openai/mle-bench
File Complexity*
The distribution of files by complexity: the sum of the McCabe indexes of their units.
File Complexity Overall
  • There are 192 files with units, with 11,886 lines of code.
    • 0 very complex files (McCabe index sum 251+; 0 lines of code)
    • 0 complex files (McCabe index sum 126-250; 0 lines of code)
    • 0 medium complex files (McCabe index sum 51-125; 0 lines of code)
    • 9 slightly complex files (McCabe index sum 26-50; 1,792 lines of code)
    • 183 simple files (McCabe index sum 1-25; 10,094 lines of code)
  • 190 main files have no units (e.g. languages without unit analysis, or files without functions) and are not classified.
system0% | 0% | 0% | 15% | 84%
Legend:
251+
126-250
51-125
26-50
1-25


explore: grouped by folders | grouped by complexity
File Complexity per Extension
251+
126-250
51-125
26-50
1-25
py0% | 0% | 0% | 15% | 84%
File Complexity per Logical Decomposition
primary
251+
126-250
51-125
26-50
1-25
mlebench0% | 0% | 0% | 14% | 85%
experiments0% | 0% | 0% | 46% | 53%
extras0% | 0% | 0% | 0% | 100%
agents0% | 0% | 0% | 0% | 100%
environment0% | 0% | 0% | 0% | 100%
Most Complex Files (Top 50)

The McCabe index of a file grows with its size: per 100 lines tells a large but plain file from a dense one, and most complex unit whether the complexity sits in one unit or is spread over many.

File# lines# unitsMcCabe index
(sum)		per 100
lines		most complex
unit
282 12 49 17 17
mAP_evaluation.py
in mlebench/competitions/3d-object-detection-for-autonomous-vehicles
 215 18 45 21 10
utils.py
in mlebench
 190 21 41 22 8
grade.py
in mlebench/competitions/siim-covid19-detection
 98 4 37 38 29
data.py
in mlebench
 275 14 35 13 9
prepare.py
in mlebench/competitions/3d-object-detection-for-autonomous-vehicles
 324 1 33 10 33
prepare.py
in mlebench/competitions/mlsp-2013-birds
 143 2 27 19 22
grade_helpers.py
in mlebench
 171 7 26 15 15
grade.py
in mlebench/competitions/uw-madison-gi-tract-image-segmentation
 94 4 26 28 13
prepare.py
in mlebench/competitions/rsna-2022-cervical-spine-fracture-detection
 153 1 24 16 24
grade.py
in mlebench/competitions/vinbigdata-chest-xray-abnormalities-detection
 136 9 23 17 6
grade.py
in mlebench/competitions/tensorflow2-question-answering
 80 2 23 29 22
analyze.py
in extras/plagiarism_detector
 118 4 22 19 14
grade.py
in mlebench/competitions/alaska2-image-steganalysis
 64 4 21 33 8
utils.py
in environment
 90 5 21 23 7
prepare.py
in mlebench/competitions/smartphone-decimeter-2022
 104 2 20 19 16
utils.py
in mlebench/competitions
 167 9 20 12 7
grade.py
in mlebench
 110 4 20 18 8
grade.py
in mlebench/competitions/3d-object-detection-for-autonomous-vehicles
 85 3 19 22 11
grade.py
in mlebench/competitions/tgs-salt-identification-challenge
 93 3 19 20 9
familiarity.py
in experiments/familiarity
 213 5 18 8 10
grade.py
in mlebench/competitions/lmsys-chatbot-arena
 39 2 18 46 17
kuzushiji_metric.py
in mlebench/competitions/kuzushiji-recognition
 73 2 18 25 9
prepare.py
in mlebench/competitions/google-research-identify-contrails-reduce-global-warming
 122 1 17 14 17
cli.py
in mlebench
 200 1 17 9 17
prepare.py
in mlebench/competitions/cdiscount-image-classification-challenge
 95 1 15 16 15
prepare.py
in mlebench/competitions/AI4Code
 55 2 15 27 8
grade.py
in mlebench/competitions/icecube-neutrinos-in-deep-ice
 59 3 15 25 10
download_kernels.py
in extras/kernels
 121 2 15 12 12
run.py
in agents
 100 4 14 14 6
prepare.py
in mlebench/competitions/kuzushiji-recognition
 57 1 14 25 14
prepare.py
in mlebench/competitions/plant-seedlings-classification
 57 2 14 25 7
prepare.py
in mlebench/competitions/cassava-leaf-disease-classification
 84 1 14 17 14
prepare.py
in mlebench/competitions/freesound-audio-tagging-2019
 61 2 14 23 11
registry.py
in mlebench
 113 10 13 12 2
grade.py
in mlebench/competitions/osic-pulmonary-fibrosis-progression
 52 3 13 25 11
grade.py
in mlebench/competitions/AI4Code
 48 3 13 27 7
prepare.py
in mlebench/competitions/uw-madison-gi-tract-image-segmentation
 89 2 13 15 11
prepare.py
in mlebench/competitions/rsna-breast-cancer-detection
 104 1 13 13 13
prepare.py
in mlebench/competitions/ventilator-pressure-prediction
 44 1 13 30 13
prepare.py
in mlebench/competitions/iwildcam-2020-fgvc7
 112 1 13 12 13
prepare.py
in mlebench/competitions/statoil-iceberg-classifier-challenge
 80 1 13 16 13
prepare.py
in mlebench/competitions/denoising-dirty-documents
 93 2 13 14 10
start.py
in agents/opendevin
 134 3 12 9 7
grade.py
in mlebench/competitions/multi-modal-gesture-recognition
 35 3 12 34 8
prepare.py
in mlebench/competitions/herbarium-2021-fgvc8
 176 1 12 7 12
prepare.py
in mlebench/competitions/tgs-salt-identification-challenge
 113 1 12 11 12
prepare.py
in mlebench/competitions/herbarium-2020-fgvc7
 176 1 12 7 12
prepare.py
in mlebench/competitions/random-acts-of-pizza
 57 1 12 21 12
prepare.py
in mlebench/competitions/osic-pulmonary-fibrosis-progression
 72 2 11 15 10
About This Analysis
  • File complexity is the sum of the McCabe indexes (conditional complexity) of the units (methods, functions...) in a file.
  • Files are classified in five categories based on that sum: 1-25 (simple files), 26-50 (slightly complex files), 51-125 (medium complex files), 126-250 (complex files), 251+ (very complex files). The default bands are five times the unit complexity bands, as a file is a group of units.
  • Only main code files with units are classified. Files without units (languages without unit analysis, or files without functions) have no complexity to measure and are left out rather than counted as simple.
  • A very complex file holds many decisions, which often means it has too many responsibilities: a candidate to split, and a place where changes need more testing.
Learn more...