AMD Ryzen 9 7945HX vs Intel Core i7-13790F Comparison

Where Each One Wins

The benchmark split is clear: the Intel Core i7-13790F wins 6 of the 15 head-to-head tests, while the AMD Ryzen 9 7945HX wins 9. The Intel chip dominates in single-core and lightly threaded workloads, while the AMD processor takes the majority of multi-threaded and data-heavy tasks.

The Intel Core i7-13790F is the choice for latency-sensitive, per-thread performance. Its single-core wins include a 63.3% lead in Cinebench R15 single-core, a 157.6% lead in Cinebench R23 single-core, and a 4.3% edge in Passmark single-thread. It also wins Passmark physics by 20.7%, suggesting better responsiveness in tasks that depend on one or two cores.

The AMD Ryzen 9 7945HX is the throughput king. It wins all of the Passmark compute workloads except physics and single-thread: data compression by 19.8%, data encryption by 25.8%, extended instructions by 32.8%, find prime numbers by 27.1%, floating point math by 10.4%, integer math by 27%, multithread by 18%, and random string sorting by 28.3%. Its biggest single win is the 32.5% lead in Cinebench R15 multicore.

The interesting outlier is Cinebench R23 multicore, where the Intel part wins by 5.8% despite losing the older R15 multicore test by a wide margin. This suggests the Intel chip scales better in the newer Cinebench version, while the AMD chip loses ground there. Overall, the AMD part is the better all-around multi-core performer, but the Intel chip holds its own in the most recent Cinebench multicore test.

Architecture Differences

The two chips come from fundamentally different design philosophies. The Intel Core i7-13790F is a desktop part built on Intel's Raptor Lake architecture, using a 10 nm process from Intel's own foundry. It has 16 cores and 24 threads, a base clock of 2.10 GHz, and a boost clock of 5.20 GHz. Its thermal design power is 65 watts, and it uses the Intel Socket 1700.

The AMD Ryzen 9 7945HX is a mobile processor from AMD's Dragon Range family, built on Zen 4 architecture. It uses a 5 nm process from TSMC, with a transistor count of 13,140 million across two chiplets, each measuring 71 mm². It has 16 cores and 32 threads, a base clock of 2.50 GHz, and a boost clock of 5.40 GHz. Its thermal design power is lower at 55 watts, and it uses the AMD Socket FL1.

Cache layouts differ substantially. The Intel chip has 80 KB of L1 per core, 2 MB of L2 per core, and 33 MB of shared L3. The AMD chip has smaller L1 and L2 per core (64 KB and 1 MB respectively) but a much larger 64 MB shared L3. This larger L3 cache is likely a factor in the AMD chip's strong showing in data compression and encryption workloads, which benefit from larger on-die working sets.

Memory support also differs. The Intel part supports both DDR4 and DDR5, while the AMD part supports DDR5 only. Both are dual-channel. The AMD chip lists a memory bandwidth of 83.2 GB/s, while the Intel chip does not list a bandwidth figure. The AMD chip supports ECC memory, the Intel chip does not.

PCIe lanes differ as well: the Intel chip offers Gen 5 with 20 lanes from the CPU, while the AMD chip offers Gen 5 with 28 lanes. The AMD chip also includes integrated Radeon 610M graphics, while the Intel chip has no integrated graphics listed. The AMD chip has an unlocked multiplier, the Intel chip does not.

Head-to-Head Benchmarks

The largest win for the Intel Core i7-13790F is in Cinebench R23 single-core, where it scores 4998 against the AMD's 1940, a 157.6% advantage. This is a dominant result, more than two and a half times the AMD score. The Intel chip also wins Cinebench R15 single-core by 63.3% (503 vs 308) and Passmark single-thread by 4.3% (4212 vs 4040). In Passmark physics, the Intel chip wins 3017 to 2500, a 20.7% lead.

The AMD Ryzen 9 7945HX's biggest win is in Cinebench R15 multicore, where it scores 5289 against the Intel's 3568, a 32.5% lead. It also wins Passmark extended instructions by 32.8% (51834 vs 34828), Passmark random string sorting by 28.3% (81736 vs 58607), Passmark find prime numbers by 27.1% (284 vs 207), and Passmark integer math by 27% (207524 vs 151416).

In the remaining multi-threaded tests, the AMD chip leads by smaller margins: data encryption by 25.8% (42703 vs 31703), data compression by 19.8% (707249 vs 567473), Passmark multithread by 18% (54548 vs 44737), and floating point math by 10.4% (123390 vs 110512).

The one multicore test the Intel chip wins is Cinebench R23 multicore: 35404 vs 33459, a 5.8% margin. This is notable because it flips the R15 multicore result. The data suggests the Intel architecture handles the newer Cinebench workload more efficiently, while the AMD chip's advantage in older Cinebench and most Passmark compute tests points to a broader multi-threaded strength.

FAQ

Q: Which processor is faster in single-core workloads?

A: The Intel Core i7-13790F wins every single-core test. It leads by 63.3% in Cinebench R15 single-core, 157.6% in Cinebench R23 single-core, and 4.3% in Passmark single-thread.

Q: Does the AMD Ryzen 9 7945HX beat the Intel chip in all multi-threaded tests?

A: No. The AMD chip wins most multi-threaded tests, including Cinebench R15 multicore by 32.5% and all Passmark compute workloads except physics. However, the Intel chip wins Cinebench R23 multicore by 5.8%.

Q: Which chip has more threads?

A: The AMD Ryzen 9 7945HX has 32 threads, while the Intel Core i7-13790F has 24 threads. Both have 16 cores.

Q: What is the difference in thermal design power?

A: The Intel Core i7-13790F has a thermal design power of 65 watts, while the AMD Ryzen 9 7945HX has a lower 55 watts.

Q: Which chip supports ECC memory?

A: The AMD Ryzen 9 7945HX supports ECC memory, while the Intel Core i7-13790F does not.

Q: Which chip has a larger L3 cache?

A: The AMD Ryzen 9 7945HX has 64 MB of shared L3 cache, nearly double the Intel Core i7-13790F's 33 MB.

The Verdict

For single-threaded and low-thread-count tasks, the Intel Core i7-13790F is the clear winner. Its Cinebench R23 single-core score is 157.6% higher, which is a massive gap. Users running applications that rely on one or two cores, such as older games or lightly threaded productivity tools, will see a substantial advantage from the Intel chip. Its Passmark physics win by 20.7% also suggests better performance in physics simulation that uses fewer threads.

For heavily parallel workloads, the AMD Ryzen 9 7945HX is the better choice. It wins data compression, encryption, extended instructions, prime number finding, floating point math, integer math, multithread, and random string sorting by margins ranging from 10.4% to 32.8%. Its larger L3 cache and higher thread count (32 vs 24) likely contribute to these wins. The only exception is Cinebench R23 multicore, where the Intel chip wins by 5.8%, so any user specifically running that workload should prefer the Intel part.

The overall benchmark averages place the Intel chip slightly ahead: its average benchmark score is 63080 against the AMD's 60099. The Intel chip also sits at the 93rd percentile of all CPUs, versus the AMD chip's 92nd percentile. However, the Intel chip's nearest rival, the Intel Core Ultra 7 265HX, scores 63173, just 0.1% higher, while the AMD chip's nearest rival, the AMD Ryzen 7 8745HX, scores 60104, essentially identical (0% delta).

The decision comes down to workload. Choose the Intel Core i7-13790F for single-core speed and newer Cinebench multicore performance. Choose the AMD Ryzen 9 7945HX for broad multi-threaded throughput, especially in encryption, compression, and math-heavy tasks. The AMD chip also offers ECC memory support, integrated graphics, and an unlocked multiplier, which may matter for specific use cases.

Specification Differences

| Specification | Intel Core i7-13790F | AMD Ryzen 9 7945HX |

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

| Cores | 16 | 16 |

| Threads | 24 | 32 |

| Base Clock | 2.10 GHz | 2.50 GHz |

| Boost Clock | 5.20 GHz | 5.40 GHz |

| Thermal Design Power | 65 W | 55 W |

| Socket | Intel Socket 1700 | AMD Socket FL1 |

| Architecture | Raptor Lake | Zen 4 |

| Codename | Raptor Lake-S | Dragon Range |

| Process Node | 10 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | Not listed | 13,140 million |

| Die Size | 257 mm² | 2x 71 mm² |

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

| L2 Cache | 2 MB (per core) | 1 MB (per core) |

| L3 Cache | 33 MB (shared) | 64 MB (shared) |

| Memory Support | DDR4, DDR5 | DDR5 |

| Memory Bus | Dual-channel | Dual-channel |

| Memory Bandwidth | Not listed | 83.2 GB/s |

| ECC Memory | No | Yes |

| PCIe | Gen 5, 20 Lanes (CPU only) | Gen 5, 28 Lanes (CPU only) |

| Integrated Graphics | None | Radeon 610M |

| Market Segment | Desktop | Mobile |

| Release Date | 2023-02-09 | 2023-01-03 |

| Launch MSRP | $441 | Not listed |

| Multiplier Unlocked | No | Yes |