GeForce RTX 5070 vs GTX 960
VS
Nvidia GeForce RTX 5070
GB205-300
Nvidia GeForce GTX 960
GM206
We compared two discrete desktop gaming GPUs: the GeForce RTX 5070 12 GB with 48 pipelines and 6144 shaders against the 10 years and 2 months older GTX 960 2 GB that utilizes 8 pipelines and 1024 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
DeviceFacts Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 5070
- Performs significantly better (up to 10.7x) in 3DMark Steel Nomad Lite
- 12.9x higher maximum theoretical performance (30.9 vs 2.4 TFLOPS)
- Shows 9.8x higher average frame rate in modern games at QHD resolution – 128 vs 13 FPS
- Manufactured using a more efficient 4 nm process technology
- Ray-tracing support with 48 dedicated RT cores
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 197 140 130 97 |
29 14 13 - |
| The Witcher 3 | 216 183 131 71 |
24 18 13 - |
| Counter-Strike 2 | 293 210 160 81 |
46 29 19 - |
| Far Cry 6 | 164 145 128 82 |
31 27 16 10 |
| Hogwarts Legacy | 140 117 92 51 |
18 12 10 - |
| CoD: Modern Warfare III | 178 171 136 89 |
30 24 16 12 |
| Ghost of Tsushima | 123 107 89 58 |
15 - - - |
| Cyberpunk 2077 | 164 144 99 43 |
14 11 - - |
| Shadow of the Tomb Raider | 253 238 189 98 |
28 26 15 - |
| 1080p High | 192 | 26 |
| 1080p Ultra | 162 | 19 |
| 1440p Ultra | 128 | 13 |
| 4K Ultra | 74 | - |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 22708 | 2302 |
| Solar Bay | 107004 | - |
| Port Royal | 14498 | - |
| Fire Strike | 58324 | 7720 |
| Wild Life Extreme | 43879 | 4543 |
| Night Raid | 172064 | 31121 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 254.4 img/sec | 51.7 img/sec |
| Face Detection | 180.6 img/sec | 26.1 img/sec |
| Horizon Detection | 7.91 Gpixels/sec | 0.84 Gpixels/sec |
| Edge Detection | 10.2 Gpixels/sec | 1.36 Gpixels/sec |
| Gaussian Blur | 10.7 Gpixels/sec | 1.26 Gpixels/sec |
| Feature Matching | 1.84 Gpixels/sec | 0.14 Gpixels/sec |
| Stereo Matching | 975.7 Gpixels/sec | 64.9 Gpixels/sec |
| Particle Physics | 27816.5 FPS | 1825 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 1289 | 677 |
| DirectX 11 | 279 FPS | 42 FPS |
| DirectX 12 | 106 FPS | 28 FPS |
| GPU Compute | 14323 Ops/s | 2801 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 12270 | 1492 |
| Image Segmentation (HP) | 30237 | 2183 |
| Image Super Resolution (Q) | 35585 | 3618 |
| Face Detection (HP) | 62662 | 3654 |
| Pose Estimation (Q) | 145190 | 11306 |
| Text Classification (SP) | 4198 | 1315 |
| Machine Translation (HP) | 6233 | 2085 |
| Object Detection (SP) | 16709 | 1927 |
| Depth Estimation (Q) | 58300 | 5491 |
| Style Transfer (SP) | 246598 | 22683 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 5070 and GTX 960General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | January 22, 2015 |
| Launch price (MSRP) | $549 | $199 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Blackwell 2.0 | Maxwell 2.0 |
| GPU Codename | GB205-300 | GM206 |
| Rival Equivalent | - Radeon RX 9070 | - |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - |
Desktop GPU rating (21st and 90th place)
Graphics Processing Unit
| Base Clock | 2160 MHz | 1127 MHz |
| Boost Clock | 2512 MHz | 1178 MHz |
| Shading Units | 6144 | 1024 |
| Texture Mapping Units (TMUs) | 192 | 64 |
| Render Output Units (ROPs) | 80 | 32 |
| Compute Units (Pipelines) | 48 | 8 |
| Tensor Cores | 192 | No |
| Ray-tracing Cores | 48 | No |
| L1 Cache | 128KB per cluster | 48KB per cluster |
| L2 Cache | 48MB shared | 1MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 201 GPixel/s | 38 GPixel/s |
| Texture Fill Rate | 482 GTexel/s | 75 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| TGP | 250 W | 120 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 28 nm |
| Die Size | 263 mm² | 228 mm² |
| Transistor Count | 31.1 billion | 2 billion |
| Transistor Density | 118.25 MTr/mm² | 8.77 MTr/mm² |
Memory
| Memory Type | GDDR7 | GDDR5 |
| Memory Size | 12 GB | 2 GB |
| Memory Clock | 1750 MHz | 1753 MHz |
| Effective Memory Speed | 28000 Mbps | 7000 Mbps |
| Bus | 192-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 12.0 | 5.2 |
| Ray Tracing | Yes | No |
| DLSS | DLSS 4 | No |
| DisplayPort | 2.1b | 1.2 |
Cast your vote
Total votes: 6