AMD Radeon 890M vs AMD Radeon RX 6600S Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive overall victory for the AMD Radeon RX 6600S, which wins seven of the eight shared benchmark comparisons. The largest margin appears in Passmark DirectX 10, where the RX 6600S scores 81 versus 33 for the Radeon 890M, a 145.5% advantage. This is followed by Passmark DirectX 9, where the RX 6600S delivers 176 points against 97, a 81.4% lead. In Geekbench OpenCL, the RX 6600S posts 66435 versus 37254, translating to a 78.3% advantage, making it the second-largest relative gap in the dataset.

The Passmark DirectX 12 results also favor the RX 6600S, with scores of 56 and 37 respectively, a 51.4% difference. The DirectX 11 test shows a 43.8% lead for the RX 6600S (105 versus 73). In Passmark G3D, which is often treated as a general gaming indicator, the RX 6600S records 12649 against 8076, a 56.6% edge. The compute-oriented Passmark GPU Compute test is closer, with the RX 6600S at 4879 and the Radeon 890M at 4157, a 17.4% margin.

The single benchmark where the Radeon 890M wins is Passmark G2D, which measures 2D graphics and desktop-related performance. There, the 890M scores 979 versus 647 for the RX 6600S, a 33.9% difference in favor of the newer integrated part. This is notable because it is the only category where the 890M outperforms the discrete RX 6600S, and the gap is substantial rather than marginal.

Context from the nearest rival data reinforces the performance tiers. The RX 6600S has an average benchmark score of 10629, placing it just 0.4% ahead of the AMD Radeon R9 M275X (10582) and 1.4% ahead of the AMD Radeon RX 550X (10481). Its percentile rank among all GPUs is 49. The Radeon 890M averages 9210, sitting 0.1% below the AMD Radeon Vega 8 (9221) and 1% behind the NVIDIA GeForce GTX 850M (9302). The 890M’s percentile rank is 45. So while the RX 6600S wins the head-to-head, both parts occupy similar mid-low positions in the overall GPU distribution, with the 890M trailing by roughly one percentile point.

Architecture Differences

The two AMD parts come from different design generations and process nodes. The RX 6600S uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated on a 7 nm TSMC process. It contains 11,060 million transistors on a 237 mm² die, giving a transistor density of 46.7 million per square millimeter. The Radeon 890M uses the Strix Point chip on RDNA 3.5 architecture, also from TSMC but on a 4 nm node. It packs 34,000 million transistors into a 233 mm² die, resulting in a much higher density of 145.9 million per square millimeter. The 890M therefore achieves roughly three times the transistor count in a similar physical area, reflecting the newer manufacturing process.

The memory subsystems differ fundamentally. The RX 6600S has dedicated 4 GB of GDDR6 memory on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The Radeon 890M relies on System Shared memory, with the bus width and bandwidth both listed as system dependent. This means the 890M’s memory performance is contingent on the host platform’s RAM configuration, whereas the RX 6600S has fixed, dedicated bandwidth. The 890M’s memory clock is also listed as System Shared, while the RX 6600S runs at 1750 MHz (14 Gbps effective).

The compute unit configurations are also distinct. The RX 6600S has 1792 shading units, 112 texture mapping units, 64 raster operation units, and 28 ray tracing cores. The Radeon 890M has 1024 shading units, 64 TMUs, 32 ROPs, and 16 ray tracing cores. The RX 6600S thus has 75% more shading units, 75% more TMUs, double the ROPs, and 75% more ray tracing cores. The clock behavior differs as well: the RX 6600S has a base clock of 1700 MHz, a game clock of 1881 MHz, and a boost of 2000 MHz. The 890M has a much lower base of 400 MHz but a higher boost of 2900 MHz, with no game clock listed.

The FP32 throughput reflects these differences. The RX 6600S delivers 7.168 TFLOPS, while the 890M provides 5.939 TFLOPS. In FP16, the RX 6600S reaches 14.34 TFLOPS via a 2:1 ratio, whereas the 890M achieves 5.939 TFLOPS at a 1:1 ratio. The pixel rate for the RX 6600S is 128.0 GPixel/s versus 92.80 GPixel/s for the 890M. Texture rate is 224.0 GTexel/s for the RX 6600S and 185.6 GTexel/s for the 890M. Power consumption also differs sharply: the RX 6600S has a TDP of 80 W, while the 890M is rated at 15 W. Both are listed as IGP (integrated graphics processor) slot width with no power connectors, and both use PCIe 4.0 x8.

The release timeline separates them by over two years. The RX 6600S was released on January 3, 2022, and is now marked end-of-life. The Radeon 890M launched on July 14, 2024, and is still active. Their predecessors differ: the RX 6600S succeeds Polaris Mobile, while the 890M succeeds Navi II IGP. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs are portable device dependent for both.

Where Each One Wins

The RX 6600S is the clear winner for DirectX-based gaming workloads across legacy and modern APIs. Its Passmark DirectX 9, 10, 11, and 12 scores are all higher, with margins ranging from 43.8% to 145.5%. The G3D result, which often correlates with overall 3D gaming performance, also favors the RX 6600S by 56.6%. For users targeting older titles at higher settings or modern games with DirectX 12, the recorded data consistently places the RX 6600S ahead. Its higher FP32 throughput, larger ROP count, and dedicated GDDR6 bandwidth support this conclusion.

The Radeon 890M wins in exactly one measured category: Passmark G2D. This test typically reflects 2D rendering, desktop compositing, and basic graphical interface responsiveness. The 890M’s 979 score versus 647 represents a 33.9% advantage, suggesting that integrated graphics in this generation handle lightweight 2D tasks more efficiently than the older discrete part. The 890M’s much lower base clock (400 MHz) but very high boost (2900 MHz) may contribute to efficient power management in low-load scenarios, though the benchmark data itself does not directly confirm power behavior.

For compute workloads, the RX 6600S still leads in Passmark GPU Compute by 17.4%, but the gap is narrower than in most gaming tests. This indicates that the 890M’s architecture, despite fewer shading units, is relatively more competitive for general-purpose compute tasks. In Geekbench OpenCL, however, the RX 6600S dominates with a 78.3% edge, suggesting that legacy OpenCL performance strongly favors the discrete part.

The average benchmark scores reinforce the split. The RX 6600S averages 10629 across all recorded tests, while the 890M averages 9210. That is a 15.4% overall lead for the RX 6600S. In percentile terms, the RX 6600S sits at the 49th percentile of all GPUs, versus the 45th for the 890M. For a user prioritizing gaming and dedicated graphics performance, the RX 6600S is the stronger choice. For a user prioritizing low power consumption (15 W versus 80 W) and acceptable 2D performance, the Radeon 890M offers a different trade-off.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6600S has an average benchmark score of 10629, while the AMD Radeon 890M averages 9210. The RX 6600S also holds a higher percentile rank at 49 versus 45 for the 890M.

Q: In which benchmark does the Radeon 890M outperform the RX 6600S?

A: The Radeon 890M wins only in Passmark G2D, scoring 979 against the RX 6600S’s 647, a 33.9% advantage. Every other shared benchmark favors the RX 6600S.

Q: What is the largest performance gap between the two in the head-to-head tests?

A: The largest gap is in Passmark DirectX 10, where the RX 6600S scores 81 versus 33 for the 890M, a 145.5% difference. The second-largest is in Passmark DirectX 9 at 81.4%.

Q: How does the RX 6600S compare to its nearest rival, the AMD Radeon R9 M275X?

A: The RX 6600S has an average score of 10629, which is 0.4% higher than the R9 M275X’s 10582. It is also 1.4% ahead of the AMD Radeon RX 550X.

Q: How does the Radeon 890M compare to its nearest rival, the AMD Radeon Vega 8?

A: The Radeon 890M averages 9210, which is 0.1% below the Vega 8’s 9221. It also trails the NVIDIA GeForce GTX 960 by 0.7% and the GeForce GTX 465 by 0.9%.

Q: What are the TDP ratings for these two GPUs?

A: The RX 6600S has a TDP of 80 W, while the Radeon 890M has a TDP of 15 W. Both are listed as IGP slot width with no power connectors.

Specification Differences

The two GPUs differ across nearly every core specification. The RX 6600S uses a 7 nm process with 11,060 million transistors on a 237 mm² die. The Radeon 890M uses a 4 nm process with 34,000 million transistors on a 233 mm² die. Transistor density is 46.7M per mm² for the RX 6600S versus 145.9M per mm² for the 890M.

Clock speeds: the RX 6600S has a 1700 MHz base, 1881 MHz game clock, and 2000 MHz boost. The 890M has a 400 MHz base and 2900 MHz boost, with no game clock specified. Memory: the RX 6600S has 4 GB GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The 890M uses System Shared memory with system dependent bus width and bandwidth.

Compute units: the RX 6600S has 1792 shading units, 112 TMUs, 64 ROPs, and 28 ray tracing cores. The 890M has 1024 shading units, 64 TMUs, 32 ROPs, and 16 ray tracing cores. Pixel rate is 128.0 GPixel/s for the RX 6600S versus 92.80 GPixel/s for the 890M. Texture rate is 224.0 GTexel/s versus 185.6 GTexel/s. FP32 is 7.168 TFLOPS versus 5.939 TFLOPS. FP16 is 14.34 TFLOPS (2:1) versus 5.939 TFLOPS (1:1).

Power and release: the RX 6600S has a TDP of 80 W, while the 890M has a TDP of 15 W. The RX 6600S was released on January 3, 2022, and is end-of-life. The 890M was released on July 14, 2024, and is active. Predecessors differ: Polaris Mobile for the RX 6600S and Navi II IGP for the 890M. The architecture is RDNA 2.0 for the RX 6600S and RDNA 3.5 for the 890M. Both share PCIe 4.0 x8, DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4.