openai / simple-evals
File Size

The distribution of size of files (measured in lines of code).

Intro
  • File size measurements show the distribution of size of files.
  • Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
  • It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.
Learn more...
File Size Overall
  • There are 18 files with 5,288 lines of code.
    • 1 very long files (2,535 lines of code)
    • 1 long files (528 lines of code)
    • 3 medium size files (990 lines of code)
    • 4 small files (590 lines of code)
    • 9 very small files (645 lines of code)
47% | 9% | 18% | 11% | 12%
Legend:
1001+
501-1000
201-500
101-200
1-100


explore: grouped by folders | grouped by size | sunburst | 3D view
File Size per Extension
1001+
501-1000
201-500
101-200
1-100
ipynb100% | 0% | 0% | 0% | 0%
py0% | 19% | 35% | 21% | 23%
File Size per Logical Decomposition
primary
1001+
501-1000
201-500
101-200
1-100
healthbench_scripts100% | 0% | 0% | 0% | 0%
ROOT0% | 21% | 40% | 24% | 13%
sampler0% | 0% | 0% | 0% | 100%
Longest Files (Top 18)
File# lines# units
healthbench_analysis.ipynb
in healthbench_scripts
 2535 -
528 16
496 1
272 8
222 20
common.py
in root
 194 12
146 6
134 1
116 2
91 5
89 3
88 5
86 5
80 5
65 5
63 2
49 2
types.py
in root
 34 2
Files With Most Units (Top 17)
File# lines# units
222 20
528 16
common.py
in root
 194 12
272 8
146 6
80 5
88 5
91 5
65 5
86 5
89 3
63 2
49 2
116 2
types.py
in root
 34 2
496 1
134 1
Files With Long Lines (Top 5)

There are 5 files with lines longer than 120 characters. In total, there are 65 long lines.

File# lines# units# long lines
healthbench_analysis.ipynb
in healthbench_scripts
 2535 - 57
528 16 5
89 3 1
91 5 1
272 8 1
Correlations

File Size vs. Commits (all time): 18 points

healthbench_eval.py x: 4 commits (all time) y: 528 lines of code simple_evals.py x: 26 commits (all time) y: 496 lines of code healthbench_scripts/healthbench_analysis.ipynb x: 3 commits (all time) y: 2535 lines of code browsecomp_eval.py x: 8 commits (all time) y: 86 lines of code common.py x: 11 commits (all time) y: 194 lines of code drop_eval.py x: 5 commits (all time) y: 222 lines of code gpqa_eval.py x: 9 commits (all time) y: 63 lines of code healthbench_meta_eval.py x: 2 commits (all time) y: 272 lines of code math_eval.py x: 8 commits (all time) y: 49 lines of code mgsm_eval.py x: 8 commits (all time) y: 146 lines of code mmlu_eval.py x: 7 commits (all time) y: 116 lines of code sampler/chat_completion_sampler.py x: 3 commits (all time) y: 80 lines of code sampler/claude_sampler.py x: 3 commits (all time) y: 91 lines of code sampler/o_chat_completion_sampler.py x: 4 commits (all time) y: 65 lines of code sampler/responses_sampler.py x: 9 commits (all time) y: 88 lines of code simpleqa_eval.py x: 12 commits (all time) y: 89 lines of code types.py x: 3 commits (all time) y: 34 lines of code run_multilingual_mmlu.py x: 7 commits (all time) y: 134 lines of code
2535.0
lines of code
  min: 34.0
  average: 293.78
  25th percentile: 76.25
  median: 103.5
  75th percentile: 234.5
  max: 2535.0
0 26.0
commits (all time)
min: 2.0 | average: 7.33 | 25th percentile: 3.0 | median: 7.0 | 75th percentile: 9.0 | max: 26.0

File Size vs. Contributors (all time): 18 points

healthbench_eval.py x: 3 contributors (all time) y: 528 lines of code simple_evals.py x: 9 contributors (all time) y: 496 lines of code healthbench_scripts/healthbench_analysis.ipynb x: 2 contributors (all time) y: 2535 lines of code browsecomp_eval.py x: 4 contributors (all time) y: 86 lines of code common.py x: 7 contributors (all time) y: 194 lines of code drop_eval.py x: 5 contributors (all time) y: 222 lines of code gpqa_eval.py x: 8 contributors (all time) y: 63 lines of code healthbench_meta_eval.py x: 2 contributors (all time) y: 272 lines of code math_eval.py x: 7 contributors (all time) y: 49 lines of code mgsm_eval.py x: 7 contributors (all time) y: 146 lines of code mmlu_eval.py x: 6 contributors (all time) y: 116 lines of code sampler/chat_completion_sampler.py x: 3 contributors (all time) y: 80 lines of code sampler/claude_sampler.py x: 3 contributors (all time) y: 91 lines of code sampler/o_chat_completion_sampler.py x: 4 contributors (all time) y: 65 lines of code simpleqa_eval.py x: 7 contributors (all time) y: 89 lines of code types.py x: 3 contributors (all time) y: 34 lines of code run_multilingual_mmlu.py x: 3 contributors (all time) y: 134 lines of code
2535.0
lines of code
  min: 34.0
  average: 293.78
  25th percentile: 76.25
  median: 103.5
  75th percentile: 234.5
  max: 2535.0
0 9.0
contributors (all time)
min: 2.0 | average: 4.83 | 25th percentile: 3.0 | median: 4.0 | 75th percentile: 7.0 | max: 9.0

File Size vs. Commits (30 days): 0 points

No data for "commits (30d)" vs. "lines of code".

File Size vs. Contributors (30 days): 0 points

No data for "contributors (30d)" vs. "lines of code".

File Size vs. Commits (90 days): 2 points

healthbench_eval.py x: 2 commits (90d) y: 528 lines of code simple_evals.py x: 2 commits (90d) y: 496 lines of code
528.0
lines of code
  min: 496.0
  average: 512.0
  25th percentile: 496.0
  median: 512.0
  75th percentile: 528.0
  max: 528.0
0 2.0
commits (90d)
min: 2.0 | average: 2.0 | 25th percentile: 2.0 | median: 2.0 | 75th percentile: 2.0 | max: 2.0

File Size vs. Contributors (90 days): 2 points

healthbench_eval.py x: 2 contributors (90d) y: 528 lines of code simple_evals.py x: 2 contributors (90d) y: 496 lines of code
528.0
lines of code
  min: 496.0
  average: 512.0
  25th percentile: 496.0
  median: 512.0
  75th percentile: 528.0
  max: 528.0
0 2.0
contributors (90d)
min: 2.0 | average: 2.0 | 25th percentile: 2.0 | median: 2.0 | 75th percentile: 2.0 | max: 2.0