Intel Arc Pro B65 vs NVIDIA GeForce RTX 5080 SUPER Comparison

Where Each One Wins

The benchmark data splits these two cards into completely different use cases. The Intel Arc Pro B65 is a workstation-oriented GPU with a 50th percentile ranking among all GPUs in the database, meaning it sits right in the middle of the performance distribution. The NVIDIA GeForce RTX 5080 SUPER, in contrast, records a 19th percentile ranking, which places it in the lower portion of the database's performance rankings based on the single recorded 3DMark Steel Nomad DX12 test. That percentile figure, however, requires context: the RTX 5080 SUPER's score of 3075 in that specific test is nearly identical to the scores of several much older or lower-tier cards, including the NVIDIA Quadro P1000 (3163, 2.8% faster), the Intel Arc Pro B60 (3182, 3.4% faster), the NVIDIA GeForce 820A (2983, 3.1% slower), and the NVIDIA GeForce GTX 860M (2967, 3.6% slower).

The Arc Pro B65 wins in memory capacity and power efficiency. It packs 32 GB of GDDR6 memory versus the RTX 5080 SUPER's 24 GB of GDDR7, and it draws 200 W versus 415 W. The Arc Pro B65 also boosts at a flat 2400 MHz with no variance between base and boost, whereas the RTX 5080 SUPER runs at 2295 MHz base and 2617 MHz boost. For workloads that need large memory footprints, such as massive datasets or rendering scenes that exceed 24 GB, the Arc Pro B65 holds the advantage. For raw compute throughput, the RTX 5080 SUPER dominates with 56.28 TFLOPS FP32 against 12.29 TFLOPS, and it matches that figure in FP16 at 56.28 TFLOPS (1:1) versus the Arc Pro B65's 24.58 TFLOPS (2:1).

The RTX 5080 SUPER wins on memory bandwidth by a wide margin: 1.02 TB/s versus 608.0 GB/s. It also has significantly more shading units (10752 versus 2560), texture mapping units (336 versus 160), render output units (112 versus 80), ray tracing cores (84 versus 20), and tensor cores (336 versus none listed for the Arc Pro B65). The Arc Pro B65 counters with a smaller die (272 mm² versus 378 mm²), fewer transistors (19,600 million versus 45,600 million), and a lower transistor density (72.1M / mm² versus 120.6M / mm²), which reflects its simpler architecture and lower power target.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc Pro B65 uses the Xe2-HPG architecture, built on the BMG-G21 chip, and belongs to the Battlemage (Pro Series) generation. The NVIDIA GeForce RTX 5080 SUPER uses Blackwell 2.0, built on the GB203 chip, and belongs to the GeForce 50-series. Both are manufactured by TSMC on a 5 nm process, so the process node itself is identical, but the transistor budgets diverge sharply. The RTX 5080 SUPER packs 45,600 million transistors into a 378 mm² die, yielding 120.6M transistors per square millimeter. The Arc Pro B65 fits 19,600 million transistors into a 272 mm² die, yielding 72.1M per square millimeter. That density gap explains why the NVIDIA part can field 10752 shading units, 336 TMUs, 112 ROPs, 84 RT cores, and 336 tensor cores, while the Intel part manages 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores with no tensor core count listed.

Memory architecture also differs fundamentally. The Arc Pro B65 uses GDDR6 with a 256-bit bus and 608.0 GB/s bandwidth, while the RTX 5080 SUPER uses GDDR7 with the same 256-bit bus but 1.02 TB/s bandwidth. The NVIDIA card's memory runs at 2000 MHz with 32 Gbps effective speed, while the Intel card runs at 2375 MHz with 19 Gbps effective speed. The higher effective speed per pin on GDDR7 is what allows the NVIDIA card to nearly double bandwidth on the same bus width.

Feature support is similar on paper. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use PCIe 5.0 x16. Display outputs differ: the Arc Pro B65 provides 4x DisplayPort 2.1, while the RTX 5080 SUPER provides 1x HDMI 2.1b and 3x DisplayPort 2.1b. The NVIDIA card includes tensor cores, which the Intel card does not list, and the NVIDIA card's FP16 throughput matches its FP32 throughput at a 1:1 ratio, whereas the Intel card halves its FP16 rate to 2:1. The RTX 5080 SUPER also has a much higher pixel rate (293.1 GPixel/s versus 192.0 GPixel/s) and texture rate (879.3 GTexel/s versus 384.0 GTexel/s).

FAQ

Q: Which card has more memory?

A: The Intel Arc Pro B65 has 32 GB of GDDR6 memory, while the NVIDIA GeForce RTX 5080 SUPER has 24 GB of GDDR7. The Intel card offers 8 GB more capacity, but the NVIDIA card has higher bandwidth at 1.02 TB/s versus 608.0 GB/s.

Q: How do their power requirements compare?

A: The Arc Pro B65 has a 200 W TDP and uses a single 8-pin power connector, with a suggested PSU of 550 W. The RTX 5080 SUPER has a 415 W TDP and uses a single 16-pin connector, with no suggested PSU listed in the database.

Q: What is the performance difference in the recorded benchmark?

A: The RTX 5080 SUPER scored 3075 in 3DMark Steel Nomad DX12. Its nearest rivals in the database include the NVIDIA Quadro P1000 at 3163 (2.8% faster), the Intel Arc Pro B60 at 3182 (3.4% faster), the NVIDIA GeForce 820A at 2983 (3.1% slower), and the NVIDIA GeForce GTX 860M at 2967 (3.6% slower). The Arc Pro B65 has no recorded benchmark scores in the database.

Q: Which card has faster memory?

A: The RTX 5080 SUPER has significantly faster memory. Its GDDR7 memory runs at 2000 MHz with 32 Gbps effective speed and delivers 1.02 TB/s bandwidth. The Arc Pro B65's GDDR6 memory runs at 2375 MHz with 19 Gbps effective speed and delivers 608.0 GB/s bandwidth.

Q: Do both cards support the same graphics APIs?

A: Yes, both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both also use a PCIe 5.0 x16 bus interface.

Q: Which card has more compute units?

A: The RTX 5080 SUPER has 10752 shading units, 336 TMUs, 112 ROPs, 84 RT cores, and 336 tensor cores. The Arc Pro B65 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores, with no tensor core count listed.

Specification Differences

| Specification | Intel Arc Pro B65 | NVIDIA GeForce RTX 5080 SUPER |

|---|---|---|

| Chip | BMG-G21 | GB203 |

| Architecture | Xe2-HPG | Blackwell 2.0 |

| Generation | Battlemage (Pro Series) | GeForce 50 |

| Transistors | 19,600 million | 45,600 million |

| Die Size | 272 mm² | 378 mm² |

| Transistor Density | 72.1M / mm² | 120.6M / mm² |

| Base Clock | 2400 MHz | 2295 MHz |

| Boost Clock | 2400 MHz | 2617 MHz |

| Memory Size | 32 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Clock | 2375 MHz, 19 Gbps effective | 2000 MHz, 32 Gbps effective |

| Memory Bandwidth | 608.0 GB/s | 1.02 TB/s |

| Shading Units | 2560 | 10752 |

| TMUs | 160 | 336 |

| ROPs | 80 | 112 |

| RT Cores | 20 | 84 |

| Tensor Cores | Not listed | 336 |

| Pixel Rate | 192.0 GPixel/s | 293.1 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 879.3 GTexel/s |

| FP32 | 12.29 TFLOPS | 56.28 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 56.28 TFLOPS (1:1) |

| TDP | 200 W | 415 W |

| Power Connectors | 1x 8-pin | 1x 16-pin |

| Suggested PSU | 550 W | Not listed |

| Display Outputs | 4x DisplayPort 2.1 | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | Not listed | 304 mm length, 137 mm height, 40 mm width |

| Release Date | 2026-03-31 | 2025-12-31 |

| Launch MSRP | Not listed | 999 USD |

Head-to-Head Benchmarks

The database contains one benchmark result for the RTX 5080 SUPER: a 3DMark Steel Nomad DX12 score of 3075. That score places it in the 19th percentile among all GPUs, with an average benchmark score of 3075. Its nearest rivals in the database are all within a narrow band. The NVIDIA Quadro P1000 leads at 3163, which is 2.8% faster. The Intel Arc Pro B60 follows at 3182, 3.4% faster. On the slower side, the NVIDIA GeForce 820A scores 2983, which is 3.1% behind, and the NVIDIA GeForce GTX 860M scores 2967, 3.6% behind. The Arc Pro B65 has no recorded benchmark scores, so no direct head-to-head result exists between the two cards in the database.

What the data does show is a massive architectural gap. The RTX 5080 SUPER delivers 56.28 TFLOPS FP32, which is 4.6 times the Arc Pro B65's 12.29 TFLOPS. The texture rate gap is similar: 879.3 GTexel/s versus 384.0 GTexel/s, a 2.3 times difference. The pixel rate gap is 293.1 GPixel/s versus 192.0 GPixel/s, a 1.5 times difference. The RTX 5080 SUPER also has 4.2 times as many shading units and 4.2 times as many RT cores. The only areas where the Arc Pro B65 leads are memory capacity (32 GB versus 24 GB), power draw (200 W versus 415 W), and physical size, as the RTX 5080 SUPER measures 304 mm in length, 137 mm in height, and 40 mm in width while the Arc Pro B65 has no dimensions listed.

The nearest-rival data for the RTX 5080 SUPER suggests that its 3DMark Steel Nomad score is not representative of its theoretical compute advantage. The card outperforms the GeForce 820A and GTX 860M by roughly 3% in that test, yet it trails the Quadro P1000 and Arc Pro B60 by similar margins. This clustering of scores around the 3000 mark indicates that the Steel Nomad benchmark may not stress the RTX 5080 SUPER's strengths, or that the recorded result is an outlier relative to its FP32 and texture throughput figures. The Arc Pro B65, with no benchmark scores at all, cannot be compared directly in any workload from the database.

The Verdict

The data points to two different buyers. The Intel Arc Pro B65 suits workloads that need large memory capacity and modest power consumption. Its 32 GB GDDR6 frame buffer, 200 W TDP, and single 8-pin connector make it a straightforward fit for systems with a 550 W PSU. Its 50th percentile ranking among all GPUs indicates mid-pack performance overall, and its lack of tensor cores and lower FP32 throughput (12.29 TFLOPS) suggest it is not aimed at high-end compute tasks.

The NVIDIA GeForce RTX 5080 SUPER targets raw throughput. Its 56.28 TFLOPS FP32, 84 RT cores, 336 tensor cores, and 1.02 TB/s memory bandwidth give it a commanding lead in compute-heavy scenarios, provided the software can use those resources. The 19th percentile ranking and the tight clustering of its nearest rivals in the Steel Nomad test, however, indicate that its real-world performance in that specific benchmark is far below what its specifications would predict. The card's 415 W TDP and 16-pin connector require a robust power delivery setup, and its 304 mm length demands case clearance.

The release dates also matter. The RTX 5080 SUPER launched on 2025-12-31 with a launch MSRP of 999 USD. The Arc Pro B65 launched on 2026-03-31 with no launch MSRP listed. The newer Intel card is the more conservative choice for memory-heavy professional work, while the NVIDIA card is the performance pick for those who need maximum FP32, ray tracing, and tensor throughput. Neither card has a direct recorded head-to-head benchmark result, so the specification differences and the RTX 5080 SUPER's single Steel Nomad score are the only quantitative basis for a decision. The Arc Pro B65's absence from the benchmark database means its real-world performance remains unmeasured, but its 50th percentile standing and lower power envelope position it as a balanced workstation option rather than a performance leader.