
GeForce RTX 4070 SUPER
Popular choices:

GeForce RTX 5090 D v2
Popular choices:
Performance Spectrum - GPU
About G3D Mark
G3D Mark is a standard benchmark that measures graphics performance in real-world gaming scenarios. It simplifies comparing cards from different brands, where higher scores directly correlate with better fps and smoother gaming experiences.
Head-to-Head Verdict, Benchmarks, Value & Long-Term Outlook
This comparison brings together gaming FPS, raw graphics performance, VRAM, feature set, power efficiency, pricing context, and long-term value so you can see which GPU actually makes more sense.
GeForce RTX 4070 SUPER
2024Why buy it
- ✅Costs $1,400 less on MSRP ($599 MSRP vs $1,999 MSRP).
- ✅Delivers 228.9% more G3D Mark for each dollar spent, at 50.0 vs 15.2 G3D/$ ($599 MSRP vs $1,999 MSRP).
- ✅Draws 220W instead of 575W, a 355W reduction.
- ✅Measures 245mm instead of 304mm, a 59mm shorter card that is more SFF-friendly.
Trade-offs
- ❌Lower average FPS than GeForce RTX 5090 D v2 across 50 tracked games in our benchmark data.
- ❌Less VRAM, with 12 GB vs 32 GB for high-resolution textures and newer games.
- ❌Fewer Tensor Cores for AI-powered features like DLSS and frame generation (224 vs 680), which can reduce FPS gains in supported games.
GeForce RTX 5090 D v2
2025Why buy it
- ✅32.0% more average FPS across 50 tracked games in our benchmark data.
- ✅203.6% more Tensor Cores for AI-powered features like DLSS and frame generation, which can increase overall FPS in supported games (680 vs 224).
- ✅166.7% more VRAM for high-resolution textures and newer games (32 GB vs 12 GB).
Trade-offs
- ❌233.7% HIGHER MSRP$1,999 MSRPvs$599 MSRP
- ❌Lower G3D Mark per dollar, at 15.2 vs 50.0 G3D/$ ($1,999 MSRP vs $599 MSRP).
- ❌161.4% higher power demand at 575W vs 220W.
- ❌24.1% longer card at 304mm vs 245mm.
GeForce RTX 4070 SUPER
2024GeForce RTX 5090 D v2
2025Why buy it
- ✅Costs $1,400 less on MSRP ($599 MSRP vs $1,999 MSRP).
- ✅Delivers 228.9% more G3D Mark for each dollar spent, at 50.0 vs 15.2 G3D/$ ($599 MSRP vs $1,999 MSRP).
- ✅Draws 220W instead of 575W, a 355W reduction.
- ✅Measures 245mm instead of 304mm, a 59mm shorter card that is more SFF-friendly.
Why buy it
- ✅32.0% more average FPS across 50 tracked games in our benchmark data.
- ✅203.6% more Tensor Cores for AI-powered features like DLSS and frame generation, which can increase overall FPS in supported games (680 vs 224).
- ✅166.7% more VRAM for high-resolution textures and newer games (32 GB vs 12 GB).
Trade-offs
- ❌Lower average FPS than GeForce RTX 5090 D v2 across 50 tracked games in our benchmark data.
- ❌Less VRAM, with 12 GB vs 32 GB for high-resolution textures and newer games.
- ❌Fewer Tensor Cores for AI-powered features like DLSS and frame generation (224 vs 680), which can reduce FPS gains in supported games.
Trade-offs
- ❌233.7% HIGHER MSRP$1,999 MSRPvs$599 MSRP
- ❌Lower G3D Mark per dollar, at 15.2 vs 50.0 G3D/$ ($1,999 MSRP vs $599 MSRP).
- ❌161.4% higher power demand at 575W vs 220W.
- ❌24.1% longer card at 304mm vs 245mm.
Quick Answers
So, is GeForce RTX 5090 D v2 better than GeForce RTX 4070 SUPER?
Which one is more future-proof for 2026 and beyond?
Which one is the smarter buy today, not just the cheaper card?
Is GeForce RTX 4070 SUPER still worth buying for gaming in 2026?
Games Benchmarks
Real-world benchmarks and performance projections based on comprehensive hardware analysis and comparative metrics. Values represent expected performance on High/Ultra settings at 1080p, 1440p, and 4K. Modeled using a Ryzen 7 9800X3D reference profile to minimize specific CPU bottlenecks.
Note: Performance behavior can vary per game. Specific architectures may perform better or worse depending on game engine optimizations and API implementation.

Path of Exile 2
| Preset | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| 1080p | ||
| low | 183 FPS | 276 FPS |
| medium | 167 FPS | 257 FPS |
| high | 151 FPS | 219 FPS |
| ultra | 131 FPS | 192 FPS |
| 1440p | ||
| low | 150 FPS | 260 FPS |
| medium | 124 FPS | 217 FPS |
| high | 110 FPS | 172 FPS |
| ultra | 101 FPS | 155 FPS |
| 4K | ||
| low | 92 FPS | 179 FPS |
| medium | 78 FPS | 149 FPS |
| high | 65 FPS | 112 FPS |
| ultra | 58 FPS | 100 FPS |

Counter-Strike 2
| Preset | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| 1080p | ||
| low | 574 FPS | 880 FPS |
| medium | 477 FPS | 713 FPS |
| high | 368 FPS | 561 FPS |
| ultra | 317 FPS | 474 FPS |
| 1440p | ||
| low | 401 FPS | 697 FPS |
| medium | 327 FPS | 591 FPS |
| high | 262 FPS | 483 FPS |
| ultra | 221 FPS | 383 FPS |
| 4K | ||
| low | 191 FPS | 383 FPS |
| medium | 155 FPS | 328 FPS |
| high | 132 FPS | 305 FPS |
| ultra | 110 FPS | 263 FPS |

League of Legends
| Preset | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| 1080p | ||
| low | 921 FPS | 944 FPS |
| medium | 742 FPS | 772 FPS |
| high | 652 FPS | 698 FPS |
| ultra | 569 FPS | 604 FPS |
| 1440p | ||
| low | 720 FPS | 731 FPS |
| medium | 578 FPS | 598 FPS |
| high | 497 FPS | 529 FPS |
| ultra | 427 FPS | 452 FPS |
| 4K | ||
| low | 498 FPS | 506 FPS |
| medium | 403 FPS | 419 FPS |
| high | 352 FPS | 377 FPS |
| ultra | 296 FPS | 316 FPS |

Valorant
| Preset | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| 1080p | ||
| low | 857 FPS | 999 FPS |
| medium | 711 FPS | 999 FPS |
| high | 646 FPS | 907 FPS |
| ultra | 590 FPS | 684 FPS |
| 1440p | ||
| low | 695 FPS | 885 FPS |
| medium | 576 FPS | 778 FPS |
| high | 507 FPS | 684 FPS |
| ultra | 455 FPS | 513 FPS |
| 4K | ||
| low | 470 FPS | 639 FPS |
| medium | 402 FPS | 547 FPS |
| high | 361 FPS | 456 FPS |
| ultra | 321 FPS | 342 FPS |
Technical Specifications
Side-by-side comparison of GeForce RTX 4070 SUPER and GeForce RTX 5090 D v2

GeForce RTX 4070 SUPER
GeForce RTX 4070 SUPER
The GeForce RTX 4070 SUPER is manufactured by NVIDIA. It was released in January 8 2024. It features the Ada Lovelace architecture. The core clock ranges from 1980 MHz to 2475 MHz. It has 7168 shading units. The thermal design power (TDP) is 220W. Manufactured using 5 nm process technology. It features 56 dedicated ray tracing cores for enhanced lighting effects. G3D Mark benchmark score: 29,958 points. Launch price was $599.

GeForce RTX 5090 D v2
GeForce RTX 5090 D v2
The GeForce RTX 5090 D v2 is manufactured by NVIDIA. It was released in August 15 2025. It features the Blackwell 2.0 architecture. The core clock ranges from 2017 MHz to 2407 MHz. It has 21760 shading units. The thermal design power (TDP) is 575W. Manufactured using 5 nm process technology. It features 170 dedicated ray tracing cores for enhanced lighting effects. G3D Mark benchmark score: 30,399 points. Launch price was $2,299.
Graphics Performance
The GeForce RTX 4070 SUPER scores 29,958 and the GeForce RTX 5090 D v2 reaches 30,399 in the G3D Mark benchmark — just a 1.5% difference, making them near-identical in rasterization performance. The GeForce RTX 4070 SUPER is built on Ada Lovelace while the GeForce RTX 5090 D v2 uses Blackwell 2.0, both on a 5 nm process. Shader units: 7,168 (GeForce RTX 4070 SUPER) vs 21,760 (GeForce RTX 5090 D v2). Raw compute: 35.48 TFLOPS (GeForce RTX 4070 SUPER) vs 104.8 TFLOPS (GeForce RTX 5090 D v2). Boost clocks: 2475 MHz vs 2407 MHz. Ray tracing: 56 RT cores (GeForce RTX 4070 SUPER) vs 170 (GeForce RTX 5090 D v2) with 224 Tensor cores vs 680.
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| G3D Mark Score | 29,958 | 30,399+1% |
| Architecture | Ada Lovelace | Blackwell 2.0 |
| Process Node | 5 nm | 5 nm |
| Shading Units | 7168 | 21760+204% |
| Compute (TFLOPS) | 35.48 TFLOPS | 104.8 TFLOPS+195% |
| Boost Clock | 2475 MHz+3% | 2407 MHz |
| ROPs | 80 | 176+120% |
| TMUs | 224 | 680+204% |
| L1 Cache | 7 MB | 21.3 MB+204% |
| L2 Cache | 48 MB | 96 MB+100% |
| Ray Tracing Cores | 56 | 170+204% |
| Tensor Cores | 224 | 680+204% |
Advanced Features (DLSS/FSR)
Both cards support Frame Generation, but the GeForce RTX 5090 D v2 is on a newer tier with DLSS 4 Multi Frame Generation, while the GeForce RTX 4070 SUPER tops out at DLSS 3.5 + Frame Generation.The GeForce RTX 5090 D v2 supports the newer DLSS 4 Super Resolution, whereas the GeForce RTX 4070 SUPER is capped at DLSS 3.5 Super Resolution.
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| Upscaling Tech | DLSS 3.5 Super Resolution | DLSS 4 Super Resolution |
| Frame Generation | DLSS 3.5 + Frame Generation | DLSS 4 Multi Frame Generation+14% |
| Ray Reconstruction | Yes (DLSS 3.5) | Yes (DLSS 4)+14% |
| Low Latency | NVIDIA Reflex | NVIDIA Reflex |
Video Memory (VRAM)
The GeForce RTX 4070 SUPER comes with 12 GB of VRAM, while the GeForce RTX 5090 D v2 has 32 GB. The GeForce RTX 5090 D v2 offers 166.7% more capacity, crucial for higher resolutions and texture-heavy games. Memory bandwidth: 504 GB/s (GeForce RTX 4070 SUPER) vs 1792 GB/s (GeForce RTX 5090 D v2) — a 255.6% advantage for the GeForce RTX 5090 D v2. Bus width: 192-bit vs 512-bit. L2 Cache: 48 MB (GeForce RTX 4070 SUPER) vs 96 MB (GeForce RTX 5090 D v2) — the GeForce RTX 5090 D v2 has significantly larger on-die cache to reduce VRAM reliance.
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| VRAM Capacity | 12 GB | 32 GB+167% |
| Memory Type | GDDR6X | GDDR7 |
| Memory Bandwidth | 504 GB/s | 1792 GB/s+256% |
| Bus Width | 192-bit | 512-bit+167% |
| L2 Cache | 48 MB | 96 MB+100% |
Display & API Support
DirectX support: 12 Ultimate (GeForce RTX 4070 SUPER) vs 12 Ultimate (GeForce RTX 5090 D v2). Vulkan: 1.3 vs 1.4. OpenGL: 4.6 vs 4.6. Maximum simultaneous displays: 4 vs 4.
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| DirectX | 12 Ultimate | 12 Ultimate |
| Vulkan | 1.3 | 1.4+8% |
| OpenGL | 4.6 | 4.6 |
| Max Displays | 4 | 4 |
Media & Encoding
Hardware encoder: NVENC 8th gen (GeForce RTX 4070 SUPER) vs NVENC (9th Gen) (GeForce RTX 5090 D v2). Decoder: NVDEC 5th gen vs NVDEC (6th Gen). Supported codecs: AV1,H.264,H.265/HEVC (GeForce RTX 4070 SUPER) vs AV1,H.264,H.265,VP9 (GeForce RTX 5090 D v2).
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| Encoder | NVENC 8th gen | NVENC (9th Gen) |
| Decoder | NVDEC 5th gen | NVDEC (6th Gen) |
| Codecs | AV1,H.264,H.265/HEVC | AV1,H.264,H.265,VP9 |
Power & Dimensions
The GeForce RTX 4070 SUPER draws 220W versus the GeForce RTX 5090 D v2's 575W — a 89.3% difference. The GeForce RTX 4070 SUPER is more power-efficient. Recommended PSU: 650W (GeForce RTX 4070 SUPER) vs 1000W (GeForce RTX 5090 D v2). Power connectors: 16-pin (12VHPWR) vs 16-pin. Card length: 245mm vs 304mm, occupying 2 vs 2 slots. Typical load temperature: 70°C vs 70°C.
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| TDP | 220W-62% | 575W |
| Recommended PSU | 650W-35% | 1000W |
| Power Connector | 16-pin (12VHPWR) | 16-pin |
| Length | 245mm | 304mm |
| Height | 111mm | 137mm |
| Slots | 2 | 2 |
| Temp (Load) | 70°C | 70°C |
| Perf/Watt | 136.2+157% | 52.9 |
Value Analysis
The GeForce RTX 4070 SUPER launched at $599 MSRP, while the GeForce RTX 5090 D v2 launched at $1999. The GeForce RTX 4070 SUPER costs 70% less ($1400 savings) on MSRP. Performance per dollar on MSRP (G3D Mark / MSRP): 50.0 (GeForce RTX 4070 SUPER) vs 15.2 (GeForce RTX 5090 D v2) — the GeForce RTX 4070 SUPER offers 228.9% better value. The GeForce RTX 5090 D v2 is the newer GPU (2025 vs 2024).
| Feature | GeForce RTX 4070 SUPER | GeForce RTX 5090 D v2 |
|---|---|---|
| MSRP | $599-70% | $1999 |
| Performance per Dollar | 50.0+229% | 15.2 |
| Codename | AD104 | GB202 |
| Release | January 8 2024 | August 15 2025 |
| Ranking | #18 | #15 |
Top Performing GPUs
The most powerful gpus ranked by G3D Mark benchmark scores.












