Overpower

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

The AMD Ryzen 5 7600 is a 6-core, 12-thread processor based on the Zen 4 architecture (codename Raphael), built on a 5 nm process by TSMC. Its base clock is 3.80 GHz, boosting to 5.10 GHz, with a 65 W TDP. The chip carries 64 KB of L1 cache per core, 1 MB of L2 per core, and 32 MB of shared L3 cache. Memory support is DDR5 over a dual-channel bus, yielding 83.2 GB/s of bandwidth, with ECC support enabled. The processor also includes Radeon integrated graphics, though the system under analysis pairs it with a discrete GPU.

Benchmark data places the Ryzen 5 7600 in the 83rd percentile among all CPUs. Its average benchmark score is 26617, which is essentially level with its nearest rivals: the AMD Ryzen 7 5800X3D (avg score 26574, deltaPct 0.2), the Intel Core i9-12900HK (26672, deltaPct -0.2), the AMD EPYC 8024P (26555, deltaPct 0.2), and the Intel Core i9-11900K (26546, deltaPct 0.3). In practical terms, the Ryzen 5 7600 trades blows within a fraction of a percent of these chips—differences of 0.2–0.3% are negligible for gaming workloads.

In multi-threaded synthetic tests, the chip scores 6499 in 3dmark with 16 threads and 6503 with max threads, showing strong scaling from 6 cores. Single-thread performance is also solid: 999 in 3dmark single-thread, 3246 in Cinebench R23 single-core, and 3910 in Passmark single-thread. For a game like Overpower, which is an action title from 2023, these numbers indicate the CPU is not likely to bottleneck the GPU at standard resolutions. The 12 threads handle background tasks and game logic, while the 5.10 GHz boost clock keeps latency-sensitive frames responsive.

The CPU's percentile rank (83) and near-identical performance to the 5800X3D—a chip often favored for gaming—suggest that Overpower's frame rates are not CPU-limited in most scenarios. The data shows that even at 1080p Low, where CPU overhead is typically highest, the system achieves 227.3 FPS, implying ample headroom remains.

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

The NVIDIA GeForce RTX 5070 is built on the Blackwell 2.0 architecture (chip GB205) using a 5 nm process by TSMC. It packs 31,100 million transistors on a 263 mm² die, with a transistor density of 118.3M per mm². The GPU has 6144 shading units, 192 texture mapping units, 80 ROPs, 48 RT cores, and 192 tensor cores. Clock speeds are a base of 2325 MHz and a boost of 2512 MHz. Memory is 12 GB of GDDR7 on a 192-bit bus, delivering 672.0 GB/s of bandwidth.

The RTX 5070's pixel rate is 201.0 GPixel/s, texture rate is 482.3 GTexel/s, and FP32 compute reaches 30.87 TFLOPS (with FP16 at 30.87 TFLOPS as well, a 1:1 ratio). The card draws a 250 W TDP, requires a 600 W suggested PSU, and connects via PCIe 5.0 x16. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

In the GPU benchmark hierarchy, the RTX 5070 sits in the 83rd percentile, with an average score of 41687. Its nearest rivals include the AMD Radeon Pro 5300 (avg score 41610, deltaPct 0.2), NVIDIA Tesla M40 (41897, deltaPct -0.5), NVIDIA GeForce RTX 3090 (41441, deltaPct 0.6), and AMD Radeon Pro 580X (41991, deltaPct -0.7). The deltaPct values indicate the RTX 5070 is within 0.7% of these cards—essentially tied in aggregate benchmark scores. However, the RTX 3090 is an older flagship, and the RTX 5070 achieves parity with newer architecture and lower power draw.

For Overpower, the GPU's 12 GB VRAM is sufficient at all tested settings, as no memory-related stutters appear in the measured FPS data. The 672.0 GB/s bandwidth supports high-resolution texture streaming. At 4K Ultra, the system still holds 84.5 FPS, showing the GPU has enough compute headroom for demanding presets. The boost clock of 2512 MHz ensures sustained performance under load, which aligns with the consistent frame rates observed across resolutions.

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

Examining the measured FPS across resolutions reveals a clear scaling pattern. At Ultra settings, the average FPS drops from 107.8 at 1080p to 96.7 at 1440p (a 10.3% reduction), then to 84.5 at 4K (a 21.6% drop from 1080p). At High settings, the same trend appears: 134.8 at 1080p, 119.6 at 1440p (11.3% lower), and 98.9 at 4K (26.6% lower). Medium settings show 144.6 at 1080p, 129 at 1440p (10.8% lower), and 106.8 at 4K (26.1% lower). Low settings exhibit the steepest relative decline: 227.3 at 1080p, 201.7 at 1440p (11.3% lower), and 173.2 at 4K (23.8% lower).

The pattern is consistent: moving from 1080p to 1440p costs roughly 10–11% performance across all presets, while the 1440p-to-4K transition costs another 13–15%. This is a classic GPU-bound signature. If the CPU were limiting, the FPS would remain relatively flat when resolution increases, because the processor's workload (draw calls, physics, game logic) stays constant. Instead, the frame rate drops proportionally with pixel count, indicating the RTX 5070 is the primary constraint.

The fact that even at 1080p Low the system reaches 227.3 FPS—far above typical monitor refresh rates—reinforces that the CPU (6 cores, 12 threads, 83rd percentile) is not the bottleneck. The Ryzen 5 7600's single-thread score of 3910 in Passmark suggests it can feed frames quickly, but at 4K the GPU's fill rate and memory bandwidth become decisive. The 672.0 GB/s bandwidth is adequate, yet the 12 GB VRAM and 192-bit bus create a ceiling that scales predictably with resolution.

Another observation: the FPS delta between Low and Ultra widens at higher resolutions. At 1080p, Ultra is 107.8 FPS versus Low's 227.3 (a 52.6% gap). At 4K, Ultra (84.5) versus Low (173.2) shows a 51.2% gap—similar proportionally, but the absolute difference grows from 119.5 FPS to 88.7 FPS. This suggests the GPU's compute resources handle both resolution and quality settings independently, with no single component causing a cliff.

FAQ

Q: What is the combination rank of this CPU-GPU pair in Overpower?

A: The AMD Ryzen 5 7600 with NVIDIA GeForce RTX 5070 ranks 332 out of 1744 tested combinations, placing it in the top 19% of all pairings.

Q: How does the Ryzen 5 7600 compare to its nearest rival in synthetic benchmarks?

A: The Ryzen 5 7600 scores 26617 on average, which is 0.2% higher than the AMD Ryzen 7 5800X3D (26574) and 0.2% higher than the AMD EPYC 8024P (26555). It trails the Intel Core i9-12900HK (26672) by 0.2% and beats the Intel Core i9-11900K (26546) by 0.3%.

Q: What is the best frame rate achieved at any resolution and setting?

A: The maximum average FPS recorded is 227.3, achieved at 1920x1080 with Low settings. This is 12.7% faster than the 1440p Low result (201.7) and 31.2% faster than 4K Low (173.2).

Q: Is the GPU or CPU the limiting factor at 4K Ultra?

A: At 3840x2160 Ultra, the system produces 84.5 FPS. Since the CPU maintains similar scores to rivals (within 0.3%) and the FPS scales down with resolution, the GPU is the limiting component. The RTX 5070's 12 GB VRAM and 672.0 GB/s bandwidth are the binding constraints.

Q: How much performance is lost when going from 1080p to 4K at High settings?

A: At High settings, the FPS drops from 134.8 at 1080p to 98.9 at 4K, a 26.6% reduction. The 1440p result (119.6) sits almost exactly halfway in percentage terms (11.3% lower than 1080p).

Q: What is the RTX 5070's benchmark position relative to the RTX 3090?

A: The RTX 5070 has an average score of 41687, which is 0.6% higher than the RTX 3090's 41441. Both GPUs occupy similar performance tiers despite the generational gap.

Measured FPS Breakdown

The measured FPS data covers three resolutions (1920x1080, 2560x1440, 3840x2160) and four settings presets (Low, Medium, High, Ultra). All values are average FPS; no minimum or maximum frames are recorded.

At 1920x1080, the system delivers 227.3 FPS on Low, 144.6 on Medium, 134.8 on High, and 107.8 on Ultra. The gap between Low and Ultra is 119.5 FPS (52.6% difference). Medium is 36.4% below Low, while High is only 6.8% below Medium—indicating diminishing returns from Medium to High.

At 2560x1440, performance drops to 201.7 FPS on Low, 129 on Medium, 119.6 on High, and 96.7 on Ultra. The Low-to-Ultra gap narrows to 105 FPS (52.1% difference). Medium is 36.1% below Low, and High is 7.3% below Medium, mirroring the 1080p pattern.

At 3840x2160, the results are 173.2 FPS on Low, 106.8 on Medium, 98.9 on High, and 84.5 on Ultra. The Low-to-Ultra gap is 88.7 FPS (51.2% difference). Medium is 38.3% below Low, High is 7.4% below Medium, and Ultra is 14.6% below High—the largest relative step between High and Ultra across all resolutions.

Comparing settings across resolutions: Ultra at 1080p (107.8) is actually faster than High at 1440p (119.6) by 10.9%, but slower than Medium at 1440p (129) by 16.4%. Similarly, Ultra at 1440p (96.7) outperforms High at 4K (98.9) by 2.2%, and Medium at 4K (106.8) beats High at 1080p (134.8) by 20.8%. These overlaps show the resolution-versus-settings tradeoff is not linear.

The 4K Low result (173.2) exceeds 1080p Ultra (107.8) by 60.7%, demonstrating that lowering quality at high resolution yields more frames than raising quality at low resolution. Conversely, 1080p Low (227.3) is 168.9% faster than 4K Ultra (84.5), underscoring the GPU's fill-rate limits at extreme pixel counts.

Settings Recommendations

Based on the measured rows, the optimal preset depends on the target resolution and frame rate goal. At 1920x1080, Ultra (107.8 FPS) is playable, but High (134.8) offers 25.0% more frames with a modest visual step down. Medium (144.6) adds 7.3% over High but sacrifices more visual fidelity for a smaller gain. For competitive play, Low (227.3) is the clear choice, providing more than double the Ultra frame rate.

At 2560x1440, High (119.6) is the sweet spot for smooth gameplay, as it stays above 100 FPS while retaining decent quality. Ultra (96.7) dips below 100 FPS, which may be noticeable on high-refresh displays. Medium (129) is a strong alternative if the user prioritizes frame rate over shadows and textures. Low (201.7) remains viable for esports-style play, though the visual penalty is significant at this resolution.

At 3840x2160, Medium (106.8) is the recommended preset, as it maintains a comfortable margin above 100 FPS. High (98.9) is acceptable but hovers near the triple-digit threshold, and Ultra (84.5) drops to a level where motion clarity suffers. Low (173.2) is unnecessary unless the user targets 144 Hz at 4K, which Low achieves but with heavily reduced detail.

The data suggests a general rule: for 60+ FPS targets, all presets work at every resolution. For 100+ FPS, the user must choose High at 1080p, Medium at 1440p, or Medium at 4K. For 144+ FPS, only Low at 1080p (227.3) and Low at 1440p (201.7) qualify; 4K Low (173.2) also exceeds 144 FPS. The best experience per the measured rows is High at 1440p (119.6) or Medium at 4K (106.8), depending on whether resolution or visual fidelity is weighted more heavily.