Microsoft Flight Simulator

The Intel Core Ultra 7 270K Plus and NVIDIA GeForce RTX 5090 D combination delivers the top measured performance in Microsoft Flight Simulator, securing the number one rank out of 2,996 tested combos. This pairing produces frame rates that range from 84 FPS at 4K Ultra settings to 254 FPS at 1080p Low settings. The data shows a system that scales predictably across resolutions and quality presets, with the CPU and GPU each playing distinct roles in the final output.

CPU Role — cores, clocks, and how they relate to this game's results

The Intel Core Ultra 7 270K Plus is a 24-core, 24-thread processor from the Core Ultra Series 2, built on the Arrow Lake Refresh architecture. It operates with a base clock of 3.70 GHz and a boost clock of 5.50 GHz, with a 125 W TDP. The processor uses a 3 nm process node fabricated by TSMC, containing 17,800 million transistors on a 243 mm² die. Cache configuration includes 192 KB of L1 per core, 3 MB of L2 per core, and 36 MB of shared L3 cache. Memory support is DDR5 over a dual-channel interface, providing 115.2 GB/s of bandwidth, with ECC memory support enabled.

Benchmark results place this CPU in the 96th percentile versus all CPUs, with an average benchmark score of 93,785. Its nearest rivals in the aggregate benchmark data include the Intel Xeon 6520P at a score of 93,786 with a delta of 0%, the AMD EPYC 4564P at 95,183 with a delta of -1.5%, the AMD EPYC 9175F at 95,615 with a delta of -1.9%, and the AMD EPYC 4565P at 95,764 with a delta of -2.1%. The 270K Plus trails these server-oriented chips by 1.5% to 2.1% in raw multi-threaded workloads, yet in Microsoft Flight Simulator it leads all tested combinations.

In synthetic CPU tests, the 270K Plus achieves a Cinebench R23 multi-core score of 44,253 and a single-core score of 2,439. The single-core result is particularly relevant for flight simulation, where per-thread performance often dictates the simulation loop's speed. The PassMark single-thread score of 5,068 and the PassMark physics score of 4,064 further indicate strong single-threaded capability. Data compression and encryption results are also notable: 804,322 in PassMark data compression and 59,097 in PassMark data encryption.

For Microsoft Flight Simulator specifically, the CPU's role is most visible at lower resolutions. At 1080p Low settings, the system reaches 254 FPS average, which is 67.1% higher than the 152 FPS average at 4K Low settings. This scaling pattern indicates that at 1080p, the CPU is often the primary limiter, as the GPU has spare capacity to render more frames if the processor can feed it. The 24 cores with 24 threads mean no hyper-threading overhead, which can be beneficial for latency-sensitive workloads. The 5.50 GHz boost clock provides the high frequency needed for the game's main simulation thread, while the 36 MB L3 cache helps keep frequently accessed terrain and aircraft data close to the cores.

The CPU's 96th percentile ranking suggests it outperforms the vast majority of processors currently on the market. Its nearest rival, the Intel Xeon 6520P, has a nearly identical average score (93,786 vs 93,785), yet in this game the 270K Plus combo ranks first. The AMD EPYC processors score 1.5% to 2.1% higher in aggregate benchmarks, but their server-oriented design with higher core counts does not translate to better flight simulator performance. The measured FPS data shows that this consumer desktop CPU, with its high boost clock and balanced cache hierarchy, is better suited to the game's demands than those enterprise parts.

GPU Role — VRAM, clocks, and how they relate to this game's results

The NVIDIA GeForce RTX 5090 D is a Blackwell 2.0 architecture GPU based on the GB202 chip, manufactured on a 5 nm process by TSMC. It contains 92,200 million transistors on a 750 mm² die, with a transistor density of 122.9 million per mm². The GPU operates at a base clock of 2017 MHz and a boost clock of 2407 MHz, with memory clocked at 1750 MHz for 28 Gbps effective speed. It has 32 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth.

The GPU's compute resources include 21,760 shading units, 680 texture mapping units, and 176 raster output units. It has 170 ray tracing cores and 680 tensor cores. Pixel rate is 423.6 GPixel/s, texture rate is 1,636.8 GTexel/s, and FP32 performance reaches 104.8 TFLOPS. The card has a TDP of 575 W, requires a 950 W suggested PSU, and uses a single 16-pin power connector. It fits in a dual-slot design measuring 304 mm in length, 137 mm in height, and 48 mm in width. Display outputs include one HDMI 2.1b and three DisplayPort 2.1b connections.

The RTX 5090 D ranks in the 92nd percentile versus all GPUs, with an average benchmark score of 77,712. Its nearest rivals include the AMD Radeon RX 6650M XT at 76,904 with a delta of 1.1%, the AMD Radeon RX 6850M XT at 78,940 with a delta of -1.6%, the NVIDIA Tesla P100 PCIe 12 GB at 79,396 with a delta of -2.1%, and the NVIDIA Tesla P100 PCIe 16 GB at 79,605 with a delta of -2.4%. The 5090 D outperforms the Radeon RX 6650M XT by 1.1% and trails the other three by 1.6% to 2.4% in aggregate GPU benchmarks. These rivals are largely mobile or older data center parts, which underscores the 5090 D's position in the desktop enthusiast segment.

In DirectX benchmarks, the card scores 371 in PassMark DirectX 11 and 219 in PassMark DirectX 12, with a PassMark G3D score of 44,065 and a PassMark GPU compute score of 28,396. The 32 GB of GDDR7 VRAM is far beyond what Microsoft Flight Simulator requires at any tested setting, eliminating memory capacity as a bottleneck. The 1.79 TB/s bandwidth ensures that texture streaming from storage to VRAM keeps pace with the rendering pipeline, which is crucial for a game that loads high-resolution satellite imagery and detailed aircraft models.

The GPU's role becomes more pronounced at higher resolutions. At 4K Ultra settings, the system averages 84 FPS, which is the lowest measured result. This represents a 40.8% drop from the 142 FPS at 1080p Ultra settings. The 5090 D's 104.8 TFLOPS of FP32 performance and 1,636.8 GTexel/s texture rate are the resources being taxed at these settings. The pixel rate of 423.6 GPixel/s directly translates to how quickly the GPU can fill the 3840x2160 frame buffer with rendered geometry and lighting.

Resolution Scaling — how FPS drops from 1080p to 4K and what it says about the limiting component

The measured FPS data reveals a clear scaling pattern across the three resolutions tested. At Low settings, the average frame rate drops from 254 FPS at 1920x1080 to 205 FPS at 2560x1440, then to 151 FPS at 3840x2160. This represents a 19.3% drop from 1080p to 1440p, and a 40.6% drop from 1080p to 4K. The 40.6% reduction at Low settings suggests that even at this minimal graphical load, the GPU is becoming more of a factor at higher resolutions, while the CPU still holds significant headroom.

At Medium settings, the progression is from 198 FPS at 1080p to 159 FPS at 1440p to 118 FPS at 4K. The drops are 19.7% and 40.4% respectively, nearly identical to the Low settings pattern. This consistency indicates that the Medium preset adds a fixed overhead that scales proportionally with resolution. The minimum FPS at Medium settings also shows this trend: 168 at 1080p, 136 at 1440p, and 100 at 4K.

High settings show a steeper decline: 149 FPS at 1080p, 120 FPS at 1440p, and 88 FPS at 4K. The drop from 1080p to 1440p is 19.5%, and from 1080p to 4K is 40.9%. This is remarkably close to the Low and Medium percentages, suggesting that the High preset does not disproportionately burden the GPU compared to lower presets. The absolute frame rates are lower, but the scaling curve remains consistent.

Ultra settings produce the largest absolute drops: 142 FPS at 1080p, 114 FPS at 1440p, and 84 FPS at 4K. The 1080p to 1440p drop is 19.7%, and the 1080p to 4K drop is 40.8%. Again, the percentage scaling is nearly identical to the other presets. This uniformity across all four settings presets strongly indicates that the limiting component shifts from CPU-bound at 1080p to GPU-bound at 4K, but the transition is gradual and predictable.

The fact that the percentage drops are so consistent (ranging from 40.4% to 40.9% from 1080p to 4K across all presets) suggests that neither component is an extreme bottleneck at any resolution. If the CPU were severely limiting at 1080p, the drop to 4K would be larger than 40% because the GPU would become the new limiter. If the GPU were severely limiting at 4K, the drop from 1080p would be smaller because the CPU would cap the 1080p results. The observed pattern indicates a balanced system where both components contribute meaningfully, with the GPU taking on more responsibility as pixel count increases.

FAQ

Q: What is the highest average FPS this combo achieves in Microsoft Flight Simulator?

A: The highest measured average FPS is 254, achieved at 1920x1080 resolution with Low settings.

Q: How does this combo rank against other tested combinations in this game?

A: It ranks first out of 2,996 tested combos, making it the top-performing configuration in the database for Microsoft Flight Simulator.

Q: What is the lowest average FPS recorded for this combo?

A: The lowest average FPS is 84, recorded at 3840x2160 resolution with Ultra settings.

Q: Does the CPU or GPU limit performance more at 4K?

A: At 4K, the GPU becomes the primary limiter, as evidenced by the 40.8% drop from 1080p Ultra to 4K Ultra, which aligns with the GPU-bound scaling pattern.

Q: What is the FPS range at Medium settings across all resolutions?

A: At Medium settings, the average FPS ranges from 198 at 1080p to 159 at 1440p to 118 at 4K, with minimum FPS values of 168, 136, and 100 respectively.

Q: How does the RTX 5090 D compare to its nearest GPU rival in aggregate benchmarks?

A: The RTX 5090 D scores 77,712 on average, which is 1.1% higher than the AMD Radeon RX 6650M XT's 76,904, but 1.6% lower than the AMD Radeon RX 6850M XT's 78,940.

How This Combo Ranks

The Intel Core Ultra 7 270K Plus with the NVIDIA GeForce RTX 5090 D achieves the number one rank in Microsoft Flight Simulator, out of 2,996 tested combinations. This top ranking is notable given that the individual components do not lead their respective aggregate benchmark categories. The CPU ranks in the 96th percentile versus all CPUs, while the GPU ranks in the 92nd percentile versus all GPUs. Neither component has the highest average benchmark score among its peers, yet the combination produces the best measured FPS in this specific game.

The CPU's nearest rivals include the Intel Xeon 6520P with a nearly identical average score, and three AMD EPYC processors that score 1.5% to 2.1% higher. The GPU's nearest rivals are largely mobile or older data center parts; the AMD Radeon RX 6650M XT scores 1.1% lower, while the AMD Radeon RX 6850M XT and two NVIDIA Tesla P100 variants score 1.6% to 2.4% higher. These aggregate benchmark deltas do not predict game performance, as the 270K Plus and 5090 D combination outperforms all of them in Microsoft Flight Simulator.

The rank of 1 out of 2,996 places this combo at the very top of the database for this title. This suggests that the combination of the 270K Plus's high boost clock and the 5090 D's massive compute resources is particularly well-suited to the game's rendering and simulation demands. The measured FPS data across all twelve rows (three resolutions × four settings presets) shows no anomalies or unexpected dips, indicating stable and consistent performance across the entire testing matrix.

Settings Recommendations

The measured FPS data provides clear guidance on which preset offers the best experience at each resolution. At 1920x1080, all four settings presets produce playable frame rates, with Ultra averaging 142 FPS and Low averaging 254 FPS. The Medium preset at 198 FPS offers a good balance, with a minimum of 168 FPS that keeps frame pacing smooth. For players seeking maximum visual fidelity at 1080p, the Ultra preset's 142 FPS average is well above the 60 FPS threshold and should provide a fluid experience.

At 2560x1440, the High preset at 120 FPS and the Ultra preset at 114 FPS are both excellent choices. The Medium preset at 159 FPS with a minimum of 136 FPS offers the most headroom for demanding scenes, such as flying over dense urban areas or through complex weather systems. The data indicates that 1440p Ultra is only 5% slower than 1440p High, making Ultra a viable option for users with high-refresh-rate monitors.

At 3840x2160, the High preset at 88 FPS and the Ultra preset at 84 FPS are close, with only a 4.5% difference. The Medium preset at 118 FPS with a minimum of 100 FPS provides the best combination of visual quality and frame rate stability at 4K. The Low preset at 151 FPS is available for users who prioritize frame rate above all else, but the Medium preset's minimum of 100 FPS ensures no drops below triple-digit frame rates. Given that the Ultra preset at 4K still averages 84 FPS, it is a reasonable choice for users with G-SYNC or FreeSync displays that can handle variable refresh rates.

Across all resolutions, the Medium preset consistently offers the highest minimum FPS relative to its average, with minimums of 168 at 1080p, 136 at 1440p, and 100 at 4K. This makes Medium the most predictable preset in terms of frame pacing, which is important in a flight simulator where sudden frame drops can affect control inputs. The High and Ultra presets do not report minimum FPS values in the measured data, which limits direct comparison, but their averages are close enough to Medium at 1440p and 4K that users can choose based on visual preference.

Measured FPS Breakdown

At 1920x1080, the measured average FPS values are 254 for Low, 198 for Medium, 149 for High, and 142 for Ultra. The Medium preset includes minimum and maximum values of 168 and 227 FPS respectively. This resolution produces the highest frame rates in the entire dataset, with even the Ultra preset exceeding 140 FPS. The gap between Low and Ultra is 112 FPS, representing a 44.1% reduction from Low to Ultra, which shows the graphical overhead of the higher presets at this resolution.

At 2560x1440, the average FPS values are 205 for Low, 159 for Medium, 120 for High, and 114 for Ultra. The Medium preset reports minimum and maximum values of 136 and 183 FPS. Compared to 1080p, the 1440p results are 19.3% lower for Low, 19.7% lower for Medium, 19.5% lower for High, and 19.7% lower for Ultra. This consistent reduction across all presets indicates that the 1440p resolution adds a uniform pixel-count overhead that scales with the rendering workload.

At 3840x2160, the average FPS values are 151 for Low, 118 for Medium, 88 for High, and 84 for Ultra. The Medium preset reports minimum and maximum values of 100 and 135 FPS. Compared to 1080p, the 4K results are 40.6% lower for Low, 40.4% lower for Medium, 40.9% lower for High, and 40.8% lower for Ultra. The near-identical percentage drops across all presets confirm that the 4K resolution penalty is consistent regardless of quality settings, which points to a resolution-driven bottleneck rather than a preset-driven one.

The complete dataset shows a smooth progression from the fastest configuration (1080p Low at 254 FPS) to the slowest (4K Ultra at 84 FPS). The 4K Ultra result is 66.9% lower than the 1080p Low result, but it remains well above playable thresholds. The Medium preset at each resolution provides the only rows with minimum and maximum FPS data, offering the most complete picture of frame time variability. At 1080p Medium, the range is 168 to 227 FPS, a 35.1% spread. At 1440p Medium, the range is 136 to 183 FPS, a 34.6% spread. At 4K Medium, the range is 100 to 135 FPS, a 35% spread. This consistent spread across resolutions suggests that the frame time distribution is stable regardless of pixel count.