Arc B580 vs GeForce RTX 3090
Aggregate performance score
We've compared GeForce RTX 3090 and Arc B580, covering specs and all relevant benchmarks.
RTX 3090 outperforms Arc B580 by an impressive 73% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 27 | 107 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 14.97 | 93.57 |
| Power efficiency | 13.66 | 14.57 |
| Architecture | Ampere (2020−2024) | Xe2 (2025) |
| GPU code name | GA102 | BMG-G21 |
| Market segment | Desktop | Desktop |
| Release date | 1 September 2020 (4 years ago) | 16 January 2025 (recently) |
| Launch price (MSRP) | $1,499 | $249 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
Arc B580 has 525% better value for money than RTX 3090.
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 | 10496 | 2560 |
| Core clock speed | 1395 MHz | 2670 MHz |
| Boost clock speed | 1695 MHz | 2670 MHz |
| Number of transistors | 28,300 million | 19,600 million |
| Manufacturing process technology | 8 nm | 5 nm |
| Power consumption (TDP) | 350 Watt | 190 Watt |
| Texture fill rate | 556.0 | 427.2 |
| Floating-point processing power | 35.58 TFLOPS | 13.67 TFLOPS |
| ROPs | 112 | 80 |
| TMUs | 328 | 160 |
| Tensor Cores | 328 | 160 |
| Ray Tracing Cores | 82 | 20 |
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 4.0 x16 | PCIe 4.0 x8 |
| Length | 336 mm | 272 mm |
| Width | 3-slot | 2-slot |
| Supplementary power connectors | 1x 12-pin | 1x 8-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 | GDDR6X | GDDR6 |
| Maximum RAM amount | 24 GB | 12 GB |
| Memory bus width | 384 Bit | 192 Bit |
| Memory clock speed | 1219 MHz | 2375 MHz |
| Memory bandwidth | 936.2 GB/s | 456.0 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 | 1x HDMI, 3x DisplayPort | 1x HDMI 2.1a, 3x DisplayPort 2.1 |
| HDMI | + | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.5 | 6.6 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.4 |
| CUDA | 8.5 | - |
| 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 | 198
+58.4%
| 125
−58.4%
|
| 1440p | 128
+82.9%
| 70
−82.9%
|
| 4K | 87
+107%
| 42
−107%
|
Cost per frame, $
| 1080p | 7.57
−280%
| 1.99
+280%
|
| 1440p | 11.71
−229%
| 3.56
+229%
|
| 4K | 17.23
−191%
| 5.93
+191%
|
- Arc B580 has 280% lower cost per frame in 1080p
- Arc B580 has 229% lower cost per frame in 1440p
- Arc B580 has 191% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 220
+53.8%
|
143
−53.8%
|
| Cyberpunk 2077 | 207
+88.2%
|
110−120
−88.2%
|
Full HD
Medium Preset
| Battlefield 5 | 102
−3.9%
|
100−110
+3.9%
|
| Counter-Strike 2 | 188
+60.7%
|
117
−60.7%
|
| Cyberpunk 2077 | 151
+77.6%
|
85−90
−77.6%
|
| Forza Horizon 4 | 505
+74.1%
|
290−300
−74.1%
|
| Forza Horizon 5 | 184
+78.6%
|
100−110
−78.6%
|
| Metro Exodus | 169
+76%
|
95−100
−76%
|
| Red Dead Redemption 2 | 130
+64.6%
|
75−80
−64.6%
|
| Valorant | 393
+144%
|
160−170
−144%
|
Full HD
High Preset
| Battlefield 5 | 110−120
+10.4%
|
100−110
−10.4%
|
| Counter-Strike 2 | 161
+54.8%
|
104
−54.8%
|
| Cyberpunk 2077 | 135
+80%
|
75−80
−80%
|
| Dota 2 | 186
+32.9%
|
140
−32.9%
|
| Far Cry 5 | 147
+113%
|
69
−113%
|
| Fortnite | 270−280
+56%
|
170−180
−56%
|
| Forza Horizon 4 | 402
+74.8%
|
230−240
−74.8%
|
| Forza Horizon 5 | 182
+76.7%
|
100−110
−76.7%
|
| Grand Theft Auto V | 171
+80%
|
95−100
−80%
|
| Metro Exodus | 150
+317%
|
36
−317%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+6.4%
|
200−210
−6.4%
|
| Red Dead Redemption 2 | 132
+67.1%
|
75−80
−67.1%
|
| The Witcher 3: Wild Hunt | 170−180
+20.8%
|
140−150
−20.8%
|
| Valorant | 222
+37.9%
|
160−170
−37.9%
|
| World of Tanks | 270−280
+0%
|
270−280
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 95
−11.6%
|
100−110
+11.6%
|
| Counter-Strike 2 | 146
+53.7%
|
95
−53.7%
|
| Cyberpunk 2077 | 121
+72.9%
|
70−75
−72.9%
|
| Dota 2 | 213
+77.5%
|
120−130
−77.5%
|
| Far Cry 5 | 130−140
+32.3%
|
95−100
−32.3%
|
| Forza Horizon 4 | 351
+75.5%
|
200−210
−75.5%
|
| Forza Horizon 5 | 159
+54.4%
|
100−110
−54.4%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+6.4%
|
200−210
−6.4%
|
| Valorant | 296
+83.9%
|
160−170
−83.9%
|
1440p
High Preset
| Counter-Strike 2 | 35−40
+34.6%
|
24−27
−34.6%
|
| Dota 2 | 150
+117%
|
69
−117%
|
| Grand Theft Auto V | 150
+76.5%
|
85−90
−76.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 160−170
+80%
|
90−95
−80%
|
| Red Dead Redemption 2 | 92
+130%
|
40−45
−130%
|
| World of Tanks | 450−500
+91%
|
250−260
−91%
|
1440p
Ultra Preset
| Battlefield 5 | 91
+23%
|
70−75
−23%
|
| Cyberpunk 2077 | 87
+74%
|
50−55
−74%
|
| Far Cry 5 | 160−170
+23.1%
|
130−140
−23.1%
|
| Forza Horizon 4 | 266
+77.3%
|
150−160
−77.3%
|
| Forza Horizon 5 | 134
+100%
|
65−70
−100%
|
| Metro Exodus | 139
+59.8%
|
85−90
−59.8%
|
| The Witcher 3: Wild Hunt | 152
+78.8%
|
85−90
−78.8%
|
| Valorant | 295
+130%
|
120−130
−130%
|
4K
High Preset
| Counter-Strike 2 | 40−45
+144%
|
18−20
−144%
|
| Dota 2 | 182
+133%
|
78
−133%
|
| Grand Theft Auto V | 182
+82%
|
100−105
−82%
|
| Metro Exodus | 76
+65.2%
|
46
−65.2%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 200−210
+59.5%
|
130−140
−59.5%
|
| Red Dead Redemption 2 | 64
+146%
|
24−27
−146%
|
| The Witcher 3: Wild Hunt | 182
+82%
|
100−105
−82%
|
4K
Ultra Preset
| Battlefield 5 | 91
+93.6%
|
45−50
−93.6%
|
| Counter-Strike 2 | 22
+57.1%
|
14
−57.1%
|
| Cyberpunk 2077 | 45
+87.5%
|
24−27
−87.5%
|
| Dota 2 | 202
+83.6%
|
110−120
−83.6%
|
| Far Cry 5 | 100−110
+75%
|
60−65
−75%
|
| Fortnite | 95−100
+65.5%
|
55−60
−65.5%
|
| Forza Horizon 4 | 159
+76.7%
|
90−95
−76.7%
|
| Forza Horizon 5 | 83
+118%
|
35−40
−118%
|
| Valorant | 188
+176%
|
65−70
−176%
|
This is how RTX 3090 and Arc B580 compete in popular games:
- RTX 3090 is 58% faster in 1080p
- RTX 3090 is 83% faster in 1440p
- RTX 3090 is 107% faster in 4K
Here's the range of performance differences observed across popular games:
- in Metro Exodus, with 1080p resolution and the High Preset, the RTX 3090 is 317% faster.
- in Battlefield 5, with 1080p resolution and the Ultra Preset, the Arc B580 is 12% faster.
All in all, in popular games:
- RTX 3090 is ahead in 42 tests (93%)
- Arc B580 is ahead in 2 tests (4%)
- there's a draw in 1 test (2%)
Pros & cons summary
| Performance score | 68.70 | 39.77 |
| Recency | 1 September 2020 | 16 January 2025 |
| Maximum RAM amount | 24 GB | 12 GB |
| Chip lithography | 8 nm | 5 nm |
| Power consumption (TDP) | 350 Watt | 190 Watt |
RTX 3090 has a 72.7% higher aggregate performance score, and a 100% higher maximum VRAM amount.
Arc B580, on the other hand, has an age advantage of 4 years, a 60% more advanced lithography process, and 84.2% lower power consumption.
The GeForce RTX 3090 is our recommended choice as it beats the Arc B580 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.
