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

2023

Why buy it

✅Costs $1,400 less on MSRP ($599 MSRP vs $1,999 MSRP).
✅Delivers 195.5% more G3D Mark for each dollar spent, at 44.9 vs 15.2 G3D/$ ($599 MSRP vs $1,999 MSRP).
✅Draws 200W instead of 575W, a 375W reduction.

Trade-offs

❌Lower average FPS than GeForce RTX 5090 D v2 across 13 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 (184 vs 680), which can reduce FPS gains in supported games.

GeForce RTX 5090 D v2

2025

Why buy it

✅37.5% more average FPS across 13 tracked games in our benchmark data.
✅269.6% more Tensor Cores for AI-powered features like DLSS and frame generation, which can increase overall FPS in supported games (680 vs 184).
✅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$599 MSRP
❌Lower G3D Mark per dollar, at 15.2 vs 44.9 G3D/$ ($1,999 MSRP vs $599 MSRP).
❌187.5% higher power demand at 575W vs 200W.

GeForce RTX 4070

2023

GeForce RTX 5090 D v2

2025

Why buy it

✅Costs $1,400 less on MSRP ($599 MSRP vs $1,999 MSRP).
✅Delivers 195.5% more G3D Mark for each dollar spent, at 44.9 vs 15.2 G3D/$ ($599 MSRP vs $1,999 MSRP).
✅Draws 200W instead of 575W, a 375W reduction.

Why buy it

✅37.5% more average FPS across 13 tracked games in our benchmark data.
✅269.6% more Tensor Cores for AI-powered features like DLSS and frame generation, which can increase overall FPS in supported games (680 vs 184).
✅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 13 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 (184 vs 680), which can reduce FPS gains in supported games.

Trade-offs

❌
233.7% HIGHER MSRP
$1,999 MSRPvs$599 MSRP
❌Lower G3D Mark per dollar, at 15.2 vs 44.9 G3D/$ ($1,999 MSRP vs $599 MSRP).
❌187.5% higher power demand at 575W vs 200W.

Quick Answers

So, is GeForce RTX 5090 D v2 better than GeForce RTX 4070?

Yes. GeForce RTX 5090 D v2 is the better GPU overall here. You are getting 37.5% more average FPS across 13 tracked games in our benchmark data, 12.9% higher PassMark G3D performance, 680 vs 184 Tensor cores, and 32 GB vs 12 GB of VRAM. It also comes from 2025 instead of 2023, which helps its case as the more complete modern gaming card.

Which one is more future-proof for 2026 and beyond?

GeForce RTX 5090 D v2 is the more future-proof choice for 2026 and beyond. You are getting a newer 2025 generation instead of 2023, 12.9% more raw performance headroom, more VRAM at 32 GB instead of 12 GB, and better upscaling support with DLSS 4 Super Resolution (2025) instead of DLSS 3.5 Super Resolution (2023) and better frame-generation support with DLSS 4 Multi Frame Generation (2025) instead of DLSS 3.5 + Frame Generation (2023). That leaves it with more room for heavier textures, tougher ray tracing loads, and higher-end 1440p or 4K gaming over the next few years.

Which one is the smarter buy today, not just the cheaper card?

GeForce RTX 5090 D v2 is about 233.7% more expensive on MSRP at $1,999 MSRP versus $599 MSRP, and you are getting 37.5% more estimated average FPS across 13 tracked games in our benchmark data and 12.9% higher G3D Mark. GeForce RTX 4070 still holds the G3D-per-dollar lead, so the performance win comes with a real value premium. If you are comfortable paying the premium for the stronger gaming result, GeForce RTX 5090 D v2 is the one to buy. If staying closer to budget matters more, GeForce RTX 4070 still makes more sense on price alone and remains capable enough for modern gaming.

Is GeForce RTX 4070 still worth buying for gaming in 2026?

Yes. GeForce RTX 4070 is still a strong gaming GPU in 2026: it is excellent for 1080p, very strong for 1440p, and still capable at 4K with sensible settings or upscaling. This mostly comes down to price. If you want to stay closer to $599 MSRP, it remains a strong choice; if you are comfortable paying more, GeForce RTX 5090 D v2 earns that extra money with a clearly stronger gaming result and a more complete overall package.

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.

GeForce RTX 4070 Benchmark Check

GeForce RTX 5090 D v2 Benchmark Check

Path of Exile 2

Preset	GeForce RTX 4070	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

Open GeForce RTX 4070 Open GeForce RTX 5090 D v2

Path of Exile 2

Path of Exile 2

Counter-Strike 2

Preset	GeForce RTX 4070	GeForce RTX 5090 D v2
1080p
low	544 FPS	880 FPS
medium	454 FPS	713 FPS
high	353 FPS	561 FPS
ultra	299 FPS	474 FPS
1440p
low	351 FPS	697 FPS
medium	288 FPS	591 FPS
high	235 FPS	483 FPS
ultra	197 FPS	383 FPS
4K
low	172 FPS	383 FPS
medium	144 FPS	328 FPS
high	125 FPS	305 FPS
ultra	101 FPS	263 FPS

Open GeForce RTX 4070 Open GeForce RTX 5090 D v2

Counter-Strike 2

Counter-Strike 2

League of Legends

Preset	GeForce RTX 4070	GeForce RTX 5090 D v2
1080p
low	884 FPS	944 FPS
medium	713 FPS	772 FPS
high	643 FPS	698 FPS
ultra	569 FPS	604 FPS
1440p
low	684 FPS	731 FPS
medium	549 FPS	598 FPS
high	483 FPS	529 FPS
ultra	424 FPS	452 FPS
4K
low	467 FPS	506 FPS
medium	373 FPS	419 FPS
high	326 FPS	377 FPS
ultra	277 FPS	316 FPS

Open GeForce RTX 4070 Open GeForce RTX 5090 D v2

League of Legends

League of Legends

Valorant

Preset	GeForce RTX 4070	GeForce RTX 5090 D v2
1080p
low	751 FPS	999 FPS
medium	612 FPS	999 FPS
high	536 FPS	907 FPS
ultra	497 FPS	684 FPS
1440p
low	615 FPS	885 FPS
medium	500 FPS	778 FPS
high	433 FPS	684 FPS
ultra	395 FPS	513 FPS
4K
low	384 FPS	639 FPS
medium	324 FPS	547 FPS
high	301 FPS	456 FPS
ultra	272 FPS	342 FPS

Open GeForce RTX 4070 Open GeForce RTX 5090 D v2

Valorant

Valorant

Check FPS for your specific build

Technical Specifications

Side-by-side comparison of GeForce RTX 4070 and GeForce RTX 5090 D v2

GeForce RTX 4070

The GeForce RTX 4070 is manufactured by NVIDIA. It was released in April 12 2023. It features the Ada Lovelace architecture. The core clock ranges from 1920 MHz to 2475 MHz. It has 5888 shading units. The thermal design power (TDP) is 200W. Manufactured using 5 nm process technology. It features 46 dedicated ray tracing cores for enhanced lighting effects. G3D Mark benchmark score: 26,919 points. Launch price was $599.

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

In G3D Mark, the GeForce RTX 4070 scores 26,919 versus the GeForce RTX 5090 D v2's 30,399 — the GeForce RTX 5090 D v2 leads by 12.9%. The GeForce RTX 4070 is built on Ada Lovelace while the GeForce RTX 5090 D v2 uses Blackwell 2.0, both on a 5 nm process. Shader units: 5,888 (GeForce RTX 4070) vs 21,760 (GeForce RTX 5090 D v2). Raw compute: 29.15 TFLOPS (GeForce RTX 4070) vs 104.8 TFLOPS (GeForce RTX 5090 D v2). Boost clocks: 2475 MHz vs 2407 MHz. Ray tracing: 46 RT cores (GeForce RTX 4070) vs 170 (GeForce RTX 5090 D v2) with 184 Tensor cores vs 680.

Feature	GeForce RTX 4070	GeForce RTX 5090 D v2
G3D Mark Score	26,919	30,399+13%
Architecture	Ada Lovelace	Blackwell 2.0
Process Node	5 nm	5 nm
Shading Units	5888	21760+270%
Compute (TFLOPS)	29.15 TFLOPS	104.8 TFLOPS+260%
Boost Clock	2475 MHz+3%	2407 MHz
ROPs	64	176+175%
TMUs	184	680+270%
L1 Cache	5.8 MB	21.3 MB+267%
L2 Cache	36 MB	96 MB+167%
Ray Tracing Cores	46	170+270%
Tensor Cores	184	680+270%

✨

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 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 is capped at DLSS 3.5 Super Resolution.

Feature	GeForce RTX 4070	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 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) 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: 36 MB (GeForce RTX 4070) 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	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	36 MB	96 MB+167%

🖥️

Display & API Support

DirectX support: 12.2 (GeForce RTX 4070) 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	GeForce RTX 5090 D v2
DirectX	12.2+2%	12 Ultimate
Vulkan	1.3	1.4+8%
OpenGL	4.6	4.6
Max Displays	4	4

🎬

Media & Encoding

Hardware encoder: 8th Gen NVENC (2x) (GeForce RTX 4070) vs NVENC (9th Gen) (GeForce RTX 5090 D v2). Decoder: 5th Gen NVDEC vs NVDEC (6th Gen). Supported codecs: MPEG-2,H.264,HEVC,VP9,AV1 (GeForce RTX 4070) vs AV1,H.264,H.265,VP9 (GeForce RTX 5090 D v2).

Feature	GeForce RTX 4070	GeForce RTX 5090 D v2
Encoder	8th Gen NVENC (2x)	NVENC (9th Gen)
Decoder	5th Gen NVDEC	NVDEC (6th Gen)
Codecs	MPEG-2,H.264,HEVC,VP9,AV1	AV1,H.264,H.265,VP9

🔌

Power & Dimensions

The GeForce RTX 4070 draws 200W versus the GeForce RTX 5090 D v2's 575W — a 96.8% difference. The GeForce RTX 4070 is more power-efficient. Recommended PSU: 650W (GeForce RTX 4070) vs 1000W (GeForce RTX 5090 D v2). Power connectors: 8-pin vs 16-pin. Card length: 304mm vs 304mm, occupying 3 vs 2 slots. Typical load temperature: 80°C vs 70°C.

Feature	GeForce RTX 4070	GeForce RTX 5090 D v2
TDP	200W-65%	575W
Recommended PSU	650W-35%	1000W
Power Connector	8-pin	16-pin
Length	304mm	304mm
Height	137mm	137mm
Slots	3	2-33%
Temp (Load)	80°C	70°C-13%
Perf/Watt	134.6+154%	52.9

💰

Value Analysis

The GeForce RTX 4070 launched at $599 MSRP, while the GeForce RTX 5090 D v2 launched at $1999. The GeForce RTX 4070 costs 70% less ($1400 savings) on MSRP. Performance per dollar on MSRP (G3D Mark / MSRP): 44.9 (GeForce RTX 4070) vs 15.2 (GeForce RTX 5090 D v2) — the GeForce RTX 4070 offers 195.4% better value. The GeForce RTX 5090 D v2 is the newer GPU (2025 vs 2023).