AMD Ryzen 5 PRO 4655GE vs Intel Core i5-12490F Comparison

FAQ

Q: How do the two processors compare in overall average benchmark score?

A: The AMD Ryzen 5 PRO 4655GE posts an average benchmark score of 20900, while the Intel Core i5-12490F scores 20802. That is a difference of roughly 0.5%, placing both in the same performance tier despite their architectural differences.

Q: Which CPU wins more individual benchmark tests?

A: The Intel Core i5-12490F wins all 17 head-to-head benchmark comparisons. The AMD Ryzen 5 PRO 4655GE has zero wins in the head-to-head suite, with Intel leading by margins ranging from 3.6% to 67.8% depending on the workload.

Q: What are the biggest performance gaps between the two?

A: The largest deltas appear in PassMark find prime numbers, where Intel leads by 67.8%, and PassMark physics, where Intel leads by 56%. The smallest gap is in PassMark data encryption, at just 3.6% in favor of Intel.

Q: Do both CPUs support the same memory types?

A: No. The AMD Ryzen 5 PRO 4655GE supports only DDR4 memory, while the Intel Core i5-12490F supports both DDR4 and DDR5. Both use dual-channel memory buses, but the AMD part lists a memory bandwidth of 51.2 GB/s while Intel does not list a bandwidth figure.

Q: What are the TDP and socket differences?

A: The AMD Ryzen 5 PRO 4655GE has a 35W TDP and uses AMD Socket AM4. The Intel Core i5-12490F has a 65W TDP and uses Intel Socket 1700. This makes the AMD part significantly lower-power, but the Intel chip has a higher boost clock.

Q: Which CPU has integrated graphics?

A: Only the AMD Ryzen 5 PRO 4655GE includes integrated graphics, featuring Radeon Vega 7. The Intel Core i5-12490F lists no integrated graphics, meaning a discrete GPU is required for display output.

Architecture Differences

The two processors represent fundamentally different design philosophies. The AMD Ryzen 5 PRO 4655GE is built on the Zen 2 architecture with the Renoir codename, fabricated on a 7 nm process at TSMC. Intel's Core i5-12490F uses the Alder Lake architecture, codenamed Alder Lake-S, on Intel's 10 nm process. The AMD chip integrates 9,800 million transistors on a 156 mm² die, while Intel's die is slightly larger at 163 mm² but has no transistor count listed.

Both CPUs feature 6 cores and 12 threads, making them directly comparable in thread count. However, cache hierarchies differ substantially. The AMD part has 64 KB of L1 cache per core, 512 KB of L2 per core, and 8 MB of shared L3 cache. Intel's design uses larger caches across the board: 80 KB of L1 per core, 1.25 MB of L2 per core, and 20 MB of shared L3 cache. That gives Intel a 12 MB advantage in L3 alone, which helps explain its performance edge in cache-sensitive workloads.

Clock speeds also differ. The AMD Ryzen 5 PRO 4655GE runs at a 3.30 GHz base clock and 4.20 GHz boost clock. Intel's Core i5-12490F has a lower 3.00 GHz base clock but a significantly higher 4.60 GHz boost clock. The higher boost clock, combined with the larger cache, gives Intel a clear single-thread advantage in the benchmark data.

Process node and foundry choices further separate the two. AMD uses TSMC's 7 nm node, while Intel uses its own 10 nm process. Despite AMD's smaller node, the Intel chip delivers better performance across all tested workloads. Power envelopes also differ: AMD's 35W TDP is nearly half of Intel's 65W TDP, making the Ryzen part more power-efficient on paper, though the performance gap is consistent and large.

Platform features diverge as well. The AMD chip supports ECC memory, while Intel does not. AMD also specifies Gen 3 PCIe with 20 lanes (CPU only), whereas Intel supports Gen 5 PCIe with 20 lanes (CPU only). Memory support shows Intel supporting both DDR4 and DDR5, while AMD is limited to DDR4. The AMD part includes Radeon Vega 7 integrated graphics; Intel has no iGPU at all.

The Verdict

The data presents a one-sided comparison. The Intel Core i5-12490F wins every single head-to-head benchmark, with no exceptions. Across Cinebench R15, R20, and R23, both single-core and multi-core, Intel leads by roughly 30%. PassMark workloads show Intel ahead by margins ranging from 3.6% in data encryption to 67.8% in prime number finding. The average benchmark scores are nearly identical, but that is because the AMD chip's percentile position is supported by its lower power draw and integrated graphics, not by raw compute performance.

Who should pick the AMD Ryzen 5 PRO 4655GE? Users who need a low-power processor with integrated graphics and ECC memory support. The 35W TDP makes it suitable for compact or power-constrained builds, and the Radeon Vega 7 iGPU removes the need for a discrete graphics card. The Renoir chip also fits the AM4 platform, which may be relevant for existing motherboard compatibility.

Who should pick the Intel Core i5-12490F? Users who prioritize raw performance in compute workloads. The 30% leads in Cinebench multi-core tests and the 40.9% lead in floating-point math show a decisive advantage for CPU-bound tasks. The lack of integrated graphics means a GPU is mandatory, but for systems that already include one, the Intel chip delivers stronger results across every measured category. The higher 65W TDP and support for both DDR4 and DDR5 memory give it more flexibility for performance-oriented builds.

There is no scenario in the data where the AMD chip wins a performance comparison. The choice comes down to platform requirements, power constraints, and the need for integrated graphics versus pure compute capability.

Specification Differences

The two processors differ in nearly every specification category except core count, thread count, and memory bus width. Both have 6 cores and 12 threads, and both use dual-channel memory.

| Specification | AMD Ryzen 5 PRO 4655GE | Intel Core i5-12490F |

|---|---|---|

| Base clock | 3.30 GHz | 3.00 GHz |

| Boost clock | 4.20 GHz | 4.60 GHz |

| TDP | 35W | 65W |

| Socket | AMD Socket AM4 | Intel Socket 1700 |

| Process node | 7 nm (TSMC) | 10 nm (Intel) |

| Die size | 156 mm² | 163 mm² |

| Transistors | 9,800 million | Not listed |

| L1 cache | 64 KB (per core) | 80 KB (per core) |

| L2 cache | 512 KB (per core) | 1.25 MB (per core) |

| L3 cache | 8 MB (shared) | 20 MB (shared) |

| Memory support | DDR4 | DDR4, DDR5 |

| Memory bandwidth | 51.2 GB/s | Not listed |

| ECC support | Yes | No |

| PCIe version | Gen 3, 20 lanes | Gen 5, 20 lanes |

| Integrated graphics | Radeon Vega 7 | None |

| Release date | 2022-11-10 | Not listed |

Both processors are locked (multiplier not unlocked), target the desktop market, and are currently listed as Active in production status.

Head-to-Head Benchmarks

The head-to-head results are remarkably consistent. In Cinebench R15 multi-core, Intel scores 1742 against AMD's 1213, a 30.4% lead. The single-core test shows Intel at 245 versus AMD's 171, a 30.2% margin. Moving to Cinebench R20, Intel leads multi-core with 7259 against 5058 (30.3%) and single-core with 1024 against 714 (30.3%). Cinebench R23 follows the same pattern: Intel's 17284 beats AMD's 12045 in multi-core (30.3%), and Intel's 2440 beats AMD's 1700 in single-core (30.3%).

The consistency across Cinebench versions suggests a fixed architectural advantage rather than workload-specific behavior. Intel's roughly 30% lead in both single and multi-threaded rendering indicates that the combination of higher boost clock and larger cache provides a uniform benefit.

PassMark results vary more widely. In floating-point math, Intel's 47326 crushes AMD's 27947, a 40.9% lead. Prime number finding shows the largest gap at 67.8% (Intel's 87 versus AMD's 28). Physics tests show Intel at 1345 against AMD's 592, a 56% difference. Extended instructions see Intel ahead by 26.3% (15993 vs 11792). Integer math gives Intel a 19.9% edge (60548 vs 48513).

Other PassMark workloads show narrower margins. Data compression favors Intel by 18.6% (237304 vs 193067). Random string sorting shows Intel at 23791 versus AMD's 21382, a 10.1% lead. Data encryption is the closest result: Intel's 12018 barely edges AMD's 11586, just 3.6% apart. The multithread test shows Intel at 20202 against AMD's 14171, a 29.9% difference. Single-thread results put Intel at 3682 versus AMD's 2660, a 27.8% margin.

The data also includes 3DMark tests for Intel only, with scores of 5923 for 16 threads, 1727 for 2 threads, 3133 for 4 threads, 4811 for 8 threads, 5936 for max threads, and 946 for single thread. No comparable AMD data is provided.

Where Each One Wins

The Intel Core i5-12490F wins in every benchmark category where both CPUs have data. There are no exceptions. The strongest Intel advantages appear in prime number calculation (67.8%), physics simulation (56%), and floating-point math (40.9%). These are compute-heavy workloads that benefit from Intel's higher boost clock and larger L3 cache.

The Intel chip also excels in rendering workloads, as shown by the consistent 30% leads across all three Cinebench versions, both single-core and multi-core. For users running CPU-based rendering, video encoding, or other multi-threaded production tasks, the data strongly favors Intel. The 20 MB of shared L3 cache versus AMD's 8 MB likely contributes to Intel's advantage in cache-sensitive workloads like data compression and extended instructions.

The AMD Ryzen 5 PRO 4655GE has no benchmark wins, but it has qualitative advantages that the data supports. The 35W TDP is nearly half of Intel's 65W, making it the better choice for low-power or thermally constrained systems. The integrated Radeon Vega 7 graphics mean no discrete GPU is required, which is a decisive factor for basic desktop use or office builds. ECC memory support is another differentiator, relevant for systems where data integrity is critical. The AM4 socket may also be advantageous for users with existing AM4 motherboards.

For users who already have a discrete GPU and need maximum compute performance, the Intel Core i5-12490F is the clear choice. For users building a compact, low-power system without a dedicated graphics card, the AMD Ryzen 5 PRO 4655GE offers a viable alternative, though with significantly lower performance. The 3.6% gap in data encryption is the only close contest; every other workload shows a substantial Intel advantage.