Arc B390 vs Radeon AI PRO R9700
Aggregate performance score
We've compared Radeon AI PRO R9700 with Arc B390, including specs and performance data.
AI PRO R9700 outperforms B390 by a whopping 203% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 29 | 299 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 28.17 | no data |
| Power efficiency | 16.90 | 20.93 |
| Architecture | RDNA 4.0 (2025) | Xe3-LPG (2026) |
| GPU code name | Navi 48 | Panther Lake |
| Market segment | Workstation | Laptop |
| Release date | 23 July 2025 (less than a year ago) | 27 January 2026 (less than a year ago) |
| Launch price (MSRP) | $1,299 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Currently popular graphics cards are shown for comparison.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 4096 | 1536 |
| Core clock speed | 1660 MHz | 300 MHz |
| Boost clock speed | 2920 MHz | 2500 MHz |
| Number of transistors | 53,900 million | no data |
| Manufacturing process technology | 4 nm | 3 nm |
| Power consumption (TDP) | 300 Watt | 80 Watt |
| Texture fill rate | 747.5 | 120.0 |
| Floating-point processing power | 47.84 TFLOPS | 7.68 TFLOPS |
| ROPs | 128 | 24 |
| TMUs | 256 | 48 |
| Tensor Cores | 128 | no data |
| Ray Tracing Cores | 64 | 12 |
| L0 Cache | 1 MB | no data |
| L1 Cache | no data | 768 KB |
| L2 Cache | 8 MB | 16 MB |
| L3 Cache | 64 MB | no data |
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 5.0 x16 | IGP |
| Length | 267 mm | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 1x 16-pin | None |
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 | GDDR6 | System Shared |
| Maximum RAM amount | 32 GB | System Shared |
| Memory bus width | 256 Bit | System Shared |
| Memory clock speed | 2518 MHz | System Shared |
| Memory bandwidth | 644.6 GB/s | no data |
| Shared memory | - | + |
| Resizable BAR | + | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x HDMI 2.1b, 3x DisplayPort 2.1a | Portable Device Dependent |
| HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.8 | 6.9 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 3.0 |
| Vulkan | 1.3 | 1.4 |
| DLSS | + | - |
Synthetic benchmarks
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 | 170−180
+198%
| 57
−198%
|
| 1440p | 100−110
+178%
| 36
−178%
|
| 4K | 75−80
+200%
| 25
−200%
|
Cost per frame, $
| 1080p | 7.64 | no data |
| 1440p | 12.99 | no data |
| 4K | 17.32 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 120−130
+0%
|
120−130
+0%
|
| Cyberpunk 2077 | 45−50
+0%
|
45−50
+0%
|
| Resident Evil 4 Remake | 50−55
+0%
|
50−55
+0%
|
Full HD
Medium
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Counter-Strike 2 | 120−130
+0%
|
120−130
+0%
|
| Cyberpunk 2077 | 45−50
+0%
|
45−50
+0%
|
| Far Cry 5 | 87
+0%
|
87
+0%
|
| Fortnite | 110−120
+0%
|
110−120
+0%
|
| Forza Horizon 4 | 85−90
+0%
|
85−90
+0%
|
| Forza Horizon 5 | 65−70
+0%
|
65−70
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+0%
|
85−90
+0%
|
| Valorant | 150−160
+0%
|
150−160
+0%
|
Full HD
High
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Counter-Strike 2 | 27
+0%
|
27
+0%
|
| Counter-Strike: Global Offensive | 240−250
+0%
|
240−250
+0%
|
| Cyberpunk 2077 | 45−50
+0%
|
45−50
+0%
|
| Far Cry 5 | 79
+0%
|
79
+0%
|
| Fortnite | 110−120
+0%
|
110−120
+0%
|
| Forza Horizon 4 | 85−90
+0%
|
85−90
+0%
|
| Forza Horizon 5 | 88
+0%
|
88
+0%
|
| Grand Theft Auto V | 72
+0%
|
72
+0%
|
| Metro Exodus | 45−50
+0%
|
45−50
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+0%
|
85−90
+0%
|
| The Witcher 3: Wild Hunt | 107
+0%
|
107
+0%
|
| Valorant | 149
+0%
|
149
+0%
|
Full HD
Ultra
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Cyberpunk 2077 | 45−50
+0%
|
45−50
+0%
|
| Far Cry 5 | 73
+0%
|
73
+0%
|
| Forza Horizon 4 | 85−90
+0%
|
85−90
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+0%
|
85−90
+0%
|
| The Witcher 3: Wild Hunt | 47
+0%
|
47
+0%
|
Full HD
Epic
| Fortnite | 110−120
+0%
|
110−120
+0%
|
1440p
High
| Counter-Strike 2 | 41
+0%
|
41
+0%
|
| Counter-Strike: Global Offensive | 150−160
+0%
|
150−160
+0%
|
| Grand Theft Auto V | 31
+0%
|
31
+0%
|
| Metro Exodus | 27−30
+0%
|
27−30
+0%
|
| Valorant | 96
+0%
|
96
+0%
|
1440p
Ultra
| Battlefield 5 | 60−65
+0%
|
60−65
+0%
|
| Cyberpunk 2077 | 21−24
+0%
|
21−24
+0%
|
| Far Cry 5 | 53
+0%
|
53
+0%
|
| Forza Horizon 4 | 55−60
+0%
|
55−60
+0%
|
| The Witcher 3: Wild Hunt | 30−35
+0%
|
30−35
+0%
|
1440p
Epic
| Fortnite | 50−55
+0%
|
50−55
+0%
|
4K
High
| Counter-Strike 2 | 18
+0%
|
18
+0%
|
| Grand Theft Auto V | 40−45
+0%
|
40−45
+0%
|
| Metro Exodus | 18−20
+0%
|
18−20
+0%
|
| The Witcher 3: Wild Hunt | 30−35
+0%
|
30−35
+0%
|
| Valorant | 45
+0%
|
45
+0%
|
4K
Ultra
| Battlefield 5 | 30−35
+0%
|
30−35
+0%
|
| Cyberpunk 2077 | 9−10
+0%
|
9−10
+0%
|
| Far Cry 5 | 24−27
+0%
|
24−27
+0%
|
| Forza Horizon 4 | 35−40
+0%
|
35−40
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 21−24
+0%
|
21−24
+0%
|
4K
Epic
| Fortnite | 21−24
+0%
|
21−24
+0%
|
This is how AI PRO R9700 and Arc B390 compete in popular games:
- AI PRO R9700 is 198% faster in 1080p
- AI PRO R9700 is 178% faster in 1440p
- AI PRO R9700 is 200% faster in 4K
All in all, in popular games:
- there's a draw in 54 tests (100%)
Pros & cons summary
| Performance score | 65.86 | 21.76 |
| Recency | 23 July 2025 | 27 January 2026 |
| Chip lithography | 4 nm | 3 nm |
| Power consumption (TDP) | 300 Watt | 80 Watt |
AI PRO R9700 has a 203% higher aggregate performance score.
Arc B390, on the other hand, has an age advantage of 6 months, a 33% more advanced lithography process, and 275% lower power consumption.
The Radeon AI PRO R9700 is our recommended choice as it beats the Arc B390 in performance tests.
Be aware that Radeon AI PRO R9700 is a workstation graphics card while Arc B390 is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
