Intel Xeon E5-1650 v3 vs Intel Xeon E5-2643 v3 Comparison

Both processors are six-core Haswell-EP parts on the same 22 nm process, but the benchmark results show a consistent, if narrow, advantage for the Intel Xeon E5-1650 v3 across every tested workload. The data is unambiguous: the E5-1650 v3 wins all six head-to-head comparisons, with the E5-2643 v3 failing to take a single test. The margins are small, ranging from 1.4% to 1.6%, but they appear in every single-core and multi-core Cinebench test, making the E5-1650 v3 the faster chip in this matchup.

Head-to-Head Benchmarks

The most telling result comes from Cinebench R23 multi-core, where the E5-1650 v3 scores 8800 against the E5-2643 v3's 8682. That 1.4% delta translates to a 118-point gap, which is small enough to be within run-to-run variance on many systems, but it is still a win. The single-core R23 test shows a similar story: 1242 for the E5-1650 v3 versus 1225 for the E5-2643 v3, a 1.4% edge. These are the two most modern workloads in the dataset, and the E5-1650 v3 leads in both.

Moving to Cinebench R20, the pattern holds. The multi-core score is 3696 for the E5-1650 v3 and 3646 for the E5-2643 v3, again a 1.4% difference. Single-core R20 shows 521 versus 514, which is a 1.4% lead. The E5-1650 v3’s advantage is remarkably consistent at roughly 1.4% across all multi-core and R20 tests, suggesting a systematic clock-speed advantage rather than a workload-specific quirk.

The oldest test in the set, Cinebench R15, tells the same tale. In multi-core, the E5-1650 v3 scores 887 while the E5-2643 v3 scores 875, a 1.4% difference. In single-core, the margin is slightly larger at 1.6%, with scores of 125 and 123 respectively. This is the only test where the delta exceeds 1.4%, and it still favors the E5-1650 v3.

Looking at the aggregate benchmark average, the E5-1650 v3 posts 2545 versus 2511 for the E5-2643 v3. That is a 34-point gap, or roughly 1.4% overall. Both chips sit at the 49th percentile of all CPUs, meaning they are statistically equivalent in the broader market, but the direct comparison favors the E5-1650 v3 in every measurable way. The nearest rivals for the E5-1650 v3 include the Intel Xeon E5-4640 v3 at 2550 (-0.2%) and the AMD Ryzen 7 4800HS at 2557 (-0.4%), while the E5-2643 v3’s closest competitor is the Intel Xeon E-2144G at 2514 (-0.1%). The E5-1650 v3 also edges out the Intel Core i3-10325 (2530) by 0.6% and the Intel Xeon E-2244G (2527) by 0.7%, whereas the E5-2643 v3 trails the same E-2244G by 0.6% and beats the Intel Xeon E5-2630 v3 (2507) by only 0.2%.

Architecture Differences

Both processors are built on the Haswell-EP architecture with a 22 nm process node from Intel, and both use the Intel Socket 2011-3. The core and thread counts are identical at 6 cores and 12 threads, and both have the same transistor count of 2,600 million on a 356 mm² die. The L1 and L2 caches are the same at 64 KB and 256 KB per core respectively. The key architectural difference is in the L3 cache: the E5-1650 v3 has 15 MB shared, while the E5-2643 v3 has 20 MB shared. That 5 MB difference is the only significant cache divergence, and it does not translate into a performance win for the E5-2643 v3 in any benchmark.

The base clock differs slightly: the E5-1650 v3 runs at 3.50 GHz versus 3.40 GHz for the E5-2643 v3. Boost clocks are 3.80 GHz and 3.70 GHz respectively. The E5-1650 v3 also has an unlocked multiplier, while the E5-2643 v3 does not, meaning the E5-1650 v3 can be overclocked if the platform allows it. The TDP is 140 W for the E5-1650 v3 and 135 W for the E5-2643 v3, a 5 W difference that is negligible for most server or workstation cooling solutions.

Memory support is identical: both support DDR4 with a quad-channel memory bus and 68.3 GB/s of bandwidth, and both support ECC memory. PCIe connectivity is the same at Gen 3 with 40 lanes from the CPU. Neither chip has integrated graphics, and both are marked as end-of-life with a release date of 2014-09-07. The part numbers differ (QFSTSR20J for the E5-1650 v3, SR204SR1XQ for the E5-2643 v3), but that is a manufacturing identifier, not a functional difference.

FAQ

Q: Which CPU has the higher clock speed?

A: The Intel Xeon E5-1650 v3 has a base clock of 3.50 GHz and a boost clock of 3.80 GHz, while the Intel Xeon E5-2643 v3 runs at 3.40 GHz base and 3.70 GHz boost. This 100 MHz advantage at both ends contributes to the E5-1650 v3’s consistent benchmark wins.

Q: Do both processors support ECC memory?

A: Yes, both the E5-1650 v3 and the E5-2643 v3 support ECC memory. They also share the same DDR4 memory type, quad-channel memory bus, and 68.3 GB/s memory bandwidth.

Q: Is there any benchmark where the E5-2643 v3 wins?

A: No. The head-to-head data shows the E5-1650 v3 winning all six Cinebench tests (R15, R20, and R23 in both single-core and multi-core). The E5-2643 v3 has zero wins.

Q: What is the difference in L3 cache size?

A: The E5-2643 v3 has 20 MB of shared L3 cache, while the E5-1650 v3 has 15 MB. Despite having 5 MB more cache, the E5-2643 v3 still loses all benchmark comparisons.

Q: Can either CPU be overclocked?

A: The E5-1650 v3 has an unlocked multiplier, so it can be overclocked. The E5-2643 v3 has a locked multiplier, meaning it cannot be adjusted in the same way. The E5-1650 v3’s TDP of 140 W versus 135 W for the E5-2643 v3 gives it a bit more thermal headroom for such adjustments.

Q: How do these chips compare to modern mainstream CPUs?

A: Both sit at the 49th percentile of all CPUs. The E5-1650 v3’s nearest rival is the AMD Ryzen 7 4800HS, which scores 2557 and is 0.4% faster, while the E5-2643 v3’s nearest rival is the Intel Xeon E-2144G at 2514, which is 0.1% faster. They are roughly on par with a mid-range laptop chip from a few years later.

Specification Differences

The only specification fields where the two processors differ are clock speed, TDP, L3 cache, multiplier unlock status, launch MSRP, and part number. The E5-1650 v3 has a base clock of 3.50 GHz versus 3.40 GHz, a boost clock of 3.80 GHz versus 3.70 GHz, and a TDP of 140 W versus 135 W. The L3 cache is 15 MB on the E5-1650 v3 and 20 MB on the E5-2643 v3. The E5-1650 v3 has an unlocked multiplier; the E5-2643 v3 does not. The E5-2643 v3 has a launch MSRP of $1552; the E5-1650 v3 has no listed launch MSRP. The part numbers are QFSTSR20J for the E5-1650 v3 and SR204SR1XQ for the E5-2643 v3.

All other specifications are identical: 6 cores, 12 threads, 22 nm process, Haswell-EP architecture, Intel Socket 2011-3, 2,600 million transistors, 356 mm² die size, 64 KB L1 and 256 KB L2 per core, DDR4 quad-channel memory with 68.3 GB/s bandwidth, ECC support, PCIe Gen 3 with 40 lanes, no integrated graphics, server/workstation market segment, end-of-life production status, and a release date of 2014-09-07.

The Verdict

The data points to a clear winner: the Intel Xeon E5-1650 v3. It wins every benchmark in the head-to-head comparison, with a 1.4% advantage in most tests and a 1.6% edge in Cinebench R15 single-core. The E5-1650 v3 has higher base and boost clocks, an unlocked multiplier for potential overclocking, and still posts a higher average benchmark score of 2545 versus 2511. The E5-2643 v3’s only advantages are a larger 20 MB L3 cache and a lower TDP of 135 W, but neither translates into a performance win. The 5 MB cache difference does not help in any of the six tested workloads, and the 5 W TDP reduction is unlikely to matter in a server or workstation chassis.

For a buyer choosing between these two specific parts, the E5-1650 v3 is the better choice on raw performance. The fact that it also has an unlocked multiplier, unlike the locked E5-2643 v3, gives it additional flexibility for users willing to overclock. The E5-2643 v3’s launch MSRP of $1552 is listed in the data, but the E5-1650 v3 has no listed MSRP, so a direct price comparison is not possible from the facts provided. However, on benchmark evidence alone, the E5-1650 v3 is the superior processor.

Where Each One Wins

The E5-1650 v3 wins in every benchmark category that matters for general performance. It is ahead in single-core and multi-core tests across Cinebench R15, R20, and R23. That means it is better suited for workloads that are lightly threaded, such as older applications or those with a single dominant thread, as well as heavily threaded tasks like rendering or encoding. The 1.4% to 1.6% margins are not large, but they are consistent, and the unlocked multiplier on the E5-1650 v3 offers headroom to extend that lead further.

The E5-2643 v3 does not win any benchmark, but it has a few practical advantages that are not reflected in the scores. Its 20 MB L3 cache is 5 MB larger, which could theoretically help in cache-sensitive workloads, though the data shows no benefit in the tested scenarios. Its TDP is 5 W lower, which might simplify cooling in a dense server environment where every watt counts. The E5-2643 v3 also has a listed launch MSRP of $1552, which is a data point for reference, though the E5-1650 v3’s lack of a listed MSRP prevents a direct cost comparison.

In practice, the E5-1650 v3 is the pick for anyone who wants the fastest possible performance from these two Haswell-EP chips. The E5-2643 v3 is not without merit, but its advantages are speculative (cache size) or minor (power draw), and they do not show up in the benchmark results. The E5-1650 v3 is the benchmark winner, and that is the metric that matters most.