NVIDIA GeForce GTX 950 vs NVIDIA GeForce RTX 2060 Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GTX 950

CORE STATE GM206
VRAM 2 GB
CLOCK SPEED 1188 MHz
TDP 90 W
BUS WIDTH 128 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
NVIDIA
GEFORCE

GeForce RTX 2060

CORE STATE TU106
VRAM 6 GB
CLOCK SPEED 1680 MHz
TDP 160 W
BUS WIDTH 192 bit
ARCHITECTURE Turing
nm
PROCESS 12 nm
LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_metal
7,172
N/A
geekbench_opencl
15,662
65,014
geekbench_vulkan
16,734
65,846
3dmark_3dmark_steel_nomad_dx12
N/A
1,242
passmark_directx_10
N/A
98
passmark_directx_11
N/A
110
passmark_directx_12
N/A
53
passmark_directx_9
N/A
190
passmark_g2d
N/A
745
passmark_g3d
N/A
14,111
passmark_gpu_compute
N/A
5,488

Analysis: NVIDIA GeForce GTX 950 vs NVIDIA GeForce RTX 2060

Head-to-Head Benchmarks

The recorded data shows a complete sweep for the RTX 2060 in the two directly comparable benchmark tests. In Geekbench OpenCL, the RTX 2060 scores 65014 against the GTX 950's 15662, a 315.1% advantage. That is not a marginal generational step; it is a quadrupling of raw compute throughput as measured by that workload. The Vulkan result is similarly lopsided: 65846 versus 16734, a 293.5% lead for the newer card.

These two tests are the only head-to-head measurements shared by both cards in the database, and the RTX 2060 wins both. There is no benchmark in the shared set where the GTX 950 comes out ahead. The wins tally stands at 2 for the RTX 2060 and 0 for the GTX 950.

Context from the nearest-rival data reinforces how far apart these two sit in the overall hierarchy. The RTX 2060's average benchmark score is 15290, which places it at the 58th percentile of all GPUs. Its closest rivals are the GTX 580 (15283, 0% delta), the AMD Radeon 680M (15270, 0.1% ahead), the RTX 3050 OEM (15199, 0.6% behind), and the RX 7600 (15171, 0.8% behind). The GTX 950, by contrast, averages 13189 and sits at the 53rd percentile, with nearest rivals including the GTX 480 (13300, 0.8% ahead of it) and the AMD FirePro M6100 (13354, 1.2% ahead). The gap between the two cards' average scores is roughly 2100 points, which is larger than the entire delta between the GTX 950 and any of its four closest competitors.

The OpenCL gap deserves particular attention because it is the larger of the two wins. A 315.1% difference means the RTX 2060 delivers more than four times the OpenCL performance of the GTX 950. Even the Vulkan margin, at 293.5%, is close to a fourfold improvement. These are not percentage points that can be explained by clock speed alone; they reflect a fundamentally different class of hardware.

FAQ

Q: Which card has the higher average benchmark score?

A: The RTX 2060 averages 15290 across all recorded benchmarks, while the GTX 950 averages 13189. The RTX 2060 also holds a higher percentile ranking at 58 versus 53.

Q: How much faster is the RTX 2060 in OpenCL?

A: The RTX 2060 scores 65014 versus 15662 for the GTX 950, a 315.1% advantage in the database's Geekbench OpenCL test.

Q: Does the GTX 950 win any shared benchmark?

A: No. In the two head-to-head tests recorded (Geekbench OpenCL and Geekbench Vulkan), the GTX 950 loses both. Its wins tally is 0.

Q: What is the RTX 2060's closest rival according to the database?

A: The NVIDIA GeForce GTX 580, with an average score of 15283 and a 0% delta from the RTX 2060's 15290. The AMD Radeon 680M is nearly tied at 15270, 0.1% off.

Q: What is the GTX 950's closest rival?

A: The NVIDIA Tesla M2090, at 13075, is 0.9% behind the GTX 950's 13189. The GTX 480 (13300) and AMD Radeon Pro 555X (13321) are slightly ahead of it.

Q: Do both cards support Vulkan and DirectX 12?

A: Yes, both support Vulkan 1.4 and OpenGL 4.6. The RTX 2060 supports DirectX 12 Ultimate (12_2), while the GTX 950 supports DirectX 12 (12_1).

Architecture Differences

The RTX 2060 uses the TU106 chip built on Turing architecture, fabricated by TSMC on a 12 nm process. It packs 10,800 million transistors onto a 445 mm² die, for a transistor density of 24.3 million per square millimeter. The GTX 950 uses the GM206 chip on Maxwell 2.0 architecture, also TSMC, but on a 28 nm node. It holds 2,940 million transistors on a 228 mm² die, giving a density of 12.9 million per square millimeter. The RTX 2060 therefore has roughly 3.7 times the transistor count and nearly double the die area, on a process two nodes smaller.

The RTX 2060 introduces hardware features that the GTX 950 simply does not have. It includes 30 RT cores for ray tracing and 240 tensor cores for AI workloads. The GTX 950 has neither. This is a categorical difference, not a scaling one. The RTX 2060 also has 1920 shading units, 120 texture mapping units, and 48 ROPs, versus 768 shading units, 48 TMUs, and 32 ROPs on the GTX 950.

Clock behavior differs as well. The RTX 2060 runs at a 1365 MHz base and 1680 MHz boost, while the GTX 950 runs at 1024 MHz base and 1188 MHz boost. The RTX 2060's memory operates at 1750 MHz with 14 Gbps effective transfer, while the GTX 950's memory runs at 1653 MHz with 6.6 Gbps effective. The RTX 2060 supports DirectX 12 Ultimate (12_2) and has a full feature set for modern rendering paths, whereas the GTX 950 tops out at DirectX 12 (12_1).

Specification Differences

Memory capacity and type are the most visible differences. The RTX 2060 comes with 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s of bandwidth. The GTX 950 has 2 GB of GDDR5 on a 128-bit bus, delivering 105.8 GB/s. That is a threefold capacity increase and more than three times the bandwidth for the RTX 2060.

Compute rates follow the same pattern. The RTX 2060 delivers 6.451 TFLOPS FP32 and 12.90 TFLOPS FP16 (2:1 ratio). The GTX 950 delivers 1.825 TFLOPS FP32 and has no recorded FP16 rate. Pixel fill rate is 80.64 GPixel/s for the RTX 2060 versus 38.02 GPixel/s for the GTX 950. Texture fill rate is 201.6 GTexel/s versus 57.02 GTexel/s.

Power and physical specifications also differ. The RTX 2060 has a 160 W TDP with a single 8-pin power connector and a suggested 450 W PSU. The GTX 950 has a 90 W TDP with a single 6-pin connector and a suggested 250 W PSU. Both are dual-slot cards. The RTX 2060 measures 229 mm in length, 113 mm in height, and 35 mm in width. The GTX 950 is 202 mm long, with no recorded height or width. Display outputs differ: the RTX 2060 offers 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C, while the GTX 950 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2.

The launch MSRP for the RTX 2060 was 349 USD. The launch MSRP for the GTX 950 was 159 USD.

The Verdict

The data is unambiguous. The RTX 2060 outperforms the GTX 950 in every shared benchmark, by margins between roughly 293% and 315%. Its average score of 15290 sits at the 58th percentile of all GPUs, while the GTX 950's 13189 sits at the 53rd percentile. If the choice is between these two cards and the only consideration is measured performance, the RTX 2060 is the correct pick.

The GTX 950 still has a role for systems with strict power or length constraints. Its 90 W TDP and 250 W suggested PSU make it compatible with older or smaller power supplies, and its 202 mm length fits shorter chassis. The RTX 2060 demands 160 W, a 450 W PSU, and 229 mm of clearance. It also requires an 8-pin connector rather than the GTX 950's 6-pin. For a low-power or compact build, the GTX 950's physical profile is a legitimate advantage.

Buyers should also consider the feature gap beyond raw benchmarks. The RTX 2060's RT cores and tensor cores enable ray tracing and AI-accelerated features that the GTX 950 cannot run at all. Its 6 GB VRAM and GDDR6 memory provide headroom for modern textures and higher resolutions. The GTX 950's 2 GB GDDR5 is a hard ceiling for current titles. The RTX 2060 is the better card by every measured metric, and the GTX 950 only makes sense when power delivery, case space, or legacy system compatibility override performance.

Where Each One Wins

The RTX 2060 wins everywhere the two are directly compared. Geekbench OpenCL: 65014 versus 15662. Geekbench Vulkan: 65846 versus 16734. It also wins on the broader metrics: average score, percentile, memory bandwidth, FP32 throughput, pixel rate, and texture rate. For any workload that scales with shading units, TMUs, ROPs, or memory bandwidth, the RTX 2060 is the stronger option.

The GTX 950's wins are not in the benchmark data; they are in its physical and electrical footprint. It draws 90 W versus 160 W, needs only a 250 W PSU versus 450 W, uses a 6-pin connector instead of an 8-pin, and is 202 mm long versus 229 mm. It also launched at a lower MSRP of 159 USD versus 349 USD, though both cards are now end-of-life. For someone retrofitting an older machine with a modest power supply, or building in a very small case, the GTX 950 is the only one of the two that fits. It also matches the RTX 2060 on API support for OpenGL 4.6 and Vulkan 1.4, so it is not obsolete in every software interface.

The practical split is simple. If the system can supply 160 W and fit a 229 mm dual-slot card, the RTX 2060 is the choice on the strength of its benchmark results alone. If the system is limited to a 250 W PSU or a shorter card, the GTX 950 remains a functional option, provided the user accepts its 2 GB memory ceiling and lack of RT and tensor cores. The RTX 2060 is the faster card in every recorded test; the GTX 950 is merely the more accommodating one in constrained builds.

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 950
RTX 2060
Core Specs
Shading Units
768
1,920 +150.0%
Shaders
768
1,920 +150.0%
TMUs
48
120 +150.0%
ROPs
32
48 +50.0%
SM Count
30
Clocks
Base Clock
1024 MHz
1365 MHz
Boost Clock
1188 MHz
1680 MHz
Memory Clock
1653 MHz 6.6 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
2 GB
6 GB
VRAM (MB)
2,048
6,144 +200.0%
Memory Type
GDDR5
GDDR6
Memory Bus
128 bit
192 bit
Bandwidth
105.8 GB/s
336.0 GB/s
Cache
L1 Cache
48 KB (per SMM)
64 KB (per SM)
L2 Cache
1024 KB
3 MB
Performance
Pixel Rate
38.02 GPixel/s
80.64 GPixel/s
Texture Rate
57.02 GTexel/s
201.6 GTexel/s
FP32 (TFLOPS)
1.825 TFLOPS
6.451 TFLOPS
FP64 (TFLOPS)
57.02 GFLOPS (1:32)
201.6 GFLOPS (1:32)
FP16 (TFLOPS)
12.90 TFLOPS (2:1)
AI/RT
RT Cores
30
Tensor Cores
240
Power
TDP
90 W
160 W
TDP (W)
90
160 +77.8%
Suggested PSU
250 W
450 W
Power Connectors
1x 6-pin
1x 8-pin
Architecture
Architecture
Maxwell 2.0
Turing
GPU Name
GM206
TU106
Generation
GeForce 900
GeForce 20
Process Size
28 nm
12 nm
Transistors
2,940 million
10,800 million
Die Size
228 mm²
445 mm²
Foundry
TSMC
TSMC
Density
12.9M / mm²
24.3M / 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
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
202 mm 8 inches
229 mm 9 inches
Height
113 mm 4.4 inches
Outputs
1x DVI1x HDMI 2.03x DisplayPort 1.2
1x DVI1x HDMI 2.02x DisplayPort 1.4a1x USB Type-C
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
159 USD
349 USD
Production
End-of-life
End-of-life
Predecessor
GeForce 700
GeForce 10
Successor
GeForce 10
GeForce 30
View GeForce GTX 950 Details View GeForce RTX 2060 Details