openai / simple-evals
File Churn

File change frequency (churn) shows the distribution of file updates (days with at least one commit).

Overview
File Change Frequency Overall
  • There are 18 files with 5,288 lines of code.
    • 0 files changed more than 100 times (0 lines of code)
    • 0 files changed 51-100 times (0 lines of code)
    • 0 files changed 21-50 times (0 lines of code)
    • 4 files changed 6-20 times (802 lines of code)
    • 14 files changed 1-5 times (4,486 lines of code)
0% | 0% | 0% | 15% | 84%
Legend:
101+
51-100
21-50
6-20
1-5

explore: grouped by folders | grouped by update frequency | data
Contributors Count Frequency Overall
  • There are 18 files with 5,288 lines of code.
    • 0 files changed by more than 25 contributors (0 lines of code)
    • 0 files changed by 11-25 contributors (0 lines of code)
    • 7 files changed by 6-10 contributors (1,153 lines of code)
    • 11 files changed by 2-5 contributors (4,135 lines of code)
    • 0 files changed by 1 contributor (0 lines of code)
0% | 0% | 21% | 78% | 0%
Legend:
26+
11-25
6-10
2-5
1

explore: grouped by folders | grouped by contributors count | data
File Change Frequency per File Extension
py, md, txt, gitignore, ipynb
File Change Frequency per Extension
The number of recorded file updates
101+
51-100
21-50
6-20
1-5
py0% | 0% | 0% | 29% | 70%
ipynb0% | 0% | 0% | 0% | 100%
File Change Frequency per Logical Decomposition
primary
primary (file change frequency)
The number of recorded file updates
101+
51-100
21-50
6-20
1-5
ROOT0% | 0% | 0% | 33% | 66%
healthbench_scripts0% | 0% | 0% | 0% | 100%
sampler0% | 0% | 0% | 0% | 100%
Most Frequently Changed Files (Top 18)

See data for all files...

File# lines# unitscreatedlast modified# changes
(days)		# contributorsline
churn		first
contributor		latest
contributor
496 1 2024-11-20 2026-04-22 12 9 +1188 / -128 jmcgrath@openai.com rahul-openai@users.noreply....
common.py
in root
 194 12 2024-05-13 2025-05-12 8 7 +391 / -30 openai@openai.com rahul@openai.com
63 2 2024-05-13 2025-05-12 7 8 +27 / -29 openai@openai.com rahul@openai.com
49 2 2024-04-12 2025-05-12 6 7 +48 / -105 openai@openai.com rahul@openai.com
88 5 2025-04-10 2025-05-12 5 4 +248 / -46 mgl@openai.com rahul@openai.com
89 3 2024-10-30 2025-05-12 5 7 +424 / -32 165065090+kzl-openai@users.... rahul@openai.com
116 2 2024-05-13 2025-05-12 5 6 +75 / -64 openai@openai.com rahul@openai.com
146 6 2024-05-13 2025-05-12 5 7 +29 / -25 openai@openai.com rahul@openai.com
134 1 2024-09-11 2025-02-01 4 3 +300 / -12 erik@openai.com shanth@openai.com
222 20 2024-05-13 2025-05-12 3 5 +16 / -16 openai@openai.com rahul@openai.com
types.py
in root
 34 2 2024-05-13 2025-05-12 2 3 +42 / -5 openai@openai.com rahul@openai.com
65 5 2025-01-31 2025-05-12 2 4 +170 / -10 erik@openai.com rahul@openai.com
80 5 2024-05-13 2025-05-12 2 3 +70 / -19 openai@openai.com rahul@openai.com
86 5 2025-04-10 2025-05-12 2 4 +307 / -17 165065090+kzl-openai@users.... rahul@openai.com
91 5 2024-05-13 2025-05-12 2 3 +81 / -24 openai@openai.com rahul@openai.com
528 16 2025-05-12 2026-04-22 2 3 +1362 / -0 151101053+rahul-openai@user... rahul-openai@users.noreply....
healthbench_analysis.ipynb
in healthbench_scripts
 2535 - 2025-05-12 2025-05-13 2 2 +5072 / -2 151101053+rahul-openai@user... 151101053+rahul-openai@user...
272 8 2025-05-12 2025-05-12 1 2 +672 / -0 151101053+rahul-openai@user... rahul@openai.com
Files With Most Churn (Top 18)
Based on the number of lines added and deleted across all commits.

See data for all files...

File# lines# unitscreatedlast modified# changes
(days)		# contributorsline
churn		first
contributor		latest
contributor
healthbench_analysis.ipynb
in healthbench_scripts
 2535 - 2025-05-12 2025-05-13 2 2 +5072 / -2 151101053+rahul-openai@user... 151101053+rahul-openai@user...
528 16 2025-05-12 2026-04-22 2 3 +1362 / -0 151101053+rahul-openai@user... rahul-openai@users.noreply....
496 1 2024-11-20 2026-04-22 12 9 +1188 / -128 jmcgrath@openai.com rahul-openai@users.noreply....
272 8 2025-05-12 2025-05-12 1 2 +672 / -0 151101053+rahul-openai@user... rahul@openai.com
89 3 2024-10-30 2025-05-12 5 7 +424 / -32 165065090+kzl-openai@users.... rahul@openai.com
common.py
in root
 194 12 2024-05-13 2025-05-12 8 7 +391 / -30 openai@openai.com rahul@openai.com
86 5 2025-04-10 2025-05-12 2 4 +307 / -17 165065090+kzl-openai@users.... rahul@openai.com
134 1 2024-09-11 2025-02-01 4 3 +300 / -12 erik@openai.com shanth@openai.com
88 5 2025-04-10 2025-05-12 5 4 +248 / -46 mgl@openai.com rahul@openai.com
65 5 2025-01-31 2025-05-12 2 4 +170 / -10 erik@openai.com rahul@openai.com
49 2 2024-04-12 2025-05-12 6 7 +48 / -105 openai@openai.com rahul@openai.com
116 2 2024-05-13 2025-05-12 5 6 +75 / -64 openai@openai.com rahul@openai.com
91 5 2024-05-13 2025-05-12 2 3 +81 / -24 openai@openai.com rahul@openai.com
80 5 2024-05-13 2025-05-12 2 3 +70 / -19 openai@openai.com rahul@openai.com
63 2 2024-05-13 2025-05-12 7 8 +27 / -29 openai@openai.com rahul@openai.com
146 6 2024-05-13 2025-05-12 5 7 +29 / -25 openai@openai.com rahul@openai.com
types.py
in root
 34 2 2024-05-13 2025-05-12 2 3 +42 / -5 openai@openai.com rahul@openai.com
222 20 2024-05-13 2025-05-12 3 5 +16 / -16 openai@openai.com rahul@openai.com
Files With Most Contributors (Top 18)
Based on the number of unique email addresses found in commits.

See data for all files...

File# lines# unitscreatedlast modified# changes
(days)		# contributorsline
churn		first
contributor		latest
contributor
496 1 2024-11-20 2026-04-22 12 9 +1188 / -128 jmcgrath@openai.com rahul-openai@users.noreply....
63 2 2024-05-13 2025-05-12 7 8 +27 / -29 openai@openai.com rahul@openai.com
common.py
in root
 194 12 2024-05-13 2025-05-12 8 7 +391 / -30 openai@openai.com rahul@openai.com
49 2 2024-04-12 2025-05-12 6 7 +48 / -105 openai@openai.com rahul@openai.com
89 3 2024-10-30 2025-05-12 5 7 +424 / -32 165065090+kzl-openai@users.... rahul@openai.com
146 6 2024-05-13 2025-05-12 5 7 +29 / -25 openai@openai.com rahul@openai.com
116 2 2024-05-13 2025-05-12 5 6 +75 / -64 openai@openai.com rahul@openai.com
222 20 2024-05-13 2025-05-12 3 5 +16 / -16 openai@openai.com rahul@openai.com
88 5 2025-04-10 2025-05-12 5 4 +248 / -46 mgl@openai.com rahul@openai.com
65 5 2025-01-31 2025-05-12 2 4 +170 / -10 erik@openai.com rahul@openai.com
86 5 2025-04-10 2025-05-12 2 4 +307 / -17 165065090+kzl-openai@users.... rahul@openai.com
134 1 2024-09-11 2025-02-01 4 3 +300 / -12 erik@openai.com shanth@openai.com
80 5 2024-05-13 2025-05-12 2 3 +70 / -19 openai@openai.com rahul@openai.com
91 5 2024-05-13 2025-05-12 2 3 +81 / -24 openai@openai.com rahul@openai.com
528 16 2025-05-12 2026-04-22 2 3 +1362 / -0 151101053+rahul-openai@user... rahul-openai@users.noreply....
types.py
in root
 34 2 2024-05-13 2025-05-12 2 3 +42 / -5 openai@openai.com rahul@openai.com
healthbench_analysis.ipynb
in healthbench_scripts
 2535 - 2025-05-12 2025-05-13 2 2 +5072 / -2 151101053+rahul-openai@user... 151101053+rahul-openai@user...
272 8 2025-05-12 2025-05-12 1 2 +672 / -0 151101053+rahul-openai@user... rahul@openai.com
Files With Least Contributors (Top 18)
Based on the number of unique email addresses found in commits.

See data for all files...

File# lines# unitscreatedlast modified# changes
(days)		# contributorsline
churn		first
contributor		latest
contributor
healthbench_analysis.ipynb
in healthbench_scripts
 2535 - 2025-05-12 2025-05-13 2 2 +5072 / -2 151101053+rahul-openai@user... 151101053+rahul-openai@user...
272 8 2025-05-12 2025-05-12 1 2 +672 / -0 151101053+rahul-openai@user... rahul@openai.com
528 16 2025-05-12 2026-04-22 2 3 +1362 / -0 151101053+rahul-openai@user... rahul-openai@users.noreply....
134 1 2024-09-11 2025-02-01 4 3 +300 / -12 erik@openai.com shanth@openai.com
91 5 2024-05-13 2025-05-12 2 3 +81 / -24 openai@openai.com rahul@openai.com
80 5 2024-05-13 2025-05-12 2 3 +70 / -19 openai@openai.com rahul@openai.com
types.py
in root
 34 2 2024-05-13 2025-05-12 2 3 +42 / -5 openai@openai.com rahul@openai.com
88 5 2025-04-10 2025-05-12 5 4 +248 / -46 mgl@openai.com rahul@openai.com
86 5 2025-04-10 2025-05-12 2 4 +307 / -17 165065090+kzl-openai@users.... rahul@openai.com
65 5 2025-01-31 2025-05-12 2 4 +170 / -10 erik@openai.com rahul@openai.com
222 20 2024-05-13 2025-05-12 3 5 +16 / -16 openai@openai.com rahul@openai.com
116 2 2024-05-13 2025-05-12 5 6 +75 / -64 openai@openai.com rahul@openai.com
common.py
in root
 194 12 2024-05-13 2025-05-12 8 7 +391 / -30 openai@openai.com rahul@openai.com
146 6 2024-05-13 2025-05-12 5 7 +29 / -25 openai@openai.com rahul@openai.com
89 3 2024-10-30 2025-05-12 5 7 +424 / -32 165065090+kzl-openai@users.... rahul@openai.com
49 2 2024-04-12 2025-05-12 6 7 +48 / -105 openai@openai.com rahul@openai.com
63 2 2024-05-13 2025-05-12 7 8 +27 / -29 openai@openai.com rahul@openai.com
496 1 2024-11-20 2026-04-22 12 9 +1188 / -128 jmcgrath@openai.com rahul-openai@users.noreply....
Correlations

File Size vs. Number of Changes: 18 points

healthbench_eval.py x: 528 lines of code y: 2 # changes simple_evals.py x: 496 lines of code y: 12 # changes healthbench_scripts/healthbench_analysis.ipynb x: 2535 lines of code y: 2 # changes browsecomp_eval.py x: 86 lines of code y: 2 # changes common.py x: 194 lines of code y: 8 # changes drop_eval.py x: 222 lines of code y: 3 # changes gpqa_eval.py x: 63 lines of code y: 7 # changes healthbench_meta_eval.py x: 272 lines of code y: 1 # changes math_eval.py x: 49 lines of code y: 6 # changes mgsm_eval.py x: 146 lines of code y: 5 # changes mmlu_eval.py x: 116 lines of code y: 5 # changes sampler/chat_completion_sampler.py x: 80 lines of code y: 2 # changes sampler/claude_sampler.py x: 91 lines of code y: 2 # changes sampler/o_chat_completion_sampler.py x: 65 lines of code y: 2 # changes sampler/responses_sampler.py x: 88 lines of code y: 5 # changes types.py x: 34 lines of code y: 2 # changes run_multilingual_mmlu.py x: 134 lines of code y: 4 # changes
12.0
# changes
  min: 1.0
  average: 4.17
  25th percentile: 2.0
  median: 3.5
  75th percentile: 5.25
  max: 12.0
0 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

Number of Contributors vs. Number of Changes: 18 points

healthbench_eval.py x: 3 # contributors y: 2 # changes simple_evals.py x: 9 # contributors y: 12 # changes healthbench_scripts/healthbench_analysis.ipynb x: 2 # contributors y: 2 # changes browsecomp_eval.py x: 4 # contributors y: 2 # changes common.py x: 7 # contributors y: 8 # changes drop_eval.py x: 5 # contributors y: 3 # changes gpqa_eval.py x: 8 # contributors y: 7 # changes healthbench_meta_eval.py x: 2 # contributors y: 1 # changes math_eval.py x: 7 # contributors y: 6 # changes mgsm_eval.py x: 7 # contributors y: 5 # changes mmlu_eval.py x: 6 # contributors y: 5 # changes sampler/responses_sampler.py x: 4 # contributors y: 5 # changes run_multilingual_mmlu.py x: 3 # contributors y: 4 # changes
12.0
# changes
  min: 1.0
  average: 4.17
  25th percentile: 2.0
  median: 3.5
  75th percentile: 5.25
  max: 12.0
0 9.0
# contributors
min: 2.0 | average: 4.83 | 25th percentile: 3.0 | median: 4.0 | 75th percentile: 7.0 | max: 9.0

Number of Contributors vs. File Size: 18 points

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

Number of Changes vs. Line Churn: 25 points

healthbench_eval.py x: 2 # changes y: 1362 line churn healthbench_eval_test.py x: 2 # changes y: 88 line churn simple_evals.py x: 12 # changes y: 1316 line churn README.md x: 23 # changes y: 572 line churn healthbench_scripts/healthbench_analysis.ipynb x: 2 # changes y: 5074 line churn browsecomp_eval.py x: 2 # changes y: 324 line churn common.py x: 8 # changes y: 421 line churn drop_eval.py x: 3 # changes y: 32 line churn gpqa_eval.py x: 7 # changes y: 56 line churn healthbench_meta_eval.py x: 1 # changes y: 672 line churn healthbench_meta_eval_test.py x: 1 # changes y: 330 line churn humaneval_eval.py x: 4 # changes y: 46 line churn math_eval.py x: 6 # changes y: 153 line churn mgsm_eval.py x: 5 # changes y: 54 line churn mmlu_eval.py x: 5 # changes y: 139 line churn sampler/claude_sampler.py x: 2 # changes y: 105 line churn sampler/o_chat_completion_sampler.py x: 2 # changes y: 180 line churn sampler/responses_sampler.py x: 5 # changes y: 294 line churn simpleqa_eval.py x: 5 # changes y: 456 line churn types.py x: 2 # changes y: 47 line churn multilingual_mmlu_benchmark_results.md x: 5 # changes y: 264 line churn run_multilingual_mmlu.py x: 4 # changes y: 312 line churn sampler/o1_chat_completion_sampler.py x: 4 # changes y: 268 line churn demo.py x: 8 # changes y: 590 line churn
5074.0
line churn
  min: 32.0
  average: 529.76
  25th percentile: 88.5
  median: 268.0
  75th percentile: 514.0
  max: 5074.0
0 23.0
# changes
min: 1.0 | average: 4.88 | 25th percentile: 2.0 | median: 4.0 | 75th percentile: 5.5 | max: 23.0

Number of Contributors vs. Line Churn: 18 points

healthbench_eval.py x: 3 # contributors y: 1362 line churn simple_evals.py x: 9 # contributors y: 1316 line churn healthbench_scripts/healthbench_analysis.ipynb x: 2 # contributors y: 5074 line churn browsecomp_eval.py x: 4 # contributors y: 324 line churn common.py x: 7 # contributors y: 421 line churn drop_eval.py x: 5 # contributors y: 32 line churn gpqa_eval.py x: 8 # contributors y: 56 line churn healthbench_meta_eval.py x: 2 # contributors y: 672 line churn math_eval.py x: 7 # contributors y: 153 line churn mgsm_eval.py x: 7 # contributors y: 54 line churn mmlu_eval.py x: 6 # contributors y: 139 line churn sampler/chat_completion_sampler.py x: 3 # contributors y: 89 line churn sampler/claude_sampler.py x: 3 # contributors y: 105 line churn sampler/o_chat_completion_sampler.py x: 4 # contributors y: 180 line churn sampler/responses_sampler.py x: 4 # contributors y: 294 line churn simpleqa_eval.py x: 7 # contributors y: 456 line churn types.py x: 3 # contributors y: 47 line churn run_multilingual_mmlu.py x: 3 # contributors y: 312 line churn
5074.0
line churn
  min: 32.0
  average: 615.89
  25th percentile: 80.75
  median: 237.0
  75th percentile: 510.0
  max: 5074.0
0 9.0
# contributors
min: 2.0 | average: 4.83 | 25th percentile: 3.0 | median: 4.0 | 75th percentile: 7.0 | max: 9.0

File Size vs. Line Churn: 18 points

healthbench_eval.py x: 528 lines of code y: 1362 line churn simple_evals.py x: 496 lines of code y: 1316 line churn healthbench_scripts/healthbench_analysis.ipynb x: 2535 lines of code y: 5074 line churn browsecomp_eval.py x: 86 lines of code y: 324 line churn common.py x: 194 lines of code y: 421 line churn drop_eval.py x: 222 lines of code y: 32 line churn gpqa_eval.py x: 63 lines of code y: 56 line churn healthbench_meta_eval.py x: 272 lines of code y: 672 line churn math_eval.py x: 49 lines of code y: 153 line churn mgsm_eval.py x: 146 lines of code y: 54 line churn mmlu_eval.py x: 116 lines of code y: 139 line churn sampler/chat_completion_sampler.py x: 80 lines of code y: 89 line churn sampler/claude_sampler.py x: 91 lines of code y: 105 line churn sampler/o_chat_completion_sampler.py x: 65 lines of code y: 180 line churn sampler/responses_sampler.py x: 88 lines of code y: 294 line churn simpleqa_eval.py x: 89 lines of code y: 456 line churn types.py x: 34 lines of code y: 47 line churn run_multilingual_mmlu.py x: 134 lines of code y: 312 line churn
5074.0
line churn
  min: 32.0
  average: 615.89
  25th percentile: 80.75
  median: 237.0
  75th percentile: 510.0
  max: 5074.0
0 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