GeForce RTX 4070 Ti vs ATI Radeon HD 3870
Aggregate performance score
We've compared Radeon HD 3870 and GeForce RTX 4070 Ti, covering specs and all relevant benchmarks.
RTX 4070 Ti outperforms ATI HD 3870 by a whopping 5624% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 1001 | 7 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 0.06 | 49.02 |
| Power efficiency | 0.93 | 19.86 |
| Architecture | TeraScale (2005−2013) | Ada Lovelace (2022−2024) |
| GPU code name | RV670 | AD104 |
| Market segment | Desktop | Desktop |
| Release date | 19 November 2007 (17 years ago) | 3 January 2023 (2 years ago) |
| Launch price (MSRP) | $269 | $799 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
RTX 4070 Ti has 81600% better value for money than ATI HD 3870.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 320 | 7680 |
| Core clock speed | 777 MHz | 2310 MHz |
| Boost clock speed | no data | 2610 MHz |
| Number of transistors | 666 million | 35,800 million |
| Manufacturing process technology | 55 nm | 4 nm |
| Power consumption (TDP) | 106 Watt | 285 Watt |
| Texture fill rate | 12.43 | 626.4 |
| Floating-point processing power | 0.4973 TFLOPS | 40.09 TFLOPS |
| ROPs | 16 | 80 |
| TMUs | 16 | 240 |
| Tensor Cores | no data | 240 |
| Ray Tracing Cores | no data | 60 |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Length | 241 mm | 285 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 6-pin | 1x 16-pin |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR4 | GDDR6X |
| Maximum RAM amount | 512 MB | 12 GB |
| Memory bus width | 256 Bit | 192 Bit |
| Memory clock speed | 1126 MHz | 1313 MHz |
| Memory bandwidth | 72.06 GB/s | 504.2 GB/s |
| Shared memory | - | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | 2x DVI, 1x S-Video | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 10.1 (10_1) | 12 Ultimate (12_2) |
| Shader Model | 4.1 | 6.7 |
| OpenGL | 3.3 | 4.6 |
| OpenCL | N/A | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | - | 8.9 |
| DLSS | - | + |
Synthetic benchmark performance
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 3−4
−7400%
| 225
+7400%
|
| 1440p | 2−3
−7300%
| 148
+7300%
|
| 4K | 1−2
−9200%
| 93
+9200%
|
Cost per frame, $
| 1080p | 89.67
−2425%
| 3.55
+2425%
|
| 1440p | 134.50
−2391%
| 5.40
+2391%
|
| 4K | 269.00
−3031%
| 8.59
+3031%
|
- RTX 4070 Ti has 2425% lower cost per frame in 1080p
- RTX 4070 Ti has 2391% lower cost per frame in 1440p
- RTX 4070 Ti has 3031% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 316
+0%
|
316
+0%
|
| Counter-Strike 2 | 190−200
+0%
|
190−200
+0%
|
| Cyberpunk 2077 | 236
+0%
|
236
+0%
|
Full HD
Medium Preset
| Atomic Heart | 253
+0%
|
253
+0%
|
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike 2 | 190−200
+0%
|
190−200
+0%
|
| Cyberpunk 2077 | 218
+0%
|
218
+0%
|
| Far Cry 5 | 211
+0%
|
211
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 5 | 244
+0%
|
244
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
Full HD
High Preset
| Atomic Heart | 180
+0%
|
180
+0%
|
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike 2 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 185
+0%
|
185
+0%
|
| Dota 2 | 259
+0%
|
259
+0%
|
| Far Cry 5 | 203
+0%
|
203
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 5 | 228
+0%
|
228
+0%
|
| Grand Theft Auto V | 178
+0%
|
178
+0%
|
| Metro Exodus | 197
+0%
|
197
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 453
+0%
|
453
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike 2 | 190−200
+0%
|
190−200
+0%
|
| Cyberpunk 2077 | 167
+0%
|
167
+0%
|
| Dota 2 | 243
+0%
|
243
+0%
|
| Far Cry 5 | 189
+0%
|
189
+0%
|
| Forza Horizon 4 | 300−350
+0%
|
300−350
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 222
+0%
|
222
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
Full HD
Epic Preset
| Fortnite | 300−350
+0%
|
300−350
+0%
|
1440p
High Preset
| Counter-Strike 2 | 95−100
+0%
|
95−100
+0%
|
| Counter-Strike: Global Offensive | 500−550
+0%
|
500−550
+0%
|
| Grand Theft Auto V | 156
+0%
|
156
+0%
|
| Metro Exodus | 131
+0%
|
131
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Cyberpunk 2077 | 105
+0%
|
105
+0%
|
| Far Cry 5 | 182
+0%
|
182
+0%
|
| Forza Horizon 4 | 280−290
+0%
|
280−290
+0%
|
| The Witcher 3: Wild Hunt | 190−200
+0%
|
190−200
+0%
|
1440p
Epic Preset
| Fortnite | 150−160
+0%
|
150−160
+0%
|
4K
High Preset
| Atomic Heart | 75−80
+0%
|
75−80
+0%
|
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
| Grand Theft Auto V | 172
+0%
|
172
+0%
|
| Metro Exodus | 84
+0%
|
84
+0%
|
| The Witcher 3: Wild Hunt | 149
+0%
|
149
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
4K
Ultra Preset
| Battlefield 5 | 130−140
+0%
|
130−140
+0%
|
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
| Cyberpunk 2077 | 48
+0%
|
48
+0%
|
| Dota 2 | 226
+0%
|
226
+0%
|
| Far Cry 5 | 111
+0%
|
111
+0%
|
| Forza Horizon 4 | 240−250
+0%
|
240−250
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+0%
|
95−100
+0%
|
4K
Epic Preset
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how ATI HD 3870 and RTX 4070 Ti compete in popular games:
- RTX 4070 Ti is 7400% faster in 1080p
- RTX 4070 Ti is 7300% faster in 1440p
- RTX 4070 Ti is 9200% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 1.44 | 82.42 |
| Recency | 19 November 2007 | 3 January 2023 |
| Maximum RAM amount | 512 MB | 12 GB |
| Chip lithography | 55 nm | 4 nm |
| Power consumption (TDP) | 106 Watt | 285 Watt |
ATI HD 3870 has 168.9% lower power consumption.
RTX 4070 Ti, on the other hand, has a 5623.6% higher aggregate performance score, an age advantage of 15 years, a 2300% higher maximum VRAM amount, and a 1275% more advanced lithography process.
The GeForce RTX 4070 Ti is our recommended choice as it beats the Radeon HD 3870 in performance tests.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
