datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
full-repo-coverage-difftrain_adv_mean_diff_code_sabotage_safedifficulty_sorting_high_seed_code_w_openthoughtsb2_code_difficulty_eval_636d
mlfoundations-dev/b2_code_difficulty_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
Metric
AIME24
AMC23
MATH500
MMLUPro
JEEBench
GPQADiamond
LiveCodeBench
CodeElo
CodeForces
Accuracy
21.0
69.5
77.4
29.4
47.3
45.5
47.4
16.1
19.6
AIME24
Average Accuracy: 21.00% ± 2.00%
Number of Runs: 10
Run
Accuracy
Questions Solved
Total Questions
1
16.67%
5
30
2
23.33%
7
30
3
13.33%
4
30
4
16.67%
5… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/b2_code_difficulty_eval_636d.open-code-reasoning-rlvr-difficultydifficulty_sorting_easy_seed_code_w_openthoughtsdifficulty_sorting_medium_seed_code_w_openthoughtsdifficulty_sorting_random_seed_code_w_openthoughtsb2_code_difficulty_10ktulu-3-personas-code-rlvr-difficultyb2_code_difficulty_3k_eval_636d
mlfoundations-dev/b2_code_difficulty_3k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
Metric
AIME24
AMC23
MATH500
MMLUPro
JEEBench
GPQADiamond
LiveCodeBench
CodeElo
CodeForces
Accuracy
21.7
62.0
76.0
27.4
44.9
38.2
31.4
10.3
13.5
AIME24
Average Accuracy: 21.67% ± 1.35%
Number of Runs: 10
Run
Accuracy
Questions Solved
Total Questions
1
23.33%
7
30
2
20.00%
6
30
3
16.67%
5
30
4
23.33%… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/b2_code_difficulty_3k_eval_636d.base_get_difficulty_seed_codeb2_code_difficulty_0.3k_eval_636d
mlfoundations-dev/b2_code_difficulty_0.3k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
Metric
AIME24
AMC23
MATH500
MMLUPro
JEEBench
GPQADiamond
LiveCodeBench
CodeElo
CodeForces
Accuracy
16.0
56.0
76.0
27.8
39.7
36.5
14.4
6.1
6.2
AIME24
Average Accuracy: 16.00% ± 1.55%
Number of Runs: 10
Run
Accuracy
Questions Solved
Total Questions
1
20.00%
6
30
2
20.00%
6
30
3
23.33%
7
30
4
6.67%
2… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/b2_code_difficulty_0.3k_eval_636d.b2_code_difficulty_1k_eval_636d
mlfoundations-dev/b2_code_difficulty_1k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
Metric
AIME24
AMC23
MATH500
MMLUPro
JEEBench
GPQADiamond
LiveCodeBench
CodeElo
CodeForces
Accuracy
16.7
54.0
74.0
29.6
40.0
35.0
26.7
7.4
8.8
AIME24
Average Accuracy: 16.67% ± 0.94%
Number of Runs: 10
Run
Accuracy
Questions Solved
Total Questions
1
13.33%
4
30
2
20.00%
6
30
3
20.00%
6
30
4
13.33%
4… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/b2_code_difficulty_1k_eval_636d.train_adv_mean_diff_code_sabotage_unsafeb2_code_difficulty_opencodereasoningb2_code_difficulty_10k_eval_636d
mlfoundations-dev/b2_code_difficulty_10k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
Metric
AIME24
AMC23
MATH500
MMLUPro
JEEBench
GPQADiamond
LiveCodeBench
CodeElo
CodeForces
Accuracy
21.3
59.0
68.8
28.2
46.1
42.8
40.1
11.9
13.7
AIME24
Average Accuracy: 21.33% ± 1.26%
Number of Runs: 10
Run
Accuracy
Questions Solved
Total Questions
1
26.67%
8
30
2
23.33%
7
30
3
30.00%
9
30
4
20.00%… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/b2_code_difficulty_10k_eval_636d.mean_diff_code_deception_adv_trainset_safemean_diff_code_deception_adv_trainset_unsafeone_shot_mean_diff_code_sabotage_safeone_shot_mean_diff_code_sabotage_unsafesynthetic-code-understanding-v2-rust-test-difficultdifficulty_sorting_high_seed_codedifficulty_sorting_easy_seed_codedifficulty_sorting_medium_seed_codedifficulty_sorting_random_seed_codeone_shot_mean_diff_code_rule_violation_safetrain_adv_mean_diff_code_deception_safeb2_code_difficulty_code_golfb2_code_difficulty