CPU Comparison

The Intel Core i5-3335S and AMD A12-9800 are two desktop processors from different eras and design philosophies, yet benchmark data places them in the same performance tier. The AMD A12-9800 holds a slight edge across every measured workload, but the Intel chip counters with architectural advantages that matter for platform flexibility. The average benchmark scores are nearly identical, 1083 for the Intel versus 1081 for the AMD, and both sit at the 30th percentile of all CPUs. This is a head-to-head where the winner takes a narrow margin, and the loser compensates with a different set of platform attributes.

Where Each One Wins

The AMD A12-9800 wins every single benchmark in the head-to-head comparison, but the margins are uniformly small. In multi-threaded workloads, the AMD part leads by 0.6% in both Cinebench R15 (316 versus 314) and Cinebench R20 (1318 versus 1310), and again by 0.6% in Cinebench R23 (3140 versus 3121). Single-threaded workloads show a slightly larger gap: the AMD part wins Cinebench R20 single-core by 1.1% (186 versus 184) and Cinebench R23 single-core by 0.7% (443 versus 440). These are not decisive victories, but they are consistent across all five tests, indicating a small but real performance advantage in CPU-bound tasks.

The Intel Core i5-3335S wins in the areas that are not measured by raw compute benchmarks. It supports PCIe Gen 3 with 16 lanes from the CPU, exactly double the 8 lanes offered by the AMD part. This gives the Intel platform more headroom for discrete graphics or other expansion cards. The Intel chip also has a larger shared L3 cache at 6 MB, compared to the AMD part’s 2 MB L2 cache with no L3 at all. For workloads that benefit from a large unified cache pool, the Intel architecture has a structural advantage that the benchmark scores do not capture.

Architecture Differences

The two processors represent fundamentally different design targets. The Intel Core i5-3335S is built on the Ivy Bridge architecture using a 22 nm process from Intel, packing 1,480 million transistors into a 160 mm² die. The AMD A12-9800 uses the Excavator architecture on a 28 nm process from GlobalFoundries, with 3,100 million transistors on a 250 mm² die. The AMD part has more than double the transistor count and a substantially larger die, largely due to its integrated Radeon R7 graphics and the older process node.

Cache layouts diverge sharply. The Intel chip uses a three-level hierarchy: 64 KB of L1 per core, 256 KB of L2 per core, and a shared 6 MB L3 cache. The AMD part uses a two-level hierarchy with 320 KB of total L1 and 2 MB of L2, with no L3 cache present. The Intel design’s shared L3 cache is a significant architectural difference, as it allows all four cores to access a common pool of fast memory.

Memory support also separates the two. The Intel chip uses DDR3 memory in a dual-channel configuration, while the AMD part uses DDR4 memory with a rated bandwidth of 38.4 GB/s. The AMD processor’s newer memory standard provides higher theoretical bandwidth, though the benchmarks do not show a decisive real-world impact. The Intel chip is locked to the LGA 1155 socket, while the AMD part uses Socket AM4, which is a more modern platform with longer potential upgrade paths.

Clock speeds favor the AMD part significantly. The AMD A12-9800 runs at a 3.80 GHz base clock and boosts to 4.20 GHz, while the Intel Core i5-3335S runs at a 2.70 GHz base clock and boosts to 3.20 GHz. Despite the 1.1 GHz base clock disadvantage, the Intel chip nearly matches the AMD part in every benchmark, which points to the efficiency of the Ivy Bridge architecture and its larger cache.

Head-to-Head Benchmarks

The Cinebench R15 multi-core test sets the tone: the AMD A12-9800 scores 316 against the Intel’s 314, a 0.6% advantage. This is a workload that scales with cores and threads, and both chips have exactly four of each, so the result is a direct comparison of per-core efficiency and clock speed. The AMD part’s higher clocks give it the edge, but the margin is minimal.

In Cinebench R20 multi-core, the pattern repeats. The AMD scores 1318, the Intel scores 1310, again a 0.6% difference. The R23 multi-core test shows the same 0.6% gap, with the AMD at 3140 and the Intel at 3121. These three multi-core results are remarkably consistent, suggesting that the performance difference is a fixed percentage regardless of the specific rendering workload.

Single-threaded tests show a slightly larger spread. Cinebench R20 single-core has the AMD at 186 and the Intel at 184, a 1.1% advantage for AMD. Cinebench R23 single-core has the AMD at 443 and the Intel at 440, a 0.7% gap. The single-core advantage for AMD is marginally bigger than the multi-core gap, which is logical given the 1.1 GHz base clock difference and the lack of L3 cache on the AMD part.

The Geekbench tests are not part of the direct head-to-head set, but the Intel chip’s scores are available: 1647 in multi-core and 562 in single-core. The AMD part has no Geekbench scores listed, so no comparison can be made for that suite. The Intel chip’s average benchmark score across all listed tests is 1083, versus 1081 for the AMD, a rounding-level difference that reinforces the overall parity.

FAQ

Q: Which processor is faster in multi-threaded workloads?

A: The AMD A12-9800 wins all three multi-core Cinebench tests. It scores 316 versus 314 in R15, 1318 versus 1310 in R20, and 3140 versus 3121 in R23, each a 0.6% advantage over the Intel Core i5-3335S.

Q: How do the single-threaded scores compare?

A: The AMD A12-9800 also wins single-threaded tests, with a 1.1% lead in Cinebench R20 (186 versus 184) and a 0.7% lead in Cinebench R23 (443 versus 440).

Q: What is the cache difference between the two chips?

A: The Intel Core i5-3335S has 64 KB L1 and 256 KB L2 per core, plus a 6 MB shared L3 cache. The AMD A12-9800 has 320 KB total L1 and 2 MB L2, with no L3 cache at all.

Q: Do the two processors support the same memory type?

A: No. The Intel chip supports DDR3 memory in dual-channel mode. The AMD chip supports DDR4 memory with a rated bandwidth of 38.4 GB/s.

Q: Which processor has a higher clock speed?

A: The AMD A12-9800 runs at a 3.80 GHz base and 4.20 GHz boost. The Intel Core i5-3335S runs at a 2.70 GHz base and 3.20 GHz boost.

Q: What is the PCIe lane difference?

A: The Intel chip provides 16 PCIe Gen 3 lanes from the CPU. The AMD chip provides 8 PCIe Gen 3 lanes.

The Verdict

The data points to a clear but narrow victory for the AMD A12-9800 in raw CPU performance. It wins all five head-to-head benchmarks, with margins ranging from 0.6% to 1.1%. For any workload that relies purely on the processor’s compute throughput, the AMD part is the faster choice, albeit by a small margin that most users would not notice in daily use.

The Intel Core i5-3335S, however, is not without a case. Its 6 MB shared L3 cache and 16 PCIe Gen 3 lanes give it a platform-level advantage that the benchmarks do not quantify. The larger cache can benefit workloads with repeated data access patterns, and the extra PCIe lanes allow for more expansion options. The Intel chip also achieves near-parity despite a 1.1 GHz lower base clock, which speaks to the efficiency of the Ivy Bridge architecture.

For a user building a system with a discrete GPU and multiple expansion cards, the Intel chip’s extra PCIe lanes and larger cache make it the more flexible choice. For a user who values the highest possible CPU benchmark scores, even by a fraction of a percent, the AMD part delivers. Both processors sit at the 30th percentile of all CPUs, so neither is a high-end option. The AMD A12-9800 is the benchmark winner, but the Intel Core i5-3335S is the more balanced platform.

Specification Differences

| Specification | Intel Core i5-3335S | AMD A12-9800 |

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

| Architecture | Ivy Bridge | Excavator |

| Process Node | 22 nm | 28 nm |

| Foundry | Intel | GlobalFoundries |

| Transistors | 1,480 million | 3,100 million |

| Die Size | 160 mm² | 250 mm² |

| Base Clock | 2.70 GHz | 3.80 GHz |

| Boost Clock | 3.20 GHz | 4.20 GHz |

| L1 Cache | 64 KB (per core) | 320 KB (total) |

| L2 Cache | 256 KB (per core) | 2 MB (total) |

| L3 Cache | 6 MB (shared) | None |

| Memory Support | DDR3 | DDR4 |

| Memory Bandwidth | Not listed | 38.4 GB/s |

| PCIe | Gen 3, 16 Lanes (CPU only) | Gen 3, 8 Lanes (CPU only) |

| Integrated Graphics | Intel HD 4000 | Radeon R7 |

| Socket | Intel Socket 1155 | AMD Socket AM4 |

| Release Date | 2012-10-31 | 2017-07-26 |

| Production Status | Not listed | Active |