AMD Radeon R9 M290X vs AMD Radeon RX 6700M Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive victory for the AMD Radeon RX 6700M across every shared benchmark test. In the two direct comparisons available, the RX 6700M wins both, with the most dramatic margin appearing in Geekbench Metal where it scores 91,911 versus the R9 M290X’s 24,524, a gap of 274.8%. That is not a marginal improvement; it represents a generational leap in raw compute performance as measured by the database.

The Geekbench OpenCL results tell a similar story, though with a slightly smaller margin. The RX 6700M posts 77,666 points against 22,028 for the R9 M290X, a 252.6% advantage. Both deltas exceed 250%, meaning the newer part is roughly three and a half times faster in these workloads. The data does not show a single test where the R9 M290X comes out ahead. Wins tally at 2 for the RX 6700M and 0 for the R9 M290X.

Context from the nearest rivals section reinforces how far apart these two sit in the broader field. The RX 6700M’s average benchmark score is 25,633, placing it just 0.4% behind the AMD Radeon Pro W5700 (25,726) and 0.4% behind the NVIDIA GeForce RTX 3080 Ti Mobile (25,740). It also trails the AMD FirePro D700 by 0.8% and the AMD FirePro W7100 by 0.9%. These are all near-identical scores, meaning the RX 6700M sits in a tight cluster of high-end GPUs. The R9 M290X, by contrast, averages 23,276, which is statistically tied with the AMD Radeon RX 6600M (23,273, 0% delta) and the AMD Radeon Pro Vega 16 (23,250, 0.1% delta). It also sits within 0.2% of the AMD Radeon AI PRO R9700 (23,315) and leads the NVIDIA P106-100 by 0.1% (23,249). What this means: the RX 6700M competes with modern flagship mobile parts, while the R9 M290X trades blows with mid-range cards from several generations later.

Percentile rankings add another layer. The RX 6700M lands at the 71st percentile among all GPUs in the database, while the R9 M290X sits at the 68th. That difference sounds modest, but the percentile is computed across the entire GPU population, and the raw score gap between the two is substantial. The RX 6700M’s percentile confirms its placement in the upper tier, whereas the R9 M290X, despite being end-of-life and released much earlier, still holds a respectable position due to its compute capabilities.

The takeaway from the head-to-head data is unambiguous: the RX 6700M outperforms the R9 M290X by a factor of roughly 2.5 to 2.7 in the only tests where both have recorded results. No benchmark in the database shows the R9 M290X winning, and the margins are far beyond any run-to-run variance. This is a clean sweep.

FAQ

Q: Which GPU wins the Geekbench Metal benchmark?

A: The AMD Radeon RX 6700M wins with a score of 91,911, compared to 24,524 for the AMD Radeon R9 M290X. That is a 274.8% advantage for the RX 6700M.

Q: How large is the performance gap in Geekbench OpenCL?

A: The RX 6700M scores 77,666, while the R9 M290X scores 22,028. The RX 6700M leads by 252.6% in this test.

Q: Are the two GPUs close in overall average benchmark score?

A: No. The RX 6700M averages 25,633, while the R9 M290X averages 23,276. The RX 6700M is ahead by roughly 2,357 points, or about 10.1%.

Q: How do these GPUs compare to their nearest rivals?

A: The RX 6700M is within 0.9% of the AMD FirePro W7100, AMD FirePro D700, NVIDIA GeForce RTX 3080 Ti Mobile, and AMD Radeon Pro W5700. The R9 M290X is within 0.2% of the AMD Radeon RX 6600M, AMD Radeon Pro Vega 16, NVIDIA P106-100, and AMD Radeon AI PRO R9700.

Q: Which GPU has the higher percentile ranking?

A: The RX 6700M sits at the 71st percentile among all GPUs, while the R9 M290X sits at the 68th percentile.

Q: Does the R9 M290X win any benchmark in the database?

A: No. The head-to-head data shows 2 wins for the RX 6700M and 0 wins for the R9 M290X.

Where Each One Wins

The RX 6700M wins everywhere the data records a comparison. In Geekbench Metal and Geekbench OpenCL, it dominates. For users who need compute-heavy tasks like OpenCL acceleration in content creation or Metal-based rendering on macOS-style workloads, the RX 6700M is the clear pick. Its 274.8% lead in Metal and 252.6% lead in OpenCL mean it handles these tasks at a completely different performance level.

The R9 M290X does not win any recorded benchmark, so there is no workload in the database where it comes out ahead of the RX 6700M. However, the R9 M290X still has a role in systems that require its specific form factor. It is an MXM Module, while the RX 6700M is an IGP. For a laptop with an MXM slot, the R9 M290X may be the only physically compatible option, even though its performance is far lower. The data cannot quantify that compatibility advantage, but the form factor difference is recorded.

For pure performance, the RX 6700M is the only choice between the two. For hardware compatibility in legacy MXM systems, the R9 M290X has a structural advantage that no benchmark score can override. The RX 6700M also wins on memory capacity with 10 GB versus 4 GB, and on memory bandwidth at 320.0 GB/s versus 153.6 GB/s. Those numbers matter for large textures and high-resolution assets, where the RX 6700M can keep more data on-board and feed it faster.

Specification Differences

The two GPUs differ in nearly every measurable specification. The RX 6700M uses a 160-bit memory bus with 10 GB of GDDR6, while the R9 M290X uses a wider 256-bit bus but only 4 GB of GDDR5. Peak bandwidth favors the RX 6700M at 320.0 GB/s versus 153.6 GB/s. Clock speeds also diverge sharply: the RX 6700M has a base clock of 1489 MHz and a boost of 2400 MHz, while the R9 M290X runs at 850 MHz base and 900 MHz boost. The RX 6700M also lists a game clock of 2300 MHz, a field the R9 M290X does not have.

Shader resources differ substantially. The RX 6700M has 2304 shading units, 144 texture mapping units, and 64 ROPs. The R9 M290X has 1280 shading units, 80 TMUs, and 32 ROPs. This translates into a pixel rate of 153.6 GPixel/s for the RX 6700M versus 28.80 GPixel/s for the R9 M290X, and a texture rate of 345.6 GTexel/s versus 72.00 GTexel/s. FP32 compute is 11.06 TFLOPS for the RX 6700M and 2.304 TFLOPS for the R9 M290X. The RX 6700M also records FP16 at 22.12 TFLOPS (2:1), while the R9 M290X has no FP16 figure.

Transistor counts and process nodes are far apart. The RX 6700M packs 17,200 million transistors on a 335 mm² die at 7 nm, while the R9 M290X has 2,800 million transistors on a 212 mm² die at 28 nm. Transistor density is 51.3 million per mm² for the RX 6700M versus 13.2 million per mm² for the R9 M290X. Both chips come from TSMC, but the process gap is enormous. The RX 6700M also supports PCIe 4.0 x16, while the R9 M290X uses PCIe 3.0 x16.

Power targets differ as well: the RX 6700M has a TDP of 135 W, and the R9 M290X has a TDP of 100 W. The RX 6700M is an IGP with no power connectors, while the R9 M290X is an MXM Module, also with no power connectors. The RX 6700M supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The R9 M290X supports DirectX 12 (11_1), Vulkan 1.2.170, and OpenGL 4.6. The RX 6700M has 36 ray tracing cores; the R9 M290X has none.

Architecture Differences

The architectural gap between these two is fundamental. The RX 6700M is built on RDNA 2.0, while the R9 M290X uses GCN 1.0. That is a difference of roughly two full architecture generations. RDNA 2.0 brings hardware ray tracing, which is why the RX 6700M lists 36 RT cores while the R9 M290X lists none. The RX 6700M is part of the Radeon RX 6000 series and the Navi Mobile (RX 6000M) generation, built on the Navi 22 chip. The R9 M290X belongs to the Gem System (R9 M200) generation and uses the Neptune chip.

The process node difference drives much of the performance gap. At 7 nm versus 28 nm, the RX 6700M fits 17,200 million transistors into 335 mm², achieving a density of 51.3 million per mm². The R9 M290X fits 2,800 million transistors into 212 mm² at 13.2 million per mm². This density advantage allows the RX 6700M to pack more compute units, more memory bandwidth per pin, and more features into a similar power envelope. The RX 6700M’s TDP is 135 W, only 35 W higher than the R9 M290X’s 100 W, yet it delivers roughly 4.8 times the FP32 throughput.

Memory architecture also differs. The RX 6700M uses GDDR6 at 16 Gbps effective, while the R9 M290X uses GDDR5 at 4.8 Gbps effective. Despite a narrower 160-bit bus, the RX 6700M achieves more than double the bandwidth. The RX 6700M also supports PCIe 4.0, doubling the bus bandwidth available to the CPU compared with the R9 M290X’s PCIe 3.0.

API support reflects the architectural divide. DirectX 12 Ultimate (12_2) on the RX 6700M includes features like ray tracing and mesh shaders, while the R9 M290X tops out at DirectX 12 (11_1). Vulkan support is newer on the RX 6700M (1.4 versus 1.2.170). The R9 M290X’s GCN 1.0 architecture was designed for an era before these features existed, and the database shows no ray tracing capability for it. The RX 6700M’s predecessor is listed as Polaris Mobile, and the R9 M290X’s successor is Polaris Mobile, meaning the R9 M290X sits at the end of one lineage while the RX 6700M represents a newer branch.

The Verdict

The data points to one conclusion: the AMD Radeon RX 6700M is the superior GPU in every benchmarked dimension. It wins both shared tests with margins above 250%, has a higher average benchmark score (25,633 versus 23,276), and holds a higher percentile ranking (71st versus 68th). For anyone choosing between these two based on performance, the RX 6700M is the only rational pick.

The RX 6700M also offers more memory (10 GB versus 4 GB), faster memory (320.0 GB/s versus 153.6 GB/s), more shading units, more TMUs, more ROPs, higher clocks, and hardware ray tracing. It supports newer APIs including DirectX 12 Ultimate and Vulkan 1.4. Its 7 nm process gives it a transistor density of 51.3 million per mm², enabling all of this at a TDP of 135 W.

The R9 M290X is not without a niche. Its MXM Module form factor means it can slot into systems designed for that interface, something the RX 6700M’s IGP design cannot do. Its 28 nm process, 2,800 million transistors, and 212 mm² die are far older, but it remains an end-of-life product with a recorded successor in Polaris Mobile. For a legacy laptop with an MXM slot, it may be the only option that physically fits.

But the verdict from the benchmark data is not close. The RX 6700M leads by 274.8% in Metal and 252.6% in OpenCL. It averages 10.1% higher overall. Its nearest rivals include the RTX 3080 Ti Mobile and Radeon Pro W5700, while the R9 M290X’s nearest rivals are the RX 6600M and Pro Vega 16. The performance class is simply different. Choose the RX 6700M for compute, for modern API support, for memory capacity, and for ray tracing. Choose the R9 M290X only if the hardware slot demands it, and even then, the performance ceiling will be far lower. The database records no scenario where the R9 M290X wins.