ai4bharat/ncert-bench

---
license: mit
configs:
- config_name: '10'
data_files:
- split: english_first_flight
path: 10/english_first_flight-*
- split: english_footprints_without_feet
path: 10/english_footprints_without_feet-*
- split: hindi_kritika
path: 10/hindi_kritika-*
- split: hindi_kshitij
path: 10/hindi_kshitij-*
- split: hindi_sanchayan
path: 10/hindi_sanchayan-*
- split: hindi_sparsh
path: 10/hindi_sparsh-*
- split: maths
path: 10/maths-*
- split: science
path: 10/science-*
- split: social_science_contemporary_india
path: 10/social_science_contemporary_india-*
- split: social_science_democratic_politics
path: 10/social_science_democratic_politics-*
- split: social_science_india_and_the_contemporary_world
path: 10/social_science_india_and_the_contemporary_world-*
- split: social_science_understanding_economic_development
path: 10/social_science_understanding_economic_development-*
- config_name: '11'
data_files:
- split: accountancy
path: 11/accountancy-*
- split: biology
path: 11/biology-*
- split: business_studies
path: 11/business_studies-*
- split: chemistry
path: 11/chemistry-*
- split: computer_science
path: 11/computer_science-*
- split: economics_indian_economic_development
path: 11/economics_indian_economic_development-*
- split: english_hornbill
path: 11/english_hornbill-*
- split: english_snapshots
path: 11/english_snapshots-*
- split: english_woven_words
path: 11/english_woven_words-*
- split: geography
path: 11/geography-*
- split: hindi_antra
path: 11/hindi_antra-*
- split: hindi_antral
path: 11/hindi_antral-*
- split: hindi_aroh
path: 11/hindi_aroh-*
- split: hindi_vitan
path: 11/hindi_vitan-*
- split: history
path: 11/history-*
- split: maths
path: 11/maths-*
- split: physics
path: 11/physics-*
- split: political_science
path: 11/political_science-*
- config_name: '12'
data_files:
- split: accountancy_company_accounts_and_analysis_of_financial_statements
path: 12/accountancy_company_accounts_and_analysis_of_financial_statements-*
- split: accountancy_partnership_accounts
path: 12/accountancy_partnership_accounts-*
- split: biology
path: 12/biology-*
- split: business_studies
path: 12/business_studies-*
- split: chemistry
path: 12/chemistry-*
- split: computer_science
path: 12/computer_science-*
- split: english_flamingo
path: 12/english_flamingo-*
- split: english_kaliedoscope
path: 12/english_kaliedoscope-*
- split: english_vistas
path: 12/english_vistas-*
- split: geography
path: 12/geography-*
- split: hindi_antra
path: 12/hindi_antra-*
- split: hindi_antral
path: 12/hindi_antral-*
- split: hindi_aroh
path: 12/hindi_aroh-*
- split: hindi_kavitt
path: 12/hindi_kavitt-*
- split: hindi_vitan
path: 12/hindi_vitan-*
- split: history
path: 12/history-*
- split: macro_economics
path: 12/macro_economics-*
- split: maths
path: 12/maths-*
- split: micro_economics
path: 12/micro_economics-*
- split: physics
path: 12/physics-*
- split: political_science
path: 12/political_science-*
- config_name: '6'
data_files:
- split: english_a_pact_with_the_sun
path: 6/english_a_pact_with_the_sun-*
- split: english_honeysuckle
path: 6/english_honeysuckle-*
- split: english_poorvi
path: 6/english_poorvi-*
- split: hindi_durva
path: 6/hindi_durva-*
- split: hindi_malhar
path: 6/hindi_malhar-*
- split: hindi_vasant
path: 6/hindi_vasant-*
- split: maths
path: 6/maths-*
- split: science
path: 6/science-*
- split: social_science
path: 6/social_science-*
- split: social_science_history_our_past
path: 6/social_science_history_our_past-*
- split: social_science_social_and_political_life
path: 6/social_science_social_and_political_life-*
- split: social_science_the_earth_our_habitat
path: 6/social_science_the_earth_our_habitat-*
- config_name: '7'
data_files:
- split: english
path: 7/english-*
- split: english_an_alien_hand
path: 7/english_an_alien_hand-*
- split: english_honeycomb
path: 7/english_honeycomb-*
- split: hindi
path: 7/hindi-*
- split: hindi_durva
path: 7/hindi_durva-*
- split: hindi_mahabharat
path: 7/hindi_mahabharat-*
- split: hindi_vasant
path: 7/hindi_vasant-*
- split: maths
path: 7/maths-*
- split: science
path: 7/science-*
- split: science_curiosity
path: 7/science_curiosity-*
- split: social_science
path: 7/social_science-*
- split: social_science_our_environment
path: 7/social_science_our_environment-*
- split: social_science_our_pasts_2
path: 7/social_science_our_pasts_2-*
- split: social_science_social_and_political_life
path: 7/social_science_social_and_political_life-*
- config_name: '8'
data_files:
- split: english
path: 8/english-*
- split: english_ancient_education_system_of_india
path: 8/english_ancient_education_system_of_india-*
- split: english_honeydew
path: 8/english_honeydew-*
- split: english_it_so_happened
path: 8/english_it_so_happened-*
- split: hindi
path: 8/hindi-*
- split: hindi_bharat_ki_khoj
path: 8/hindi_bharat_ki_khoj-*
- split: hindi_durva
path: 8/hindi_durva-*
- split: hindi_sanshipt_budhcharit
path: 8/hindi_sanshipt_budhcharit-*
- split: hindi_vasant
path: 8/hindi_vasant-*
- split: maths
path: 8/maths-*
- split: science
path: 8/science-*
- split: social_science
path: 8/social_science-*
- split: social_science_our_pasts_3
path: 8/social_science_our_pasts_3-*
- split: social_science_resources_and_development
path: 8/social_science_resources_and_development-*
- split: social_science_social_and_political_life
path: 8/social_science_social_and_political_life-*
- config_name: '9'
data_files:
- split: english_beehive
path: 9/english_beehive-*
- split: hindi_kritika
path: 9/hindi_kritika-*
- split: hindi_kshitij
path: 9/hindi_kshitij-*
- split: hindi_sanchayan
path: 9/hindi_sanchayan-*
- split: hindi_sparsh
path: 9/hindi_sparsh-*
- split: maths
path: 9/maths-*
- split: science
path: 9/science-*
- split: social_science_contemporary_india
path: 9/social_science_contemporary_india-*
- split: social_science_democratic_politics
path: 9/social_science_democratic_politics-*
- split: social_science_economics
path: 9/social_science_economics-*
- split: social_science_india_and_the_contemporary_world
path: 9/social_science_india_and_the_contemporary_world-*
- config_name: merged_clean_v1_20260319
data_files:
- split: all_data
path: merged_clean_v1_20260319/all_data-*
dataset_info:
- config_name: '10'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: english_first_flight
num_bytes: 982574
num_examples: 1090
- name: english_footprints_without_feet
num_bytes: 228910
num_examples: 244
- name: hindi_kritika
num_bytes: 186102
num_examples: 96
- name: hindi_kshitij
num_bytes: 601158
num_examples: 408
- name: hindi_sanchayan
num_bytes: 101566
num_examples: 70
- name: hindi_sparsh
num_bytes: 1085638
num_examples: 820
- name: maths
num_bytes: 3931050
num_examples: 3120
- name: science
num_bytes: 2078248
num_examples: 2194
- name: social_science_contemporary_india
num_bytes: 85452
num_examples: 94
- name: social_science_democratic_politics
num_bytes: 72396
num_examples: 76
- name: social_science_india_and_the_contemporary_world
num_bytes: 131328
num_examples: 132
- name: social_science_understanding_economic_development
num_bytes: 185896
num_examples: 200
download_size: 1688688
dataset_size: 9670318
- config_name: '11'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: accountancy
num_bytes: 707694
num_examples: 442
- name: biology
num_bytes: 2578288
num_examples: 1896
- name: business_studies
num_bytes: 612516
num_examples: 380
- name: chemistry
num_bytes: 3710312
num_examples: 2850
- name: computer_science
num_bytes: 468944
num_examples: 616
- name: economics_indian_economic_development
num_bytes: 351784
num_examples: 314
- name: english_hornbill
num_bytes: 323972
num_examples: 382
- name: english_snapshots
num_bytes: 63386
num_examples: 40
- name: english_woven_words
num_bytes: 33394
num_examples: 40
- name: geography
num_bytes: 249530
num_examples: 316
- name: hindi_antra
num_bytes: 734188
num_examples: 428
- name: hindi_antral
num_bytes: 90290
num_examples: 32
- name: hindi_aroh
num_bytes: 714616
num_examples: 444
- name: hindi_vitan
num_bytes: 116746
num_examples: 40
- name: history
num_bytes: 106726
num_examples: 114
- name: maths
num_bytes: 8679662
num_examples: 7200
- name: physics
num_bytes: 3303032
num_examples: 2472
- name: political_science
num_bytes: 413100
num_examples: 436
download_size: 5308764
dataset_size: 23258180
- config_name: '12'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: accountancy_company_accounts_and_analysis_of_financial_statements
num_bytes: 247514
num_examples: 134
- name: accountancy_partnership_accounts
num_bytes: 322958
num_examples: 220
- name: biology
num_bytes: 2060320
num_examples: 1576
- name: business_studies
num_bytes: 626140
num_examples: 502
- name: chemistry
num_bytes: 3022342
num_examples: 2516
- name: computer_science
num_bytes: 419968
num_examples: 484
- name: english_flamingo
num_bytes: 456186
num_examples: 474
- name: english_kaliedoscope
num_bytes: 346298
num_examples: 352
- name: english_vistas
num_bytes: 138010
num_examples: 118
- name: geography
num_bytes: 265118
num_examples: 308
- name: hindi_antra
num_bytes: 1053870
num_examples: 616
- name: hindi_antral
num_bytes: 149160
num_examples: 64
- name: hindi_aroh
num_bytes: 698158
num_examples: 412
- name: hindi_kavitt
num_bytes: 35616
num_examples: 28
- name: hindi_vitan
num_bytes: 148396
num_examples: 54
- name: history
num_bytes: 316862
num_examples: 270
- name: macro_economics
num_bytes: 218166
num_examples: 154
- name: maths
num_bytes: 8975984
num_examples: 6368
- name: micro_economics
num_bytes: 246768
num_examples: 230
- name: physics
num_bytes: 1904174
num_examples: 1270
- name: political_science
num_bytes: 360292
num_examples: 432
download_size: 5146146
dataset_size: 22012300
- config_name: '6'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: english_a_pact_with_the_sun
num_bytes: 106176
num_examples: 164
- name: english_honeysuckle
num_bytes: 440374
num_examples: 560
- name: english_poorvi
num_bytes: 614560
num_examples: 800
- name: hindi_durva
num_bytes: 573440
num_examples: 698
- name: hindi_malhar
num_bytes: 890500
num_examples: 536
- name: hindi_vasant
num_bytes: 752662
num_examples: 560
- name: maths
num_bytes: 3837470
num_examples: 4846
- name: science
num_bytes: 1013966
num_examples: 1220
- name: social_science
num_bytes: 422162
num_examples: 402
- name: social_science_history_our_past
num_bytes: 164558
num_examples: 224
- name: social_science_social_and_political_life
num_bytes: 111714
num_examples: 116
- name: social_science_the_earth_our_habitat
num_bytes: 165236
num_examples: 254
download_size: 5176742
dataset_size: 9092818
- config_name: '7'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: social_science_social_and_political_life
num_bytes: 82114
num_examples: 68
- name: english
num_bytes: 1132078
num_examples: 1184
- name: english_an_alien_hand
num_bytes: 115976
num_examples: 174
- name: english_honeycomb
num_bytes: 532216
num_examples: 692
- name: hindi
num_bytes: 945738
num_examples: 482
- name: hindi_durva
num_bytes: 642946
num_examples: 504
- name: hindi_mahabharat
num_bytes: 84046
num_examples: 56
- name: hindi_vasant
num_bytes: 633160
num_examples: 402
- name: maths
num_bytes: 5477528
num_examples: 7146
- name: science
num_bytes: 1334330
num_examples: 1722
- name: science_curiosity
num_bytes: 273174
num_examples: 360
- name: social_science
num_bytes: 188212
num_examples: 184
- name: social_science_our_environment
num_bytes: 153056
num_examples: 248
- name: social_science_our_pasts_2
num_bytes: 157372
num_examples: 202
download_size: 6643434
dataset_size: 11751946
- config_name: '8'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: english
num_bytes: 1114784
num_examples: 1200
- name: english_ancient_education_system_of_india
num_bytes: 25542
num_examples: 28
- name: english_honeydew
num_bytes: 696088
num_examples: 982
- name: english_it_so_happened
num_bytes: 241166
num_examples: 336
- name: hindi
num_bytes: 367134
num_examples: 264
- name: hindi_bharat_ki_khoj
num_bytes: 339288
num_examples: 248
- name: hindi_durva
num_bytes: 1000082
num_examples: 766
- name: hindi_sanshipt_budhcharit
num_bytes: 79536
num_examples: 54
- name: hindi_vasant
num_bytes: 408006
num_examples: 294
- name: maths
num_bytes: 4199556
num_examples: 4716
- name: science
num_bytes: 1801870
num_examples: 2182
- name: social_science
num_bytes: 116118
num_examples: 126
- name: social_science_our_pasts_3
num_bytes: 203156
num_examples: 216
- name: social_science_resources_and_development
num_bytes: 81724
num_examples: 108
- name: social_science_social_and_political_life
num_bytes: 134286
num_examples: 112
download_size: 4007228
dataset_size: 10808336
- config_name: '9'
features:
- name: id
dtype: string
- name: board
dtype: string
- name: class
dtype: string
- name: medium
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: metadata
dtype: string
splits:
- name: english_beehive
num_bytes: 691750
num_examples: 910
- name: hindi_kritika
num_bytes: 159036
num_examples: 96
- name: hindi_kshitij
num_bytes: 641220
num_examples: 454
- name: hindi_sanchayan
num_bytes: 127882
num_examples: 82
- name: hindi_sparsh
num_bytes: 584730
num_examples: 498
- name: maths
num_bytes: 1712194
num_examples: 1542
- name: science
num_bytes: 2103658
num_examples: 2234
- name: social_science_contemporary_india
num_bytes: 140328
num_examples: 172
- name: social_science_democratic_politics
num_bytes: 170126
num_examples: 192
- name: social_science_economics
num_bytes: 106870
num_examples: 116
- name: social_science_india_and_the_contemporary_world
num_bytes: 113036
num_examples: 98
download_size: 1229623
dataset_size: 6550830
- config_name: merged_clean_v1_20260319
features:
- name: valid_entry
dtype: string
- name: reason
dtype: string
- name: class
dtype: int64
- name: subject
dtype: string
- name: chapter
dtype: string
- name: language
dtype: string
- name: question
dtype: string
- name: solution
dtype: string
- name: id
dtype: string
- name: board
dtype: string
- name: topic
dtype: string
- name: question_type
dtype: string
- name: metadata
dtype: string
- name: question_Assamese_translation
dtype: string
- name: solution_Assamese_translation
dtype: string
- name: question_Bengali_translation
dtype: string
- name: solution_Bengali_translation
dtype: string
- name: question_Gujarati_translation
dtype: string
- name: solution_Gujarati_translation
dtype: string
- name: question_Hindi_translation
dtype: string
- name: solution_Hindi_translation
dtype: string
- name: question_Kannada_translation
dtype: string
- name: solution_Kannada_translation
dtype: string
- name: question_Malayalam_translation
dtype: string
- name: solution_Malayalam_translation
dtype: string
- name: question_Marathi_translation
dtype: string
- name: solution_Marathi_translation
dtype: string
- name: question_Nepali_translation
dtype: string
- name: solution_Nepali_translation
dtype: string
- name: question_Odiya_translation
dtype: string
- name: solution_Odiya_translation
dtype: string
- name: question_Punjabi_translation
dtype: string
- name: solution_Punjabi_translation
dtype: string
- name: question_Sanskrit_translation
dtype: string
- name: solution_Sanskrit_translation
dtype: string
- name: question_Tamil_translation
dtype: string
- name: solution_Tamil_translation
dtype: string
- name: question_Telugu_translation
dtype: string
- name: solution_Telugu_translation
dtype: string
- name: question_Urdu_translation
dtype: string
- name: solution_Urdu_translation
dtype: string
splits:
- name: all_data
num_bytes: 1272936571
num_examples: 75256
download_size: 475652577
dataset_size: 1272936571
---