Black Desert Online · 1440p Remastered · 25 cards, identical settings · Updated July 2026
We benchmark Black Desert Online at 1440p Remastered with ray tracing off, frame generation off and upscaling off, logging the average, the 1% low, frametime, VRAM used, board power and temperature. 7 of the 98 cards below were measured first-party on our Ryzen 7 7800X3D test bench; the rest are anchored estimates placed against those runs, and every row is labelled so you always know which is which. 76 clear 60 FPS, 44 clear 100, 25 clear 144.

282 FPS average, 180 FPS 1% low at 1440p Remastered. Anchored estimate. 5.29GB of VRAM used, 546W board power, 70°C. $1,999 MSRP.
Best for: 1440p Remastered at high refresh.

235 FPS average, 150 FPS 1% low at 1440p Remastered. Anchored estimate. 5.29GB of VRAM used, 428W board power, 66°C. $1,599 MSRP.
Best for: 1440p Remastered at high refresh.

219 FPS average, 140 FPS 1% low at 1440p Remastered. Anchored estimate. 5.29GB of VRAM used, 342W board power, 66°C. $999 MSRP.
Best for: 1440p Remastered at high refresh.
Black Desert Remastered is an MMO, which means the number that matters isn't the average. It's what happens when fifty players render at once and everything falls apart. BDO Remastered is heavy on shading and unusually spiky. The averages here look comfortable across most of the ladder; the 1% lows are where you learn which cards actually hold up in a crowded node.
Black Desert Online at 1440p Remastered, average FPS, fastest 12
60 FPS
Identical settings on every card: 1440p, ray tracing off, frame generation off, upscaling off, Ryzen 7 7800X3D. Rows marked (est.) are anchored estimates, not measurements. Averages only: the 1% lows are below, and they tell a different story.
The number nobody publishes, 1% lows next to averages
The 1% low is what a stutter feels like. Two cards with the same average can play completely differently, and the gap between these two bars is the whole reason we log both. Tap a series to isolate it.
Full leaderboard, Black Desert Online, 1440p Remastered
| GPU | Avg FPS | 1% low | Frametime | VRAM used | Power | Temp | Data |
|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 | 282 | 180 | 3.5 ms | 5.29 GB | 546W | 70°C | Estimated |
| NVIDIA GeForce RTX 4090 | 235 | 150 | 4.3 ms | 5.29 GB | 428W | 66°C | Estimated |
| GeForce RTX 5080 | 219 | 140 | 4.6 ms | 5.29 GB | 342W | 66°C | Estimated |
| AMD Radeon RX 7900 XTX | 198 | 127 | 5.1 ms | 5.29 GB | 337W | 66°C | Estimated |
| GeForce RTX 4080 Super | 198 | 127 | 5.1 ms | 5.29 GB | 304W | 63°C | Estimated |
| AMD Radeon RX 9070 XT | 196 | 114 | 4.8 ms | 6.4 GB | 330W | 57°C | Measured |
| GeForce RTX 5070 Ti | 194 | 93 | 5.7 ms | 5.59 GB | 262W | 58°C | Measured |
| NVIDIA GeForce RTX 4080 | 193 | 123 | 5.2 ms | 5.29 GB | 304W | 63°C | Estimated |
| NVIDIA GeForce RTX 5090 (Laptop) | 180 | 115 | 5.6 ms | 5.29 GB | 150W | n/a | Estimated |
| NVIDIA GeForce RTX 3090 Ti | 178 | 114 | 5.6 ms | 5.29 GB | 428W | 76°C | Estimated |
| AMD Radeon RX 7900 XT | 172 | 110 | 5.8 ms | 5.29 GB | 285W | 65°C | Estimated |
| NVIDIA GeForce RTX 5080 (Laptop) | 169 | 108 | 5.9 ms | 5.29 GB | 150W | n/a | Estimated |
| AMD Radeon RX 9070 | 167 | 108 | 5.3 ms | 6.07 GB | 220W | 52°C | Measured |
| GeForce RTX 4090 Laptop | 167 | 107 | 6.0 ms | 5.29 GB | 166W | 80°C | Estimated |
| NVIDIA GeForce RTX 3090 | 165 | 105 | 6.1 ms | 5.29 GB | 332W | 73°C | Estimated |
| NVIDIA GeForce RTX 4070 Ti Super | 165 | 78 | 6.1 ms | 4.59 GB | 279W | 57°C | Estimated |
| NVIDIA GeForce RTX 3080 Ti | 162 | 104 | 6.2 ms | 5.29 GB | 332W | 74°C | Estimated |
| GeForce RTX 5070 | 158 | 74 | 5.7 ms | 5.36 GB | 236W | 72°C | Measured |
| AMD Radeon RX 6950 XT | 155 | 99 | 6.5 ms | 5.29 GB | 318W | 66°C | Estimated |
| AMD Radeon RX 7900 GRE | 155 | 105 | 6.5 ms | 5.56 GB | 299W | 55°C | Estimated |
| NVIDIA GeForce RTX 4070 Ti | 154 | 77 | 6.5 ms | 4.81 GB | 239W | 59°C | Estimated |
| NVIDIA GeForce RTX 4080 Laptop GPU | 154 | 98 | 6.5 ms | 5.29 GB | 142W | 78°C | Estimated |
| NVIDIA GeForce RTX 3080 12GB | 153 | 98 | 6.5 ms | 5.29 GB | 332W | 73°C | Estimated |
| AMD Radeon RX 6900 XT | 145 | 93 | 6.9 ms | 5.29 GB | 285W | 65°C | Estimated |
| NVIDIA GeForce RTX 4070 Super | 145 | 84 | 6.9 ms | 4.91 GB | 200W | 65°C | Estimated |
| NVIDIA GeForce RTX 5070 Ti (Laptop) | 142 | 90 | 7.0 ms | 5.29 GB | 115W | n/a | Estimated |
| AMD Radeon RX 7800 XT | 140 | 100 | 7.1 ms | 5.16 GB | 267W | 59°C | Estimated |
| AMD Radeon RX 7900M | 139 | 88 | 7.2 ms | 5.29 GB | 180W | n/a | Estimated |
| AMD Radeon RX 9070 GRE | 136 | 87 | 7.4 ms | 5.29 GB | 173W | 63°C | Estimated |
| NVIDIA GeForce RTX 3070 Ti | 135 | 86 | 7.4 ms | 5.29 GB | 276W | 70°C | Estimated |
| NVIDIA Titan RTX | 128 | 82 | 7.8 ms | 5.29 GB | 266W | 74°C | Estimated |
| NVIDIA GeForce RTX 3080 Ti (Laptop) | 125 | 80 | 8.0 ms | 5.29 GB | 166W | 80°C | Estimated |
| NVIDIA GeForce RTX 4070 | 125 | 91 | 8.0 ms | 4.77 GB | 209W | 57°C | Estimated |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | 123 | 79 | 8.1 ms | 5.29 GB | 238W | 68°C | Estimated |
| GeForce RTX 5060 Ti | 121 | 92 | 7.9 ms | 5.29 GB | 164W | 67°C | Measured |
| AMD Radeon RX 7700 XT | 112 | 89 | 8.9 ms | 5.82 GB | 258W | 60°C | Estimated |
| NVIDIA GeForce RTX 4060 Ti | 112 | 72 | 8.9 ms | 5.29 GB | 152W | 58°C | Estimated |
| NVIDIA GeForce RTX 5070 (Laptop) | 109 | 69 | 9.2 ms | 5.29 GB | 100W | n/a | Estimated |
| AMD Radeon RX 9060 XT | 108 | 87 | 8.1 ms | 5.97 GB | 181W | 53°C | Measured |
| NVIDIA GeForce RTX 2080 Super | 108 | 69 | 9.3 ms | 5.29 GB | 238W | 67°C | Estimated |
| NVIDIA GeForce RTX 5060 | 103 | 81 | 9.3 ms | 5.28 GB | 145W | 69°C | Measured |
| NVIDIA GeForce RTX 2080 Founders Edition | 102 | 65 | 9.8 ms | 5.29 GB | 204W | 68°C | Estimated |
| NVIDIA GeForce RTX 3070 Ti (Laptop) | 100 | 64 | 10.0 ms | 5.29 GB | 142W | 77°C | Estimated |
| NVIDIA TITAN V | 100 | 64 | 10.0 ms | 5.29 GB | 238W | 72°C | Estimated |
| GeForce RTX 4070 Laptop | 99 | 63 | 10.1 ms | 5.29 GB | 133W | 75°C | Estimated |
| GeForce RTX 4060 | 97 | 62 | 10.3 ms | 5.29 GB | 109W | 56°C | Estimated |
| AMD Radeon RX 9060 | 94 | 60 | 10.6 ms | 5.29 GB | 125W | 60°C | Estimated |
| NVIDIA GeForce RTX 2070 SUPER | 94 | 60 | 10.6 ms | 5.29 GB | 204W | 67°C | Estimated |
| AMD Radeon RX 6800M | 90 | 57 | 11.1 ms | 5.29 GB | 165W | n/a | Estimated |
| NVIDIA GeForce RTX 3070 (Laptop) | 88 | 56 | 11.4 ms | 5.29 GB | 133W | 75°C | Estimated |
| NVIDIA GeForce RTX 3080 (Laptop) | 86 | 55 | 11.6 ms | 5.29 GB | 157W | 78°C | Estimated |
| NVIDIA GeForce RTX 3060 | 85 | 54 | 11.8 ms | 5.29 GB | 162W | 62°C | Estimated |
| NVIDIA GeForce RTX 2070 | 82 | 52 | 12.2 ms | 5.29 GB | 166W | 65°C | Estimated |
| NVIDIA GeForce RTX 4060 Laptop | 81 | 52 | 12.3 ms | 5.29 GB | 109W | 73°C | Estimated |
| AMD Radeon RX 6700M | 80 | 52 | 12.5 ms | 5.29 GB | 135W | n/a | Estimated |
| AMD Radeon RX 7600 XT | 79 | 64 | 12.7 ms | 5.01 GB | 203W | 60°C | Estimated |
| AMD Radeon RX 7600M XT | 79 | 51 | 12.7 ms | 5.29 GB | 120W | n/a | Estimated |
| Intel Arc B580 | 78 | 50 | 12.8 ms | 5.29 GB | 180W | 66°C | Estimated |
| AMD Radeon RX 7700S | 77 | 49 | 13.0 ms | 5.29 GB | 100W | n/a | Estimated |
| NVIDIA GeForce RTX 2060 Super | 77 | 49 | 13.0 ms | 5.29 GB | 166W | 65°C | Estimated |
| NVIDIA GeForce RTX 5050 | 77 | 49 | 13.0 ms | 5.29 GB | 124W | 58°C | Estimated |
| NVIDIA GeForce RTX 2080 (Mobile) | 76 | 49 | 13.2 ms | 5.29 GB | 150W | n/a | Estimated |
| NVIDIA GeForce RTX 3060 Laptop GPU | 76 | 49 | 13.2 ms | 5.29 GB | 109W | 75°C | Estimated |
| AMD Radeon RX 6600M | 72 | 46 | 13.9 ms | 5.29 GB | 100W | n/a | Estimated |
| AMD Radeon RX 7600 | 72 | 46 | 13.9 ms | 5.29 GB | 157W | 62°C | Estimated |
| NVIDIA GeForce RTX 5060 (Laptop) | 71 | 45 | 14.1 ms | 5.29 GB | 100W | n/a | Estimated |
| Intel Arc A770 Limited Edition | 71 | 45 | 14.1 ms | 5.29 GB | 214W | 68°C | Estimated |
| NVIDIA TITAN Xp | 71 | 45 | 14.1 ms | 5.29 GB | 238W | 72°C | Estimated |
| NVIDIA GeForce RTX 2060 | 70 | 45 | 14.3 ms | 5.29 GB | 152W | 64°C | Estimated |
| NVIDIA GeForce RTX 5050 (Laptop) | 69 | 44 | 14.5 ms | 5.29 GB | 100W | n/a | Estimated |
| GeForce GTX 1080 Ti | 68 | 43 | 14.7 ms | 5.29 GB | 238W | 72°C | Estimated |
| Intel Arc B570 | 68 | 43 | 14.7 ms | 5.29 GB | 142W | 64°C | Estimated |
| NVIDIA TITAN X (Pascal) | 67 | 43 | 14.9 ms | 5.29 GB | 238W | 72°C | Estimated |
| NVIDIA GeForce RTX 2070 (Mobile) | 65 | 42 | 15.4 ms | 5.29 GB | 115W | n/a | Estimated |
| Intel Arc A750 | 65 | 42 | 15.4 ms | 5.29 GB | 214W | 68°C | Estimated |
| NVIDIA GeForce RTX 4050 (Laptop) | 60 | 38 | 16.7 ms | 5.29 GB | 109W | 72°C | Estimated |
| NVIDIA GeForce RTX 3050 | 59 | 38 | 16.9 ms | 5.29 GB | 124W | 60°C | Estimated |
| NVIDIA GeForce RTX 2060 (Mobile) | 55 | 35 | 18.2 ms | 5.29 GB | 115W | n/a | Estimated |
| Intel Arc A580 | 55 | 35 | 18.2 ms | 5.29 GB | 176W | 66°C | Estimated |
| NVIDIA GeForce GTX 1080 | 53 | 34 | 18.9 ms | 5.29 GB | 171W | 68°C | Estimated |
| NVIDIA GeForce GTX 1070 Ti | 50 | 32 | 20.0 ms | 5.29 GB | 171W | 67°C | Estimated |
| NVIDIA GeForce RTX 3050 Ti (Laptop) | 50 | 32 | 20.0 ms | 3.68 GB | 76W | 72°C | Estimated |
| AMD Radeon RX 6500 XT | 48 | 31 | 20.8 ms | 3.68 GB | 102W | 62°C | Estimated |
| NVIDIA GeForce GTX 1070 | 43 | 27 | 23.3 ms | 5.29 GB | 142W | 65°C | Estimated |
| NVIDIA GeForce RTX 3050 (Laptop) | 43 | 27 | 23.3 ms | 3.68 GB | 76W | 70°C | Estimated |
| NVIDIA GeForce GTX 980 Ti | 41 | 26 | 24.4 ms | 5.29 GB | 238W | 72°C | Estimated |
| NVIDIA GeForce GTX 1660 Ti (Mobile) | 37 | 24 | 27.0 ms | 3.68 GB | 80W | n/a | Estimated |
| AMD Radeon RX 6400 | 36 | 23 | 27.8 ms | 3.68 GB | 50W | 60°C | Estimated |
| NVIDIA GeForce GTX 1650 Super | 34 | 22 | 29.4 ms | 3.68 GB | 95W | 62°C | Estimated |
| NVIDIA GeForce GTX 980 | 34 | 22 | 29.4 ms | 3.68 GB | 157W | 68°C | Estimated |
| NVIDIA GeForce GTX 1060 6GB | 32 | 20 | 31.2 ms | 5.29 GB | 114W | 63°C | Estimated |
| Intel Arc A380 | 31 | 20 | 32.3 ms | 5.29 GB | 71W | 62°C | Estimated |
| NVIDIA GeForce GTX 1650 Ti (Mobile) | 29 | 18 | 34.5 ms | 3.68 GB | 55W | n/a | Estimated |
| NVIDIA GeForce GTX 970 | 29 | 19 | 34.5 ms | 3.22 GB | 138W | 66°C | Estimated |
| NVIDIA GeForce GTX 1650 | 26 | 17 | 38.5 ms | 3.68 GB | 71W | 60°C | Estimated |
| NVIDIA GeForce GTX 780 Ti | 25 | 16 | 40.0 ms | 2.76 GB | 238W | 74°C | Estimated |
| NVIDIA GeForce GTX 1650 (Mobile) | 21 | 13 | 47.6 ms | 3.68 GB | 50W | n/a | Estimated |
| GeForce GTX 1050 Ti | 20 | 13 | 50.0 ms | 3.68 GB | 71W | 60°C | Estimated |
Tap any column to sort. Every card ran identical settings. That's the only way a comparison means anything.
One thing worth reading off the table rather than the chart: VRAM used. Black Desert Online peaks at about 5.59GB here, which means an 8GB card has headroom in this title even though it will drown in a modern AI workload. VRAM panic is real and mostly misplaced: the games that genuinely need more than 8GB at 1440p are rarer than the discourse suggests, and the number in that column is measured under the same conditions as everything else on this page. The bigger point: buy for the 1% low, not the average. Every card above 60 in that table is playable. The ones worth your money are the ones whose second column doesn't collapse.
NVIDIA GeForce RTX 5090 tops the chart at 282 FPS average and 180 1% low at 1440p Remastered. The more useful number is that 76 of 98 cards clear 60 FPS, and the cheapest that does is the Intel Arc B570 at $219. Black Desert Online uses about 6.4GB of VRAM here, so capacity isn't what's limiting you. Shading power is. Buy on the 1% low column, not the average: that's the one you feel. 7 of these cards were measured on our bench; the rest are labelled estimates.
Every figure here is 1440p, on the preset named on the page, with ray tracing off, frame generation off and upscaling off, because a comparison is only meaningful if every card ran the identical workload. Test CPU is an R7 7800X3D. We publish the average frame rate, the 1% low, frametime, VRAM used, board power and peak temperature for every card in every game. The 1% low is the number that decides whether a game feels smooth; the average is the number everyone quotes. We show both, side by side, on purpose. Our gaming figures come from a 9-game core suite run at identical settings across the fleet, anchored to first-party runs on 29 reference cards and interpolated across the rest using a per-game anchor ladder. We do not re-estimate a card we have run ourselves. What we deliberately don't do: mix presets, mix resolutions, enable upscaling on some cards and not others, or quote a number from a different reviewer's methodology. Those are the four ways GPU benchmarks usually become incomparable. Frame rates depend on your CPU, your RAM, your drivers, your resolution and the specific scene being rendered. Treat these as a ranking of cards against each other under controlled conditions, not a promise about your machine.