Intel Arc Pro B65 vs GeForce RTX 5080
VS
Intel Arc Pro B65
BMG-G21
Nvidia GeForce RTX 5080
GB203-400
We compared two discrete desktop graphics cards: the Intel Arc Pro B65 32 GB with 20 pipelines and 2560 shaders against the 1 year and 3 months older GeForce RTX 5080 16 GB that utilizes 84 pipelines and 10752 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Please note that the tests on the Intel Arc Pro B65 are done on an engineering sample provided by our insiders. The data will be more accurate after the final version of this GPU is available.
Key differences
Reasons to consider the Intel Arc Pro B65
- Includes 16 GB more video memory
Reasons to consider the GeForce RTX 5080
- 4.6x higher maximum theoretical performance (56.3 vs 12.3 TFLOPS)
- Manufactured using a more efficient 4 nm process technology
- Supports Nvidia DLSS 4 technology
- Has 4.2x more shading units (10752 vs 2560)
- Features 176 more tensor cores for effective ML and AI workloads
- Has 58% higher memory bandwidth: 960 vs 608 GB/s
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | - | 250 186 179 138 |
| The Witcher 3 | - | 271 244 172 90 |
| Counter-Strike 2 | - | 317 238 178 87 |
| Far Cry 6 | - | 194 171 155 97 |
| Hogwarts Legacy | - | 185 152 124 67 |
| CoD: Modern Warfare III | - | 250 244 197 135 |
| Ghost of Tsushima | - | 166 142 126 82 |
| Cyberpunk 2077 | - | 213 192 138 61 |
| Shadow of the Tomb Raider | - | 306 276 214 111 |
| 1080p High | - | 239 |
| 1080p Ultra | - | 205 |
| 1440p Ultra | - | 165 |
| 4K Ultra | - | 96 |
| Margin of Error | High | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | - | 33000 |
| Solar Bay | - | 161489 |
| Port Royal | - | 23275 |
| Fire Strike | - | 75605 |
| Wild Life Extreme | - | 69617 |
| Night Raid | - | 199650 |
GeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | - | 319.6 img/sec |
| Face Detection | - | 225 img/sec |
| Horizon Detection | - | 13.6 Gpixels/sec |
| Edge Detection | - | 19.5 Gpixels/sec |
| Gaussian Blur | - | 20.4 Gpixels/sec |
| Feature Matching | - | 2.33 Gpixels/sec |
| Stereo Matching | - | 1750 Gpixels/sec |
| Particle Physics | - | 43676.6 FPS |
| API | - | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | - | 1397 |
| DirectX 11 | - | 327 FPS |
| DirectX 12 | - | 144 FPS |
| GPU Compute | - | 19057 Ops/s |
Recent User Tests
Intel Arc Pro B65
No benchmark results yet
GeForce RTX 5080
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-06-01 (Nowh) | Cinebench 2024 | 95861 |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | - | 15441 |
| Image Segmentation (HP) | - | 47173 |
| Image Super Resolution (Q) | - | 43223 |
| Face Detection (HP) | - | 92863 |
| Pose Estimation (Q) | - | 202202 |
| Text Classification (SP) | - | 3701 |
| Machine Translation (HP) | - | 7905 |
| Object Detection (SP) | - | 20955 |
| Depth Estimation (Q) | - | 69068 |
| Style Transfer (SP) | - | 349205 |
| Framework | - | ONNX |
| Backend | - | DirectML |
Specifications
Technical specifications of Intel Arc Pro B65 and GeForce RTX 5080General
| Vendor | Intel | Nvidia |
| Build | Discrete | Discrete |
| Released | March 25, 2026 | January 7, 2025 |
| Launch price (MSRP) | - | $999 |
| Case | Desktop | Desktop |
| Purpose | Professional | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Battlemage Pro Series | Blackwell 2.0 |
| GPU Codename | BMG-G21 | GB203-400 |
| Recommended CPU | - | - Intel Core Ultra 7 265K or above |
Desktop GPU rating (#4th place)
Graphics Processing Unit
| Base Clock | 2000 MHz | 2295 MHz |
| Boost Clock | 2400 MHz | 2617 MHz |
| Shading Units | 2560 | 10752 |
| Texture Mapping Units (TMUs) | 160 | 336 |
| Render Output Units (ROPs) | 80 | 112 |
| Compute Units (Pipelines) | 20 | 84 |
| Tensor Cores | 160 | 336 |
| Ray-tracing Cores | 20 | 84 |
| L1 Cache | 256KB per cluster | 128KB per cluster |
| L2 Cache | 10MB shared | 64MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 192 GPixel/s | 293 GPixel/s |
| Texture Fill Rate | 384 GTexel/s | 879 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| TGP | 200 W | 360 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 4 nm |
| Die Size | 271.95 mm² | 378 mm² |
| Transistor Count | 19.6 billion | 45.6 billion |
| Transistor Density | 72.07 MTr/mm² | 120.63 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR7 |
| Memory Size | 32 GB | 16 GB |
| Memory Clock | 2375 MHz | 1875 MHz |
| Effective Memory Speed | 19000 Mbps | 30000 Mbps |
| Bus | 256-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | No | 12.0 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 4 |
| DisplayPort | 2.1a | 2.1b |
Cast your vote
Total votes: < 1