140 FPS at 1440p across 15 games (first-party measured) · smooth 100+ FPS 1440p gaming across demanding AAA titles
140 Avg FPS ✓ Measured
Measured, not modelled. All 15 games were run on our own bench, and every run has a screenshot behind it. Across our 15-game suite at 1440p, GeForce RTX 5070 Ti averages 140 FPS. The ceiling is Counter-Strike 2 at 281 FPS; the floor is Clair Obscur: Expedition 33 at 60 FPS, a 4.7x spread that tells you how engine-dependent this class of card is. In practical terms that means smooth 100+ FPS 1440p gaming across demanding AAA titles. Under load we logged a peak of 300W against the 300W rating.
Fast card, one caveat from my logs: Call of Duty MW3's 1% low was 45% of its average, the worst pacing ratio I recorded on it. Tarkov used 15.35GB, so the 16GB earns its keep. These gaming numbers came off my own test bench: a Ryzen 7 7800X3D system, identical settings on every card, with a capture kept for every run. Everything here was double-checked before it went up.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Alan Wake 2 1440p · High | 97 FPS | 80 | 9.62 GB | 265 W | ✓ Measured |
| Baldur's Gate 3 1440p · Ultra | 199 FPS | 161 | 7 GB | 299 W | ✓ Measured |
| Black Desert Online 1440p · Remastered | 194 FPS | 93 | 5.59 GB | 262 W | ✓ Measured |
| Black Myth: Wukong 1440p · Very High | 90 FPS | 68 | 7.38 GB | 249 W | ✓ Measured |
| Call of Duty: MW3 1440p · Extreme | 154 FPS | 70 | 14.61 GB | 247 W | ✓ Measured |
| Clair Obscur: Expedition 33 1440p · Epic | 60 FPS | 49 | 8.06 GB | 232 W | ✓ Measured |
| Counter-Strike 2 1440p · Very High | 281 FPS | 154 | 7.14 GB | 241 W | ✓ Measured |
| Cyberpunk 2077 1440p · Ultra | 127 FPS | 91 | 6.69 GB | 300 W | ✓ Measured |
| Diablo 4 1440p · Ultra | 168 FPS | 120 | 13.84 GB | 270 W | ✓ Measured |
| Escape from Tarkov 1440p · Ultra | 168 FPS | 106 | 15.35 GB | 256 W | ✓ Measured |
| Marvel Rivals 1440p · Ultra | 86 FPS | 48 | 8.63 GB | 256 W | ✓ Measured |
| Monster Hunter Wilds 1440p · Ultra | 85 FPS | 53 | 12.17 GB | 229 W | ✓ Measured |
| Red Dead Redemption 2 1440p · Favor Quality | 133 FPS | 99 | 6.26 GB | 260 W | ✓ Measured |
| The Last of Us Part II 1440p · Very High | 123 FPS | 92 | 9.05 GB | 256 W | ✓ Measured |
| The Witcher 3 1440p · Ultra | 138 FPS | 95 | 7.42 GB | 295 W | ✓ Measured |
| Architecture | Blackwell |
| CUDA cores | 8,960 |
| VRAM | 16GB GDDR7 |
| Memory bus | 256-bit |
| Memory bandwidth | 896 GB/s |
| Boost clock | 2,452 MHz |
| TDP | 300 W |
| Process | 4nm |
| Interface | PCIe 5.0 x16 |
| Release date | 2025-02-20 |
| Launch MSRP | $749 |
GeForce RTX 5070 Ti averages 140 FPS at 1440p on our suite. Measured, not modelled. All 15 games were run on our own bench, and every run has a screenshot behind it.
100% = this card, Gaming headline metric (Avg FPS). #10 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| AMD Radeon RX 7900 XTX | 117% | 164 | |
| AMD Radeon RX 7900 XT | 105% | 147 | |
| NVIDIA GeForce RTX 3090 Ti | 102% | 143 | |
| NVIDIA GeForce RTX 4070 Ti Super | 102% | 143 | |
| GeForce RTX 5070 Ti | 100% | 140 | |
| AMD Radeon RX 9070 XT | 98% | 137 | |
| NVIDIA GeForce RTX 4070 Ti | 97% | 136 | |
| AMD Radeon RX 6950 XT | 94% | 132 | |
| NVIDIA GeForce RTX 3090 | 94% | 132 |
Same card, other workloads: GeForce RTX 5070 Ti AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 45,600 million |
| Die size | 378 mm² |
| Process node | 4 nm |
| Fabricated by | TSMC |
| Transistor density | 120.6 million per mm² |
Denser than 92% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| Full codebase review | 12 min | 44.78 Wh | measured |
| Animate a batch of images | 26.1 min | 79.16 Wh | measured |
Can't run: Product photo shoot (needs FLUX.1 Kontext dev), Photo restoration batch (needs FLUX.1 Kontext dev), Restore and enlarge photos (needs FLUX.1 Kontext dev), Character sheet, 12 poses (needs FLUX.1 dev), Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B).
This card is $749 to buy. The cheapest listed rate on Vast.ai is $0.149/hour, but that is the floor: we budget $0.179/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 4,189 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $131 | 5.7 years |
| 8 hours a day, working on it | 2,920 | $522 | 1.4 years |
| 24/7, always-on agent | 8,760 | $1,566 | 5.7 months |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.