CEC2017 Benchmark Results: Optimal Values and Deviations for 100-Dimensional Functions

Yang Cao published a dataset on May 13, 2026, containing numerical results from benchmarking eight evolutionary optimization algorithms. The data includes average optimal values and standard deviations from 30 runs of algorithms like DE, SaDE, SHADE, ILSHADE, jSO, MPEDE, LSHADE, and RL-DE. The evaluation covers 29 test functions from the CEC2017 benchmark suite in 100 dimensions.

Use Cases

• Comparing algorithm performance based on average optimal values across 30 runs.
• Analyzing algorithm stability based on reported standard deviations.
• Benchmarking new optimization methods against eight established algorithms (DE, SaDE, SHADE, ILSHADE, jSO, MPEDE, LSHADE, RL-DE).
• Studying the difficulty of 29 different 100-dimensional CEC2017 test functions.

Strengths

• Results are aggregated from 30 independent runs per algorithm, providing a measure of reliability.
• Compares eight distinct optimization algorithms, offering a broad performance overview.
• Evaluates performance on 29 different test functions, covering a range of problem landscapes.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 17.2 KB, indicating limited scope.

Provenance

Source

Yang Cao via figshare

Collection Method

Results from computational experiments running algorithms on benchmark functions.

Freshness

Last updated 2026-05-13 17:44:41; freshness should be verified.