AMD Radeon RX 9070 XT vs Intel Arc B770 Comparison

Head-to-Head Benchmarks

The recorded data for the AMD Radeon RX 9070 XT shows a substantial performance profile across multiple benchmark suites. In 3DMark Steel Nomad DX12, the card records a score of 7260 points, which places it in the 55th percentile among all GPUs in the database. Its average benchmark score across the full test suite is 13543 points, and the nearest rival in the database is the AMD Radeon HD 7770M with an average score of 13536, a delta of just 0.1 percent. The next closest entries are the NVIDIA GeForce GTX 570 at 13515 (0.2 percent delta) and the NVIDIA P106-090 at 13470 (0.5 percent delta), followed by the AMD Radeon Pro 555 at 13407 (1 percent delta).

The Intel Arc B770, by contrast, has no recorded benchmark scores in the database. Its average benchmark score is listed as 0, and there are no nearest rivals provided. The percentile field for the Arc B770 is 50, which indicates a median position in the overall GPU distribution, but without actual test results, direct numerical comparisons cannot be drawn from the database. The data shows that the RX 9070 XT has a full set of ten benchmark entries, while the Arc B770 has zero entries.

Looking at the RX 9070 XT's individual results, the Geekbench Vulkan score is 65879, which is the highest single-test number recorded for the card. The OpenCL score is 17428, and the PassMark G3D score is 26795. The PassMark GPU Compute result is 15864. These figures collectively contribute to the 13543 average. The variance between tests is notable: the Vulkan score is roughly 4.9 times the OpenCL score, indicating strong API-specific performance characteristics. The PassMark DirectX 12 score is 78, while the DirectX 11 score is 292 and the DirectX 9 score is 353. The DirectX 10 score is 154, and the G2D score is 1328.

Because the Arc B770 lacks any benchmark entries, the head-to-head comparison in this database is one-sided. The RX 9070 XT's 55th percentile ranking means it sits above the median GPU, while the Arc B770's 50th percentile is exactly at the median. This difference of 5 percentile points suggests the AMD part holds a modest advantage in overall standing, but the absence of Arc B770 measurements prevents a direct score-for-score comparison. The data confirms that the RX 9070 XT is an active product with measurable performance, whereas the Arc B770's status is not listed as active, and its release date is recorded as the end of 2025.

Where Each One Wins

Based on the available data, the AMD Radeon RX 9070 XT wins in every category where measurements exist. The card's compute performance is substantial: FP32 throughput is listed at 48.66 TFLOPS, and FP16 is identical at 48.66 TFLOPS with a 1:1 ratio. The pixel rate is 380.2 GPixel/s, and the texture rate is 760.3 GTexel/s. These figures are derived from the chip's 4096 shading units, 256 TMUs, and 128 ROPs, along with a boost clock of 2970 MHz and a base clock of 1660 MHz.

The Intel Arc B770 offers different specifications. Its FP32 throughput is 19.66 TFLOPS, which is less than half of the RX 9070 XT's 48.66 TFLOPS. However, the Arc B770's FP16 performance is 39.32 TFLOPS with a 2:1 ratio, meaning it delivers double-rate FP16 compared to FP32. The RX 9070 XT runs FP16 at the same rate as FP32. This architectural choice gives the Intel card a relative advantage in workloads that use FP16 instructions, but the absolute FP16 number for the RX 9070 XT (48.66 TFLOPS) still exceeds the Arc B770's 39.32 TFLOPS.

The RX 9070 XT also wins on memory bandwidth. It has 644.6 GB/s of bandwidth from 16 GB of GDDR6 on a 256-bit bus with memory clocked at 2518 MHz (20.1 Gbps effective). The Arc B770 has 512.0 GB/s of bandwidth from 16 GB of GDDR6 on a 256-bit bus with memory at 2000 MHz (16 Gbps effective). The difference is 132.6 GB/s in favor of AMD, which is a 25.9 percent advantage. Both cards have identical memory capacity and bus width, so the bandwidth difference comes entirely from the higher memory clock.

In terms of power, the RX 9070 XT has a TDP of 304 W, while the Arc B770 has a TDP of 225 W. The suggested PSU for the AMD card is 700 W, and for the Intel card it is 550 W. The RX 9070 XT uses two 8-pin power connectors, while the Arc B770 uses one 6-pin and one 8-pin. These figures indicate that the AMD card draws more power, but the database does not include efficiency or performance-per-watt measurements.

Architecture Differences

The two GPUs come from different architectural families. The AMD Radeon RX 9070 XT uses the Navi 48 chip based on RDNA 4.0 architecture, belonging to the Navi IV generation (RX 9000 series). The Intel Arc B770 uses the BMG-G31 chip based on Xe2-HPG architecture, belonging to the Battlemage generation (Arc 7). Both are manufactured by TSMC, but on different process nodes: the RX 9070 XT is on a 4 nm process, while the Arc B770 is on a 5 nm process. The smaller node gives AMD a potential density advantage, though the transistor counts differ substantially.

The RX 9070 XT has 53,900 million transistors on a die size of 357 mm², yielding a transistor density of 151.0 million per square millimeter. The Arc B770's transistor count is listed as unknown, but its die size is 368 mm², which is slightly larger than the AMD die. Without a transistor count for the Intel part, density cannot be calculated. The die size difference is 11 mm² in favor of the Intel card being larger, but the AMD card has a more advanced process node.

Core configurations are identical in count: both GPUs have 4096 shading units, 256 TMUs, and 128 ROPs. The difference lies in ray tracing hardware. The RX 9070 XT has 64 RT cores, while the Arc B770 has 32 RT cores. This gives AMD twice the RT core count, which may influence ray-traced workload performance, though no specific RT benchmarks are recorded in the database. Neither card has tensor cores listed.

Clock speeds differ significantly. The RX 9070 XT has a base clock of 1660 MHz and a boost clock of 2970 MHz, with a game clock of 2400 MHz. The Arc B770 has a base clock of 2100 MHz and a boost clock of 2400 MHz, with no game clock listed. The AMD card's boost clock is 570 MHz higher than the Intel card's, while the Intel card's base clock is 440 MHz higher than AMD's. The memory clocks also differ: AMD runs at 2518 MHz (20.1 Gbps effective) versus Intel's 2000 MHz (16 Gbps effective), as noted previously.

Interface and connectivity also diverge. The RX 9070 XT uses PCIe 5.0 x16, while the Arc B770 uses PCIe 4.0 x16. Display outputs are similar: both have one HDMI port and three DisplayPort connections, but the AMD card has HDMI 2.1b and DisplayPort 2.1a, while the Intel card has HDMI 2.1a and DisplayPort 2.1. API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both cards are dual-slot designs. The RX 9070 XT's predecessor is listed as Navi III, while the Arc B770's predecessor is Alchemist.

The Verdict

The database clearly favors the AMD Radeon RX 9070 XT for any scenario where measured performance matters. It has an average benchmark score of 13543, a 55th percentile ranking, and a complete set of test results across multiple suites. The Intel Arc B770 has no recorded benchmark scores, an average of 0, and no nearest rivals, which means no empirical evidence exists in the database to support a performance claim for that card. The Arc B770 does have a 50th percentile ranking, but this figure is not accompanied by any test data.

For users who rely on the database's recorded measurements, the RX 9070 XT delivers a clear performance profile. Its highest single-test result is the Geekbench Vulkan score of 65879, and its lowest is the PassMark DirectX 12 score of 78. The card's FP32 compute of 48.66 TFLOPS and memory bandwidth of 644.6 GB/s are the standout specifications. The Arc B770, with its lower FP32 of 19.66 TFLOPS and bandwidth of 512.0 GB/s, would likely trail in most direct comparisons, but this cannot be confirmed from benchmark data because none exists for the Intel part.

The RX 9070 XT also has the advantage of a 4 nm process node versus the 5 nm node for the Arc B770, plus double the RT cores (64 versus 32). The Arc B770 does have a lower TDP (225 W versus 304 W) and a lower suggested PSU (550 W versus 700 W), which indicates lower power consumption, but the database provides no efficiency measurements. The RX 9070 XT has a launch MSRP of 599 USD, while the Arc B770 has no launch MSRP listed.

The verdict from the data is straightforward: the AMD Radeon RX 9070 XT is the only one of the two with measurable performance, and all recorded metrics place it above the median GPU. The Intel Arc B770 is a product with a release date at the end of 2025, but it is not yet supported by any benchmark entries in the database. Until such measurements are recorded, the RX 9070 XT stands as the superior choice based on available evidence.

FAQ

Q: What is the average benchmark score for the AMD Radeon RX 9070 XT?

A: The average benchmark score is 13543 points across ten different tests, which places it in the 55th percentile among all GPUs in the database.

Q: Does the Intel Arc B770 have any benchmark results in the database?

A: No. The Arc B770 has zero benchmark entries, an average benchmark score of 0, and no nearest rivals listed. Its percentile ranking is 50, but no test data supports that figure.

Q: How does the FP32 compute performance compare between the two cards?

A: The RX 9070 XT delivers 48.66 TFLOPS of FP32, while the Arc B770 delivers 19.66 TFLOPS. The AMD card's FP16 is also 48.66 TFLOPS at a 1:1 ratio, whereas the Intel card's FP16 is 39.32 TFLOPS at a 2:1 ratio.

Q: What are the memory bandwidth figures for each GPU?

A: The RX 9070 XT has 644.6 GB/s of bandwidth from 16 GB of GDDR6 on a 256-bit bus. The Arc B770 has 512.0 GB/s from 16 GB of GDDR6 on a 256-bit bus.

Q: Which card has more ray tracing cores?

A: The RX 9070 XT has 64 RT cores, while the Arc B770 has 32 RT cores. Both cards have 4096 shading units, 256 TMUs, and 128 ROPs.

Q: What is the process node and die size for each card?

A: The RX 9070 XT uses a 4 nm TSMC process with a 357 mm² die and 53,900 million transistors. The Arc B770 uses a 5 nm TSMC process with a 368 mm² die, but its transistor count is unknown.