMC. The RTX PRO 2000 Blackwell uses the GB206 chip built on Blackwell 2.0 architecture, fabricated on a 5 nm process, also at TSMC. The process node difference is dramatic: 28 nm versus 5 nm represents several generations of lithographic improvement. The transistor count reflects this: the GM200 packs 8,000 million transistors across a 601 mm² die, yielding a transistor density of 13.3 million per square millimeter. The GB206 packs 21,900 million transistors on a much smaller 181 mm² die, achieving a transistor density of 121.0 million per square millimeter, roughly nine times higher.

The memory subsystems differ substantially. The GTX 980 Ti has 6 GB of GDDR5 memory on a 384-bit bus, delivering 336.6 GB/s of bandwidth. The RTX PRO 2000 Blackwell has 16 GB of GDDR7 memory on a 128-bit bus, delivering 288.0 GB/s of bandwidth. The newer card has significantly more capacity but lower peak bandwidth, a trade-off enabled by the efficiency of GDDR7 and the reduced bus width. The GTX 980 Ti's memory clock is 1753 MHz (7 Gbps effective), while the RTX PRO 2000 Blackwell runs at 1125 MHz (18 Gbps effective). The higher effective data rate of GDDR7 compensates for the narrower bus.

The compute cores are configured very differently. The GTX 980 Ti has 2816 shading units, 176 texture mapping units, and 96 raster output units. The RTX PRO 2000 Blackwell has 4352 shading units, 136 TMUs, and 48 ROPs. The Blackwell card has 54% more shading units but fewer TMUs and ROPs, reflecting a design optimized for compute throughput rather than traditional rasterization. The RTX PRO 2000 Blackwell also includes 34 ray tracing cores and 136 tensor cores, features entirely absent from the GTX 980 Ti, which predates the introduction of dedicated ray tracing and tensor hardware.

Clock speeds tell a story of architectural efficiency. The GTX 980 Ti has a base clock of 1000 MHz and a boost clock of 1076 MHz. The RTX PRO 2000 Blackwell has a lower base clock of 982 MHz but a much higher boost clock of 1957 MHz. The near-doubling of boost clock, combined with the higher shading unit count, produces the FP32 output difference: 6.060 TFLOPS for the GTX 980 Ti versus 17.03 TFLOPS for the RTX PRO 2000 Blackwell. The Blackwell card also supports FP16 at 17.03 TFLOPS (1:1 ratio), while the GTX 980 Ti has no recorded FP16 capability.

The power profiles are radically different. The GTX 980 Ti has a TDP of 250 W, requires both a 6-pin and an 8-pin power connector, and suggests a 600 W power supply. The RTX PRO 2000 Blackwell has a TDP of 70 W, requires no external power connectors, and suggests a 250 W power supply. This is a 72% reduction in power draw while delivering substantially higher performance, evidence of the efficiency gains of the 5 nm process and newer architecture.

Where Each One Wins

The RTX PRO 2000 Blackwell wins in every modern workload category represented in the shared benchmarks. In DirectX 12 gaming workloads, it leads by 44.4%. In OpenCL compute, it leads by 59%. In Vulkan, it leads by 58.1%. For any application that leverages these APIs, the Blackwell card is clearly superior. The presence of ray tracing cores and tensor cores means the RTX PRO 2000 Blackwell can handle ray-traced rendering and AI-accelerated tasks that the GTX 980 Ti cannot accelerate at all. The 16 GB memory capacity also makes the Blackwell card more suitable for large datasets, machine learning models, and high-resolution texture sets.

The GTX 980 Ti does have a niche based on the overall average benchmark score. Its average of 28020 exceeds the RTX PRO 2000 Blackwell's 25269, driven by the latter's lower scores in the Passmark suite. The GTX 980 Ti also holds a higher percentile rank (73rd versus 70th), meaning it outperforms a slightly larger fraction of the GPU population in the database. The GTX 980 Ti's nearest rivals all have average scores within 0.7% of its own, indicating it is well-matched against contemporary workstation cards like the AMD Radeon Pro W5500X and the AMD FirePro S7150.

For the RTX PRO 2000 Blackwell, its nearest rivals include the NVIDIA GeForce RTX 3080 Ti Mobile and the NVIDIA RTX A5000 Mobile, with deltas of -1.8% and +2% respectively. The Blackwell card's average score sits 2% above the RTX A5000 Mobile, showing it is competitive with that mobile workstation GPU despite its much lower power draw.

The GTX 980 Ti's advantage is essentially historical: it was a high-end card in its generation, and its raw rasterization performance still holds up in legacy workloads. The Passmark DX9 and DX10 results for the RTX PRO 2000 Blackwell are particularly low (241 and 122 respectively), suggesting that the newer architecture does not prioritize legacy DirectX paths. The GTX 980 Ti does not have Passmark scores recorded in the database, so a direct comparison in those legacy APIs is not possible, but the GTX 980 Ti's older architecture may handle them more efficiently.

The Verdict

The data points to a clear split based on workload type. For any modern application using DirectX 12, Vulkan, or OpenCL, the NVIDIA RTX PRO 2000 Blackwell is the superior choice. It delivers 44.4% to 59% higher performance in these APIs, has 16 GB of memory versus 6 GB, includes ray tracing and tensor cores, and does so while drawing only 70 W compared to the GTX 980 Ti's 250 W. The RTX PRO 2000 Blackwell is also an active product in production, while the GTX 980 Ti is end-of-life, meaning driver support and availability favor the newer card.

The GTX 980 Ti retains a narrow edge in the overall average benchmark score, 28020 versus 25269, and a higher percentile ranking at 73 versus 70. This suggests that in a mixed workload environment that includes legacy APIs and older applications, the GTX 980 Ti may still perform competitively. However, the head-to-head data shows no scenario where it beats the RTX PRO 2000 Blackwell in any shared modern benchmark.

For a user with legacy software that relies on older DirectX versions or that does not benefit from the newer architecture's features, the GTX 980 Ti's higher average score could be relevant. For anyone working with current generation games, compute workloads, AI inference, or ray-traced rendering, the RTX PRO 2000 Blackwell is the only reasonable choice based on the recorded data. The power efficiency alone, a 70 W TDP versus 250 W, makes the Blackwell card dramatically easier to integrate into small form factor systems and reduces cooling requirements.

The RTX PRO 2000 Blackwell's launch MSRP is not recorded in the database, so no pricing comparison is possible. The GTX 980 Ti has a recorded launch MSRP of 649 USD, which is stated here for reference only.

FAQ

Q: Which card wins in the 3DMark Steel Nomad DX12 benchmark?

A: The NVIDIA RTX PRO 2000 Blackwell wins with a score of 2374.5 against the GTX 980 Ti's 1321, a 44.4% advantage.

Q: How much faster is the RTX PRO 2000 Blackwell in OpenCL compute?

A: The RTX PRO 2000 Blackwell scores 106087 in Geekbench OpenCL versus 43513 for the GTX 980 Ti, a 59% lead.

Q: Does the GTX 980 Ti have ray tracing or tensor cores?

A: No, the GTX 980 Ti has no ray tracing cores or tensor cores. The RTX PRO 2000 Blackwell has 34 ray tracing cores and 136 tensor cores.

Q: What is the memory capacity difference between the two cards?

A: The GTX 980 Ti has 6 GB of GDDR5 memory, while the RTX PRO 2000 Blackwell has 16 GB of GDDR7 memory. The GTX 980 Ti has a wider 384-bit bus with 336.6 GB/s bandwidth, while the RTX PRO 2000 Blackwell uses a 128-bit bus with 288.0 GB/s bandwidth.

Q: Which card has the higher average benchmark score in the database?

A: The GTX 980 Ti has a higher average benchmark score of 28020 compared to the RTX PRO 2000 Blackwell's 25269. The GTX 980 Ti also ranks at the 73rd percentile versus the 70th percentile for the RTX PRO 2000 Blackwell.

Q: What is the power consumption difference?

A: The GTX 980 Ti has a TDP of 250 W and requires a 600 W power supply, while the RTX PRO 2000 Blackwell has a TDP of 70 W and requires a 250 W power supply. The GTX 980 Ti needs 1x 6-pin and 1x 8-pin power connectors, while the RTX PRO 2000 Blackwell requires no external power connectors.

Specification Differences

The following specifications differ between the two cards:

  • Chip: GM200 (GTX 980 Ti) versus GB206 (RTX PRO 2000 Blackwell)
  • Architecture: Maxwell 2.0 versus Blackwell 2.0
  • Generation: GeForce 900 versus Blackwell PRO W (x000)
  • Process Node: 28 nm versus 5 nm
  • Transistors: 8,000 million versus 21,900 million
  • Die Size: 601 mm² versus 181 mm²
  • Transistor Density: 13.3M / mm² versus 121.0M / mm²
  • Base Clock: 1000 MHz versus 982 MHz
  • Boost Clock: 1076 MHz versus 1957 MHz
  • Memory Clock: 1753 MHz (7 Gbps effective) versus 1125 MHz (18 Gbps effective)
  • Memory Size: 6 GB versus 16 GB
  • Memory Type: GDDR5 versus GDDR7
  • Memory Bus Width: 384 bit versus 128 bit
  • Memory Bandwidth: 336.6 GB/s versus 288.0 GB/s
  • Shading Units: 2816 versus 4352
  • TMUs: 176 versus 136
  • ROPs: 96 versus 48
  • RT Cores: None versus 34
  • Tensor Cores: None versus 136
  • Pixel Rate: 103.3 GPixel/s versus 93.94 GPixel/s
  • Texture Rate: 189.4 GTexel/s versus 266.2 GTexel/s
  • FP32: 6.060 TFLOPS versus 17.03 TFLOPS
  • FP16: Not recorded versus 17.03 TFLOPS (1:1)
  • TDP: 250 W versus 70 W
  • Power Connectors: 1x 6-pin + 1x 8-pin versus None
  • Suggested PSU: 600 W versus 250 W
  • Bus Interface: PCIe 3.0 x16 versus PCIe 5.0 x8
  • Display Outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 versus 4x mini-DisplayPort 2.1b
  • DirectX Support: 12 (12_1) versus 12 Ultimate (12_2)
  • Dimensions: 267 mm length, 111 mm height, 40 mm width versus 167 mm length, 69 mm height, 20 mm width
  • Production Status: End-of-life versus Active
  • Release Date: 2015-06-01 versus 2025-08-10
  • Predecessor: GeForce 700 versus Workstation Ada
  • Successor: GeForce 10 versus not recorded
  • Launch MSRP: 649 USD versus not recorded

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 980 Ti
RTX PRO 2000 Blackwell
Core Specs
Shading Units
2,816
4,352 +54.5%
Shaders
2,816
4,352 +54.5%
TMUs
176
136 -22.7%
ROPs
96
48 -50.0%
SM Count
—
34
Clocks
Base Clock
1000 MHz
982 MHz
Boost Clock
1076 MHz
1957 MHz
Memory Clock
1753 MHz 7 Gbps effective
1125 MHz 18 Gbps effective
Memory
Memory Size
6 GB
16 GB
VRAM (MB)
6,144
16,384 +166.7%
Memory Type
GDDR5
GDDR7
Memory Bus
384 bit
128 bit
Bandwidth
336.6 GB/s
288.0 GB/s
Cache
L1 Cache
48 KB (per SMM)
128 KB (per SM)
L2 Cache
3 MB
32 MB
Performance
Pixel Rate
103.3 GPixel/s
93.94 GPixel/s
Texture Rate
189.4 GTexel/s
266.2 GTexel/s
FP32 (TFLOPS)
6.060 TFLOPS
17.03 TFLOPS
FP64 (TFLOPS)
189.4 GFLOPS (1:32)
266.2 GFLOPS (1:64)
FP16 (TFLOPS)
—
17.03 TFLOPS (1:1)
AI/RT
RT Cores
—
34
Tensor Cores
—
136
Power
TDP
250 W
70 W
TDP (W)
250
70 -72.0%
Suggested PSU
600 W
250 W
Power Connectors
1x 6-pin + 1x 8-pin
None
Architecture
Architecture
Maxwell 2.0
Blackwell 2.0
GPU Name
GM200
GB206
Generation
GeForce 900
Blackwell PRO W (x000)
Process Size
28 nm
5 nm
Transistors
8,000 million
21,900 million
Die Size
601 mm²
181 mm²
Foundry
TSMC
TSMC
Density
13.3M / mm²
121.0M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
5.2
12.0
Shader Model
6.8
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
167 mm 6.6 inches
Height
111 mm 4.4 inches
69 mm 2.7 inches
Outputs
1x DVI1x HDMI 2.03x DisplayPort 1.2
4x mini-DisplayPort 2.1b
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x8
Other
Launch Price
649 USD
—
Production
End-of-life
Active
Predecessor
GeForce 700
Workstation Ada
Successor
GeForce 10
—
View GeForce GTX 980 Ti Details View RTX PRO 2000 Blackwell Details