Intel Arc B770 vs NVIDIA GeForce RTX 5080 Mobile Comparison

Intel Arc B770 and NVIDIA GeForce RTX 5080 Mobile represent two very different design philosophies within the same process generation. The Intel part is a desktop add-in board built on the Battlemage architecture, while the NVIDIA part is a mobile integrated graphics processor for laptops. The recorded data shows that despite the RTX 5080 Mobile having a much lower thermal envelope, it delivers a substantially higher average benchmark score and percentile ranking. The RTX 5080 Mobile lands at the 81st percentile among all GPUs with an average benchmark score of 38349, whereas the Arc B770 sits at the 50th percentile with no recorded benchmark entries in the database. This performance gap is tied to fundamental architectural differences, memory subsystem choices, and power allocation strategies that separate the two products.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 5080 Mobile records an average benchmark score of 38349, while the Intel Arc B770 has no recorded benchmark scores in the database, leaving its average at 0.

Q: How do the two GPUs compare in memory bandwidth?

A: The RTX 5080 Mobile uses GDDR7 memory with a 256-bit bus and delivers 896.0 GB/s. The Arc B770 uses GDDR6 memory with a 256-bit bus and delivers 512.0 GB/s, exactly half the bandwidth of the NVIDIA part.

Q: What is the thermal design power for each GPU?

A: The Arc B770 has a TDP of 225 W and requires both a 6-pin and an 8-pin power connector. The RTX 5080 Mobile has a TDP of 80 W and uses no external power connectors, drawing power directly from the portable device.

Q: Which GPU has more shading units?

A: The RTX 5080 Mobile has 7680 shading units, compared to 4096 on the Arc B770. The NVIDIA part also has 60 RT cores and 240 tensor cores, while the Intel part has 32 RT cores and no tensor cores listed.

Q: What process node do both GPUs use?

A: Both are manufactured by TSMC on a 5 nm process. The RTX 5080 Mobile has a die size of 378 mm² with 45,600 million transistors, while the Arc B770 has a die size of 368 mm² with an unknown transistor count.

Q: What is the release timeline for these two GPUs?

A: The RTX 5080 Mobile was released in April 2025 and is listed as active in production. The Arc B770 has a release date of December 2025 and no production status recorded.

Architecture Differences

The Arc B770 uses the Xe2-HPG architecture, specifically the Battlemage generation under the Arc 7 series. Its chip is designated BMG-G31. The RTX 5080 Mobile uses the Blackwell 2.0 architecture from the GeForce 50-series, built around the GB203 chip. Both are fabricated by TSMC on a 5 nm node, but the transistor counts diverge sharply. The RTX 5080 Mobile contains 45,600 million transistors on a 378 mm² die, resulting in a density of 120.6M per mm². The Arc B770 has an unknown transistor count on a 368 mm² die, which is slightly smaller than the NVIDIA chip.

The RTX 5080 Mobile is a mobile integrated GPU, marked as IGP in slot width, with no power connectors and no dedicated display outputs (portable device dependent). The Arc B770 is a dual-slot desktop card with a PCIe 4.0 x16 interface and three DisplayPort 2.1 outputs plus one HDMI 2.1a output. The bus interface also differs: the Arc B770 uses PCIe 4.0 x16, while the RTX 5080 Mobile uses PCIe 5.0 x16.

Clock speeds show a notable inversion. The Arc B770 runs at a base clock of 2100 MHz and boosts to 2400 MHz. The RTX 5080 Mobile has a much lower base of 975 MHz and a boost of 1500 MHz, reflecting its constrained power budget and mobile thermal limits. Memory clocks also differ significantly: the Arc B770 operates at 2000 MHz (16 Gbps effective), while the RTX 5080 Mobile runs at 1750 MHz (28 Gbps effective). The higher effective data rate on the NVIDIA part, combined with GDDR7 versus GDDR6, produces the bandwidth advantage.

Ray tracing and compute resources favor the RTX 5080 Mobile. It has 60 RT cores and 240 tensor cores, while the Arc B770 has 32 RT cores and no tensor core count listed. The shading unit count is 7680 versus 4096, a near 2:1 ratio. Texture mapping units favor the Intel part with 256 TMUs versus 240, but raster operation units favor Intel as well with 128 ROPs versus 96. The Intel architecture reaches higher pixel and texture rates, 307.2 GPixel/s and 614.4 GTexel/s, compared to 144.0 GPixel/s and 360.0 GTexel/s on the NVIDIA part.

Where Each One Wins

The RTX 5080 Mobile dominates in raw compute throughput and overall benchmark performance. Its FP32 output is 23.04 TFLOPS, which is 17% higher than the Arc B770's 19.66 TFLOPS. The NVIDIA part also maintains a 1:1 FP16 ratio at 23.04 TFLOPS, whereas the Arc B770 reaches 39.32 TFLOPS FP16 through a 2:1 ratio. This means the Intel GPU can exceed the NVIDIA part in FP16 workloads, but not in FP32 or general compute.

Memory bandwidth is a clear win for the RTX 5080 Mobile at 896.0 GB/s versus 512.0 GB/s. This advantage shows up in bandwidth-sensitive workloads such as high-resolution texturing, large data sets, and certain compute tasks. The Intel GPU compensates with higher pixel fill rate and texture fill rate, which can benefit rasterization-heavy scenes at lower resolutions or with simpler shading.

The Arc B770 wins on connectivity and form factor for desktop use. It provides dedicated display outputs with HDMI 2.1a and three DisplayPort 2.1 connections, making it suitable for multi-monitor desktop setups. The RTX 5080 Mobile relies on the portable device's own outputs, which is typical for laptops. The Arc B770 also has a higher base and boost clock, which helps in latency-sensitive or lightly threaded workloads.

The RTX 5080 Mobile wins on power efficiency by a wide margin. Its 80 W TDP is less than a third of the Arc B770's 225 W TDP, yet it delivers more FP32 throughput and much higher memory bandwidth. The NVIDIA part requires no external power connectors, while the Intel card needs a 6-pin and an 8-pin connector plus a 550 W suggested PSU.

Specification Differences

The two GPUs differ across nearly every specification category. The chip names are BMG-G31 for Intel and GB203 for NVIDIA. The process node is identical at 5 nm from TSMC, but die size differs: 368 mm² for Intel and 378 mm² for NVIDIA. Transistor count is unknown for Intel and 45,600 million for NVIDIA. Transistor density is not listed for Intel and is 120.6M per mm² for NVIDIA.

Clock speeds differ substantially. Base clocks are 2100 MHz versus 975 MHz, and boost clocks are 2400 MHz versus 1500 MHz. Memory clocks are 2000 MHz (16 Gbps effective) versus 1750 MHz (28 Gbps effective). Both use a 256-bit memory bus and have 16 GB of memory, but the type differs: GDDR6 for Intel and GDDR7 for NVIDIA. Bandwidth is 512.0 GB/s versus 896.0 GB/s.

Compute resources favor NVIDIA in most categories. Shading units are 4096 versus 7680. TMUs are 256 versus 240, a small Intel advantage. ROPs are 128 versus 96, another Intel advantage. RT cores are 32 versus 60. Tensor cores are not listed for Intel and 240 for NVIDIA. Pixel rate is 307.2 GPixel/s versus 144.0 GPixel/s. Texture rate is 614.4 GTexel/s versus 360.0 GTexel/s. FP32 is 19.66 TFLOPS versus 23.04 TFLOPS. FP16 is 39.32 TFLOPS (2:1) versus 23.04 TFLOPS (1:1).

Power and physical specs also differ. TDP is 225 W versus 80 W. Slot width is dual-slot versus IGP. Power connectors are 1x 6-pin plus 1x 8-pin versus none. Suggested PSU is 550 W versus not listed. Bus interface is PCIe 4.0 x16 versus PCIe 5.0 x16. Display outputs are 1x HDMI 2.1a plus 3x DisplayPort 2.1 versus portable device dependent. Release dates are December 2025 versus April 2025. The predecessor names are Alchemist versus GeForce 40 Mobile. Production status is not listed for Intel and active for NVIDIA.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two GPUs. However, the RTX 5080 Mobile has an extensive set of recorded benchmark scores across multiple test suites, while the Arc B770 has none. The RTX 5080 Mobile's individual scores show a wide range of performance depending on the workload. In 3DMark Steel Nomad DX12, it scores 4952. In Geekbench, it scores 166986 for OpenCL and 169754 for Vulkan. Passmark results include 27711 for G3D, 12134 for GPU compute, 1095 for G2D, 314 for DirectX 9, 253 for DirectX 11, 171 for DirectX 10, and 116 for DirectX 12.

The average benchmark score for the RTX 5080 Mobile is 38349, placing it at the 81st percentile among all GPUs. Its nearest rivals in the database include the NVIDIA GeForce MX570 with an average score of 38299 and a delta of 0.1%, the NVIDIA GeForce RTX 4080 Mobile with an average score of 38135 and a delta of 0.6%, the NVIDIA GeForce MX570 A with an average score of 38691 and a delta of -0.9%, and the AMD Radeon Pro 580X with an average score of 38706 and a delta of -0.9%. These deltas are all within 1% of the RTX 5080 Mobile, indicating that it sits in a tightly clustered performance tier. The Arc B770 has no benchmark data and no nearest rivals listed, so its performance cannot be directly compared through recorded measurements.

The FP32 throughput difference is one of the clearest quantitative comparisons available. The RTX 5080 Mobile delivers 23.04 TFLOPS, which is 3.38 TFLOPS higher than the Arc B770's 19.66 TFLOPS. This represents roughly a 17% advantage for NVIDIA in standard single-precision compute. Memory bandwidth shows an even larger gap, with the RTX 5080 Mobile at 896.0 GB/s versus 512.0 GB/s, a 75% advantage. The Arc B770 counters with a 163.2 GPixel/s advantage in pixel rate and a 254.4 GTexel/s advantage in texture rate.

The Verdict

The data points decisively toward the NVIDIA GeForce RTX 5080 Mobile for any workload that depends on raw compute throughput, memory bandwidth, or ray tracing capability. Its 23.04 TFLOPS FP32 output exceeds the Arc B770's 19.66 TFLOPS, and its 896.0 GB/s bandwidth is nearly double. The RTX 5080 Mobile also carries 60 RT cores and 240 tensor cores, while the Arc B770 lists 32 RT cores and no tensor cores, giving NVIDIA a clear edge in ray-traced scenes and any tensor-based acceleration. The 81st percentile ranking and average benchmark score of 38349 demonstrate that the RTX 5080 Mobile performs well against the broader GPU landscape, sitting within 1% of several close rivals.

The Arc B770 does hold advantages in specific rasterization metrics. Its 307.2 GPixel/s pixel rate and 614.4 GTexel/s texture rate are much higher than the RTX 5080 Mobile's 144.0 GPixel/s and 360.0 GTexel/s. Its FP16 output of 39.32 TFLOPS also exceeds the RTX 5080 Mobile's 23.04 TFLOPS in that precision, making it potentially useful for workloads that can exploit FP16 with a 2:1 ratio. The desktop form factor with dedicated display outputs and a PCIe 4.0 x16 interface makes it a conventional choice for a desktop build, while the RTX 5080 Mobile is inherently a laptop part.

Power consumption tells the real story. The RTX 5080 Mobile achieves its higher average benchmark score and FP32 throughput at 80 W, while the Arc B770 needs 225 W and a 550 W suggested PSU. This efficiency gap is massive. For mobile users, the RTX 5080 Mobile is the only viable option between these two, since the Arc B770 is a dual-slot desktop card. For desktop users who prioritize rasterization rates or FP16 compute and do not need tensor cores, the Arc B770 offers specific strengths. For anyone measuring overall GPU performance, the RTX 5080 Mobile is the superior part based on the recorded data. The Arc B770's lack of benchmark entries means it cannot be positioned within the database's performance hierarchy, but its architectural specs place it behind the RTX 5080 Mobile in most compute and memory categories. The RTX 5080 Mobile is the stronger product for general use, and the Arc B770 is a niche desktop option with fill-rate advantages that do not overcome its bandwidth and compute deficits.