AMD Radeon 890M vs NVIDIA GeForce GTX 465 Comparison

The NVIDIA GeForce GTX 465 and the AMD Radeon 890M represent two radically different eras of GPU design, separated by over a decade of architectural evolution. The data reveals a stark performance gulf that is only partially explained by their similar aggregate benchmark percentiles, which sit at 46 and 45 respectively. While their overall standing among all GPUs is nearly identical, the single head-to-head benchmark available paints a very different picture of their capabilities, with the integrated Radeon 890M delivering a crushing defeat to the older discrete card.

Head-to-Head Benchmarks

The only directly comparable data point comes from the Geekbench OpenCL test, and the results are decisive. The AMD Radeon 890M scores 37,254, while the NVIDIA GeForce GTX 465 manages only 9,294. This represents a delta of -75.1% for the GTX 465, meaning the Radeon 890M is roughly four times faster in this compute workload. The margin is so large that it transcends the architectural differences and points to a fundamental generational leap in compute throughput.

This 75.1% deficit is the largest single performance gap in the comparison. It is not a close contest or a slight edge; it is a complete and total rout. The GTX 465's raw compute capabilities, listed at 855.4 GFLOPS FP32, are dwarfed by the Radeon 890M's 5.939 TFLOPS, a near seven-fold increase in theoretical shader throughput. The Radeon 890M also shows a much higher pixel rate of 92.80 GPixel/s and texture rate of 185.6 GTexel/s, versus the GTX 465's 13.38 GPixel/s and 26.75 GTexel/s, further explaining the disparity in the OpenCL result.

Interestingly, the aggregate benchmark scores tell a different story. The GTX 465's average benchmark score is 9,294, while the Radeon 890M's is 9,210. The Radeon 890M's nearest rival list includes the GTX 465 with a deltaPct of -0.9, indicating the GTX 465 is slightly ahead on average. However, this average is heavily skewed by the GTX 465's single data point (the OpenCL score) and the Radeon 890M's many lower-scoring tests like Passmark DirectX 9 (97) and Passmark G2D (979). The head-to-head test isolates a pure compute workload, while the average includes older, less demanding API tests that do not leverage the modern architecture's strengths.

The Radeon 890M's other benchmark scores, such as 40,808 in Geekbench Vulkan and 8,076 in Passmark G3D, suggest that its advantage extends beyond just OpenCL. The Vulkan score is particularly telling, as it indicates strong performance under a modern, low-overhead API, which the GTX 465 cannot even run. The GTX 465 has no Vulkan support listed in its API specifications, making any comparison in that realm impossible, but the Radeon 890M's high score there is a clear indicator of its contemporary design.

The Verdict

Based strictly on the benchmark data, the AMD Radeon 890M is the superior product for any compute-oriented task. The 75.1% lead in Geekbench OpenCL is an insurmountable advantage. For users whose primary concern is raw shader throughput, compute workloads, or running modern APIs like Vulkan and DirectX 12 Ultimate, the Radeon 890M is the clear choice. Its 5.939 TFLOPS FP32 performance and support for DirectX 12 Ultimate (12_2) and Vulkan 1.4 place it in a different performance class.

The NVIDIA GeForce GTX 465, however, holds a marginal edge in the aggregate benchmark average, with a score of 9,294 versus 9,210. This is a 0.9% difference based on the deltaPct in the Radeon 890M's rival list. This could be interpreted as the GTX 465 being slightly more consistent across a broader range of legacy tests, but it is a negligible margin compared to the massive OpenCL deficit.

The data implies that the GTX 465's only redeeming quality in this comparison is its slight edge in the overall average, which is likely due to its specialized, high-bandwidth memory configuration. The GTX 465 has a dedicated 1024 MB of GDDR5 memory with a 256-bit bus and 102.7 GB/s of bandwidth, whereas the Radeon 890M uses System Shared memory, making its bandwidth "System Dependent". In scenarios where dedicated memory bandwidth is paramount and the workload is not compute-heavy, the GTX 465 might hold up, but no benchmark in the data directly supports this.

For the vast majority of tasks, the Radeon 890M is the definitive winner. The single head-to-head benchmark is a landslide, and its support for modern graphics APIs that the GTX 465 lacks entirely makes it the more future-proof and capable component. The GTX 465 is an end-of-life product from 2010, while the Radeon 890M is an active product from 2024, and the performance data reflects this generational chasm.

Where Each One Wins

The AMD Radeon 890M wins in all modern compute and graphics scenarios. Its victory in the Geekbench OpenCL test is its primary claim, but its other scores reinforce this. The 40,808 Geekbench Vulkan score shows it excels in that modern API, and its Passmark G3D score of 8,076 is far higher than any single metric the GTX 465 can offer. Its support for DirectX 12 Ultimate and Vulkan 1.4 means it is the only one of the two capable of running the latest game titles and applications that rely on these APIs.

The NVIDIA GeForce GTX 465's only "win" is the aggregate benchmark average, where it leads by a razor-thin 0.9% over the Radeon 890M. This is a statistical artifact of the different benchmark suites available for each, not a sign of real-world superiority. Its higher average is buoyed by its single OpenCL score, which is still far lower than the Radeon's, and it has no scores for other modern API tests to drag its average down. The GTX 465's dedicated memory architecture could be a theoretical advantage for certain legacy workloads, but this is not reflected in any of the provided benchmark data.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD Radeon 890M has a significantly higher score of 37,254, compared to the NVIDIA GeForce GTX 465's 9,294, giving it a 75.1% lead.

Q: How close are the two GPUs in terms of their average benchmark scores?

A: They are very close. The NVIDIA GeForce GTX 465 has an average benchmark score of 9,294, while the AMD Radeon 890M has an average of 9,210, a difference of only 0.9%.

Q: Does the AMD Radeon 890M support modern graphics APIs?

A: Yes, the Radeon 890M supports DirectX 12 Ultimate (12_2) and Vulkan 1.4. The NVIDIA GeForce GTX 465 only supports DirectX 12 (11_0) and OpenGL 4.6, with no Vulkan support listed.

Q: What are the relative pixel fill rates of these two GPUs?

A: The AMD Radeon 890M has a pixel rate of 92.80 GPixel/s, which is nearly seven times higher than the NVIDIA GeForce GTX 465's rate of 13.38 GPixel/s.

Q: Which GPU has a higher transistor density?

A: The AMD Radeon 890M has a far higher transistor density of 145.9M per mm², compared to the NVIDIA GeForce GTX 465's 5.9M per mm².

Q: What is the TDP of each GPU?

A: The NVIDIA GeForce GTX 465 has a TDP of 200 W, while the AMD Radeon 890M has a TDP of just 15 W.

Architecture Differences

The two GPUs are built on fundamentally different architectures separated by fourteen years of progress. The NVIDIA GeForce GTX 465 uses the Fermi architecture (chip GF100) on a 40 nm process node at TSMC, with a massive die size of 529 mm². It packs 3,100 million transistors at a density of 5.9M per mm². In contrast, the AMD Radeon 890M uses the RDNA 3.5 architecture (chip Strix Point) on a 4 nm node, also from TSMC. It has a much smaller die size of 233 mm² but contains a staggering 34,000 million transistors, achieving a density of 145.9M per mm².

The Radeon 890M features 1024 shading units, 64 texture mapping units, and 32 ROPs, alongside 16 ray tracing cores. The GTX 465 is configured with 352 shading units, 44 TMUs, and 32 ROPs, and has no ray tracing cores. This fundamental difference in execution resources is the primary driver of the performance gap. The RDNA 3.5 architecture also supports FP16 compute at a 1:1 ratio to FP32 (5.939 TFLOPS each), while the Fermi architecture's FP16 capabilities are not specified.

The Radeon 890M is an integrated graphics processor (IGP) on the Strix Point mobile chip, meaning its memory is System Shared and its bandwidth is System Dependent. The GTX 465 is a discrete card with its own 1024 MB of GDDR5 memory on a 256-bit bus, providing a fixed 102.7 GB/s of bandwidth. The Radeon 890M also has a much higher base clock of 400 MHz and a boost clock of 2900 MHz, while the GTX 465's base and boost clocks are not specified in the data.

Specification Differences

The two products differ in nearly every measurable specification. The process node is a major differentiator, with the Radeon 890M using 4 nm versus the GTX 465's 40 nm. This leads to a massive difference in transistor count (34,000 million vs 3,100 million) and density (145.9M vs 5.9M per mm²). The die size is also inverted, with the older Fermi chip being larger at 529 mm² compared to the RDNA 3.5 chip's 233 mm².

The compute resources are starkly different: the Radeon 890M has 1024 shading units and 64 TMUs, while the GTX 465 has 352 and 44, respectively. Both have 32 ROPs, but the Radeon 890M adds 16 ray tracing cores that the GTX 465 lacks. The clock speeds also differ, with the Radeon 890M listing a boost clock of 2900 MHz, whereas the GTX 465 has no base or boost clock listed. The memory subsystem is a fundamental mismatch: the GTX 465 uses 1024 MB of GDDR5 on a 256-bit bus with 102.7 GB/s bandwidth, while the Radeon 890M relies on System Shared memory with System Dependent bandwidth.

The power profiles are on opposite ends of the spectrum. The GTX 465 has a TDP of 200 W, requires dual-slot cooling, and uses 2x 6-pin power connectors with a suggested PSU of 550 W. The Radeon 890M is an IGP with a TDP of just 15 W, no power connectors, and no suggested PSU. The bus interface also differs, with the GTX 465 using PCIe 2.0 x16 and the Radeon 890M using PCIe 4.0 x8. Finally, the API support is a clear generational split: the Radeon 890M supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the GTX 465 is limited to DirectX 12 (11_0) and OpenGL 4.6 with no Vulkan support.