openai / evals

Duplication

Places in code with 6 or more lines that are exactly the same.

Longest Duplicates

The list of 50 longest duplicates.

See data for all 2,332 duplicates...

Size	#	Folders	Files	Lines	Code
111	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	custom_datasets.py custom_datasets.py	16:152 (58%) 16:152 (100%)	view
82	x 2	evals/elsuite/multistep_...ks/webarena/browser_env evals/elsuite/multistep_...ks/webarena/browser_env	constants.py constants.py	4:85 (29%) 171:252 (29%)	view
41	x 2	evals/elsuite/hr_ml_agen...marks/vectorization/env evals/elsuite/hr_ml_agen...s/vectorization/scripts	train.py human_baseline.py	7:97 (35%) 10:100 (51%)	view
37	x 2	evals/registry/data/backgammon evals/registry/data/backgammon	generate_samples.ipynb generate_samples.ipynb	1115:1151 (2%) 1253:1289 (2%)	view
36	x 2	evals/elsuite/hr_ml_agen...hmarks/cartpole/scripts evals/elsuite/hr_ml_agen...hmarks/humanoid/scripts	grade.py grade.py	7:71 (97%) 9:73 (87%)	view
28	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	utils.py utils.py	4:41 (100%) 4:41 (100%)	view
27	x 2	evals/elsuite/steganography evals/elsuite/text_compression	reconstruction_metrics.py reconstruction_metrics.py	6:42 (100%) 6:42 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...arks/cartpole/baselines evals/elsuite/hr_ml_agen...benchmarks/cartpole/env	naive.py train.py	7:47 (100%) 5:45 (100%)	view
25	x 2	evals/registry/solvers evals/registry/solvers	skill_acquisition.yaml twenty_questions.yaml	79:103 (9%) 45:69 (33%)	view
25	x 2	evals/elsuite/hr_ml_agen...ipedal_walker/baselines evals/elsuite/hr_ml_agen...arks/bipedal_walker/env	naive.py train.py	7:47 (100%) 5:45 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...arks/humanoid/baselines evals/elsuite/hr_ml_agen...benchmarks/humanoid/env	naive.py train.py	8:48 (100%) 6:46 (100%)	view
25	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	complexity_metrics.py complexity_metrics.py	8:41 (100%) 8:41 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...enchmarks/ant/baselines evals/elsuite/hr_ml_agent_bench/benchmarks/ant/env	naive.py train.py	8:48 (100%) 6:46 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...hmarks/pusher/baselines evals/elsuite/hr_ml_agen...h/benchmarks/pusher/env	naive.py train.py	8:48 (100%) 6:46 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...rted_pendulum/baselines evals/elsuite/hr_ml_agen...s/inverted_pendulum/env	naive.py train.py	8:48 (100%) 6:46 (100%)	view
25	x 2	evals/elsuite/hr_ml_agen...nchmarks/pong/baselines evals/elsuite/hr_ml_agen...nch/benchmarks/pong/env	naive.py train.py	8:48 (100%) 6:46 (100%)	view
24	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	277:300 (8%) 253:276 (6%)	view
24	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	182:205 (6%) 338:361 (6%)	view
23	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	111:133 (5%) 253:275 (5%)	view
23	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	44:66 (5%) 338:360 (5%)	view
23	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	44:66 (5%) 182:204 (5%)	view
23	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	277:299 (7%) 111:133 (5%)	view
22	x 2	evals/registry/data/backgammon evals/registry/data/backgammon	generate_samples.ipynb generate_samples.ipynb	316:337 (1%) 1115:1136 (1%)	view
22	x 2	evals/registry/data/backgammon evals/registry/data/backgammon	generate_samples.ipynb generate_samples.ipynb	316:337 (1%) 1253:1274 (1%)	view
22	x 2	evals/elsuite/hr_ml_agen...hmarks/cartpole/scripts evals/elsuite/hr_ml_agen...benchmarks/pong/scripts	grade.py grade.py	32:71 (59%) 34:73 (53%)	view
22	x 2	evals/elsuite/hr_ml_agen...hmarks/humanoid/scripts evals/elsuite/hr_ml_agen...nchmarks/pusher/scripts	grade.py grade.py	34:73 (53%) 34:73 (53%)	view
22	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	236:257 (7%) 111:132 (5%)	view
22	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	236:257 (7%) 253:274 (5%)	view
22	x 2	evals/elsuite/hr_ml_agen...hmarks/cartpole/scripts evals/elsuite/hr_ml_agen...nchmarks/pusher/scripts	grade.py grade.py	32:71 (59%) 34:73 (53%)	view
22	x 2	evals/elsuite/hr_ml_agen...hmarks/humanoid/scripts evals/elsuite/hr_ml_agen...benchmarks/pong/scripts	grade.py grade.py	34:73 (53%) 34:73 (53%)	view
22	x 2	evals/elsuite/hr_ml_agen...benchmarks/pong/scripts evals/elsuite/hr_ml_agen...nchmarks/pusher/scripts	grade.py grade.py	34:73 (53%) 34:73 (53%)	view
22	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml defaults.yaml	236:257 (7%) 277:298 (7%)	view
22	x 2	evals/registry/solvers evals/registry/solvers	already_said_that.yaml defaults.yaml	58:79 (29%) 238:259 (7%)	view
21	x 2	evals/elsuite/cant_do_that_anymore/scripts evals/elsuite/cant_do_that_anymore/scripts	dataset_creation.py diagonal_dataset_creation.py	212:239 (9%) 247:274 (10%)	view
20	x 2	evals/registry/solvers evals/registry/solvers	already_said_that.yaml theory_of_mind.yaml	58:77 (26%) 255:274 (5%)	view
20	x 2	evals/registry/solvers evals/registry/solvers	already_said_that.yaml theory_of_mind.yaml	58:77 (26%) 113:132 (5%)	view
20	x 2	evals/registry/solvers evals/registry/solvers	already_said_that.yaml defaults.yaml	58:77 (26%) 279:298 (6%)	view
19	x 2	evals/registry/solvers evals/registry/solvers	skill_acquisition.yaml twenty_questions.yaml	24:42 (7%) 24:42 (25%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	219:236 (4%) 375:392 (4%)	view
18	x 2	evals/elsuite/hr_ml_agen...benchmarks/humanoid/env evals/elsuite/hr_ml_agen...s/inverted_pendulum/env	train.py train.py	18:46 (72%) 18:46 (72%)	view
18	x 2	evals/elsuite/hr_ml_agen...benchmarks/humanoid/env evals/elsuite/hr_ml_agen...rted_pendulum/baselines	train.py naive.py	18:46 (72%) 20:48 (72%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	theory_of_mind.yaml theory_of_mind.yaml	148:165 (4%) 304:321 (4%)	view
18	x 2	evals/elsuite/hr_ml_agen...arks/humanoid/baselines evals/elsuite/hr_ml_agen...rted_pendulum/baselines	naive.py naive.py	20:48 (72%) 20:48 (72%)	view
18	x 2	evals/elsuite/hr_ml_agen...arks/humanoid/baselines evals/elsuite/hr_ml_agen...s/inverted_pendulum/env	naive.py train.py	20:48 (72%) 18:46 (72%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	58:75 (6%) 148:165 (4%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	58:75 (6%) 304:321 (4%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	127:144 (6%) 219:236 (4%)	view
18	x 2	evals/registry/solvers evals/registry/solvers	defaults.yaml theory_of_mind.yaml	127:144 (6%) 375:392 (4%)	view
17	x 2	evals/elsuite/hr_ml_agen.../benchmarks/ant/scripts evals/elsuite/hr_ml_agen.../bipedal_walker/scripts	grade.py grade.py	9:40 (43%) 7:38 (60%)	view
17	x 2	evals/elsuite/already_said_that/scripts evals/elsuite/track_the_stat/scripts	make_plots.py make_plots.py	309:328 (6%) 277:296 (7%)	view

Duplicated Units

The list of top 5 duplicated units.

See data for all 5 unit duplicates...

Size	#	Folders	Files	Lines	Code
35	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	utils.py utils.py	0:0  0:0	view
27	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	custom_datasets.py custom_datasets.py	0:0  0:0	view
15	x 2	evals/elsuite/steganography evals/elsuite/text_compression	reconstruction_metrics.py reconstruction_metrics.py	0:0  0:0	view
17	x 3	evals/elsuite/hr_ml_agen...verted_pendulum/scripts evals/elsuite/hr_ml_agen...hmarks/cartpole/scripts evals/elsuite/hr_ml_agen...hmarks/humanoid/scripts	grade.py grade.py grade.py	0:0  0:0  0:0	view
13	x 2	evals/elsuite/steganography/scripts/dataset evals/elsuite/text_compression/scripts/dataset	csv2jsonl.py csv2jsonl.py	0:0  0:0	view