AMD Radeon R9 370X vs Intel Arc A770M Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between the Intel Arc A770M and the AMD Radeon R9 370X. In the two shared benchmark tests, the Intel part wins both, and the margins are not close. The most striking result comes from Geekbench Vulkan, where the Arc A770M scores 74,422 against the R9 370X’s 9,018, a delta of 725.3%. That is not a generational step; it is a chasm. The Vulkan API is heavily utilized in modern game engines and compute workloads, and the Arc A770M’s advantage here suggests it can handle contemporary rendering pipelines with far greater efficiency.

The second shared test, Geekbench OpenCL, shows a similar story but with a smaller relative gap. The Arc A770M posts 89,494, while the R9 370X manages 25,893, resulting in a 245.6% delta. OpenCL is a compute-centric benchmark, and the data indicates the Intel GPU delivers more than triple the raw compute throughput of the AMD card in this workload. The wins tally confirms the dominance: the Arc A770M wins 2 head-to-head benchmarks, and the R9 370X wins none.

Context from the database’s nearest-rival comparisons helps frame these scores. The Arc A770M’s average benchmark score sits at 18,383, placing it just 0.1% above the AMD Radeon RX 460 (18,373) and 1.2% above the NVIDIA GeForce RTX 3060 Mobile (18,159). Meanwhile, the R9 370X’s average score is 15,862, which is 0.1% above the AMD Radeon RX 7700 (15,852) but 1.7% below the NVIDIA GeForce RTX 3060 Ti (16,129). The percentile rankings reinforce this: the Arc A770M sits at the 62nd percentile of all GPUs, while the R9 370X sits at the 58th. The gap in average scores, roughly 2,500 points, is consistent with the head-to-head results and indicates that the Intel part is positioned a full tier above the older AMD card.

Looking at the individual benchmark suites, the Arc A770M’s strengths are broad. In Passmark’s DirectX 12 test, it scores 70, and in DirectX 11 it scores 69, showing nearly identical performance across those two API generations. The DirectX 9 score of 178 is notably higher, which is typical for modern GPUs that still accelerate legacy paths well. The Passmark G3D score of 11,774 is the standout, while the G2D score of 711 reflects 2D and desktop compositing workloads. The compute-focused Passmark GPU Compute score of 4,778 is solid, and the 3DMark Steel Nomad DX12 score of 2,278 provides a modern gaming workload reference. The R9 370X only has three recorded benchmarks, all from Geekbench: Metal (12,676), OpenCL (25,893), and Vulkan (9,018). The Metal score is notable because the Arc A770M has no Metal benchmark in the database, so that API remains an Apple-centric comparison where the R9 370X has at least some measurable presence.

FAQ

Q: Which GPU wins the Geekbench Vulkan benchmark?

A: The Intel Arc A770M wins decisively, scoring 74,422 against the AMD Radeon R9 370X’s 9,018, a 725.3% advantage.

Q: How does the Intel Arc A770M compare to the R9 370X in OpenCL compute?

A: The Arc A770M scores 89,494, which is 245.6% higher than the R9 370X’s 25,893, indicating more than triple the compute throughput in this workload.

Q: What are the average benchmark scores for these two GPUs?

A: The Arc A770M has an average benchmark score of 18,383, while the R9 370X has an average of 15,862. The Arc A770M is also at the 62nd percentile of all GPUs, compared to the R9 370X’s 58th percentile.

Q: Does the R9 370X have any benchmark where it wins?

A: No. In the head-to-head comparison, the Intel Arc A770M wins both shared tests (Geekbench OpenCL and Vulkan), and the R9 370X records zero wins.

Q: How does the R9 370X’s average score compare to its nearest rivals?

A: The R9 370X’s average score of 15,862 is 0.1% higher than the AMD Radeon RX 7700 (15,852) and 1.2% higher than the AMD Radeon Pro W5500 (15,679), but it is 1.7% lower than the NVIDIA GeForce RTX 3060 Ti (16,129).

Q: What is the DirectX 12 benchmark result for the Arc A770M?

A: In Passmark’s DirectX 12 test, the Arc A770M scores 70. The R9 370X does not have a recorded Passmark DirectX result in the database.

Architecture Differences

The two GPUs come from fundamentally different eras and design philosophies. The Intel Arc A770M is built on the Xe-HPG architecture, specifically the DG2-512 chip, and belongs to the Alchemist generation (Arc 7 Mobile). It is fabricated on a 6 nm process at TSMC, with a transistor count of 21,700 million and a die size of 406 mm², yielding a transistor density of 53.4 million per square millimeter. The AMD Radeon R9 370X, in contrast, uses the GCN 1.0 architecture with the Trinidad chip, part of the Pirate Islands generation (R9 300). It is built on a 28 nm process, also at TSMC, with only 2,800 million transistors on a 212 mm² die, giving a transistor density of 13.2 million per square millimeter. The process node difference is stark: 6 nm versus 28 nm, which explains why the Intel chip packs nearly eight times more transistors into roughly twice the die area.

The compute resources diverge sharply as well. The Arc A770M has 4,096 shading units, 256 texture mapping units, and 128 render output units, alongside 32 dedicated ray tracing cores. The R9 370X has 1,280 shading units, 80 TMUs, and 32 ROPs, with no ray tracing hardware at all. That absence of RT cores is critical for modern games that use hardware-accelerated ray tracing, as the Arc A770M can offload those calculations while the R9 370X cannot. The Intel GPU also features DirectX 12 Ultimate (12_2) support, which includes features like mesh shaders and variable rate shading, while the R9 370X is limited to DirectX 12 (11_1) and Vulkan 1.2.170. The Arc A770M supports Vulkan 1.4, a newer specification that brings improved performance and feature parity with newer APIs.

The memory subsystem is another major architectural divider. The Arc A770M uses 16 GB of GDDR6 memory on a 256-bit bus, delivering 512.0 GB/s of bandwidth. The R9 370X has 2 GB of GDDR5 on a 256-bit bus, with 179.2 GB/s. The memory clock speeds tell the story: the Intel part runs at 2000 MHz with 16 Gbps effective, while the AMD card runs at 1400 MHz with 5.6 Gbps effective. The Intel card’s bandwidth is nearly three times higher, which directly impacts texture-heavy workloads and high-resolution rendering. The R9 370X’s 2 GB framebuffer is a serious constraint for modern games, while the Arc A770M’s 16 GB provides ample headroom for large assets and compute buffers.

Specification Differences

The specification sheet shows a clean generational leap. The Arc A770M has a base clock of 1650 MHz and a boost clock of 2050 MHz, while the R9 370X operates at 980 MHz base and 1030 MHz boost. That clock advantage, combined with the architectural improvements, explains much of the performance delta. The Intel GPU’s FP32 compute is rated at 16.79 TFLOPS, versus 2.637 TFLOPS for the AMD card, a 6.4x difference. The texture rate is 524.8 GTexel/s for Intel and 82.40 GTexel/s for AMD, and the pixel rate is 262.4 GPixel/s versus 32.96 GPixel/s. The Arc A770M also supports FP16 at 33.59 TFLOPS with a 2:1 ratio, while the R9 370X has no recorded FP16 capability.

Power consumption differs significantly, and in an unexpected direction. The Arc A770M has a TDP of 120 W, while the R9 370X draws 180 W. The newer Intel GPU is more efficient despite delivering far higher performance. The R9 370X requires two 6-pin power connectors and a suggested PSU of 450 W, while the Arc A770M is an IGP (integrated graphics package) with no power connectors listed. The R9 370X is a dual-slot card measuring 221 mm in length and 111 mm in height, with display outputs of 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The Arc A770M’s display outputs are listed as portable device dependent, reflecting its mobile-oriented design. The bus interface differs as well: PCIe 4.0 x16 for Intel versus PCIe 3.0 x16 for AMD.

The R9 370X has a release date of 2015-08-26 and a launch MSRP of 199 USD, while the Arc A770M’s release date and launch MSRP are not recorded in the database. Both are marked as end-of-life products. The R9 370X’s predecessor is Volcanic Islands and its successor is Arctic Islands, while the Arc A770M has no listed predecessor or successor. The Intel card’s memory type is GDDR6, the AMD card’s is GDDR5, and the capacities are 16 GB versus 2 GB, as noted earlier. The shading unit count difference is 4,096 versus 1,280, and the TMU/ROP counts are 256/128 versus 80/32.

Where Each One Wins

The Intel Arc A770M is the clear winner in almost every measurable category. In compute-heavy workloads like OpenCL, it delivers 245.6% more performance than the R9 370X, making it suitable for tasks like video encoding, scientific simulation, and machine learning inference that rely on raw FP32 throughput. The Vulkan advantage of 725.3% is even more pronounced, which means the Arc A770M is far better positioned for modern game engines that use Vulkan as their primary rendering API. The 16 GB memory capacity is a decisive factor for large datasets, high-resolution textures, and multi-tasking with multiple GPU-accelerated applications. The ray tracing cores on the Intel GPU are a feature the AMD card simply lacks, so any workload involving ray-traced lighting or shadows will favor the Arc A770M without competition.

The R9 370X does retain a few niche advantages. Its 180 W TDP is higher than the Arc A770M’s 120 W, but that does not translate into a performance win; it simply means the AMD card is less efficient. The R9 370X has a Metal benchmark score of 12,676, which is the only recorded test where the Arc A770M has no data, so on Apple platforms (macOS, iPadOS) the AMD card has at least a measurable presence. The dual-slot form factor and traditional display outputs (DVI, HDMI, DisplayPort) make it easier to install in legacy desktop systems, whereas the Arc A770M is an IGP designed for mobile devices. The R9 370X also has a known release date and predecessor/successor lineage, which may appeal to retro-hardware enthusiasts cataloging older GPU generations.

For gaming, the Arc A770M’s DirectX 12 score of 70 and modern API support make it the obvious choice for current titles. The R9 370X’s lack of DirectX 12 Ultimate and its older Vulkan 1.2.170 support mean it will struggle with newer rendering features. For productivity, the Arc A770M’s 16.79 TFLOPS FP32 and 512 GB/s bandwidth dominate the R9 370X’s 2.637 TFLOPS and 179.2 GB/s. The database percentile data reinforces this: the Arc A770M sits at the 62nd percentile versus the R9 370X’s 58th, and the average score gap of roughly 2,500 points is consistent across multiple benchmark suites. In short, the Arc A770M is a modern, efficient, high-performance GPU that leaves the R9 370X as a legacy product for historical or low-demand scenarios.