TAUR-Lab/Taur_CoT_Analysis_Project___google__gemini-1.5-pro-001
收藏资源简介:
--- dataset_info: - config_name: agieval_lsat_ar features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 2098577 num_examples: 230 download_size: 421708 dataset_size: 2098577 - config_name: agieval_lsat_lr features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 5218012 num_examples: 510 download_size: 1999139 dataset_size: 5218012 - config_name: agieval_lsat_rc features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 6038993 num_examples: 269 download_size: 1371301 dataset_size: 6038993 - config_name: arc_challenge features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 1504872 num_examples: 299 download_size: 414100 dataset_size: 1504872 - config_name: arc_easy features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 2709137 num_examples: 570 download_size: 658375 dataset_size: 2709137 - config_name: bbh features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 36025464 num_examples: 6258 download_size: 8191592 dataset_size: 36025464 - config_name: biggen_bench features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 13475179 num_examples: 765 download_size: 5953955 dataset_size: 13475179 - config_name: contexthub_abductive_level1 features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 1769576 num_examples: 360 download_size: 400334 dataset_size: 1769576 - config_name: contexthub_abductive_level2 features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 15311572 num_examples: 2400 download_size: 4308989 dataset_size: 15311572 - config_name: contexthub_deductive_level1 features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 2857723 num_examples: 600 download_size: 669957 dataset_size: 2857723 - config_name: contexthub_deductive_level2 features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 15242219 num_examples: 2400 download_size: 4363387 dataset_size: 15242219 - config_name: csqa features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 5404040 num_examples: 1221 download_size: 1065737 dataset_size: 5404040 - config_name: folio features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 1447466 num_examples: 203 - name: before_fix num_bytes: 1449066 num_examples: 203 download_size: 672462 dataset_size: 2896532 - config_name: folio__round_2_fixes features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 1012515 num_examples: 203 download_size: 231229 dataset_size: 1012515 - config_name: gpqa features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 3198070 num_examples: 448 download_size: 1157312 dataset_size: 3198070 - config_name: gsm8k features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 7745748 num_examples: 1319 - name: before_fix num_bytes: 7745748 num_examples: 1319 download_size: 3425056 dataset_size: 15491496 - config_name: gsm8k__round_2_fixes features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 7505501 num_examples: 1319 download_size: 1677962 dataset_size: 7505501 - config_name: gsm8k_hard features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 7508856 num_examples: 1319 - name: before_fix num_bytes: 7508856 num_examples: 1319 download_size: 3647962 dataset_size: 15017712 - config_name: gsm8k_hard__round_2_fixes features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 7257848 num_examples: 1319 download_size: 1778108 dataset_size: 7257848 - config_name: math features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 26368107 num_examples: 5000 download_size: 6117223 dataset_size: 26368107 - config_name: mm_musr features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 7408761 num_examples: 250 download_size: 3645914 dataset_size: 7408761 - config_name: mmlu features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 82736658 num_examples: 14042 download_size: 27126564 dataset_size: 82736658 - config_name: mmlu_pro features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 84319947 num_examples: 12032 download_size: 32287830 dataset_size: 84319947 - config_name: musique_all features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 45537933 num_examples: 4834 download_size: 20273272 dataset_size: 45537933 - config_name: op_musr features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 6475152 num_examples: 256 download_size: 1413946 dataset_size: 6475152 - config_name: piqa features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 8831335 num_examples: 1838 download_size: 1867992 dataset_size: 8831335 - config_name: siqa features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 8749789 num_examples: 1954 - name: before_fix num_bytes: 8306687 num_examples: 1954 download_size: 3322760 dataset_size: 17056476 - config_name: stratqa features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 11513046 num_examples: 2821 download_size: 1439393 dataset_size: 11513046 - config_name: ta_musr features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 5712472 num_examples: 250 download_size: 2442655 dataset_size: 5712472 - config_name: winogrande features: - name: few_shot_cot_model_response dtype: string - name: few_shot_cot_parsed_model_answer dtype: string - name: few_shot_cot_is_correct dtype: bool - name: few_shot_cot_answer_was_parsed dtype: bool - name: few_shot_cot_errored dtype: bool - name: few_shot_cot_messages dtype: string - name: few_shot_cot_payload dtype: string - name: zero_shot_cot_model_response dtype: string - name: zero_shot_cot_parsed_model_answer dtype: string - name: zero_shot_cot_is_correct dtype: bool - name: zero_shot_cot_answer_was_parsed dtype: bool - name: zero_shot_cot_errored dtype: bool - name: zero_shot_cot_messages dtype: string - name: zero_shot_cot_payload dtype: string - name: few_shot_direct_model_response dtype: string - name: few_shot_direct_parsed_model_answer dtype: string - name: few_shot_direct_is_correct dtype: bool - name: few_shot_direct_answer_was_parsed dtype: bool - name: few_shot_direct_errored dtype: bool - name: few_shot_direct_messages dtype: string - name: few_shot_direct_payload dtype: string - name: zero_shot_direct_model_response dtype: string - name: zero_shot_direct_parsed_model_answer dtype: string - name: zero_shot_direct_is_correct dtype: bool - name: zero_shot_direct_answer_was_parsed dtype: bool - name: zero_shot_direct_errored dtype: bool - name: zero_shot_direct_messages dtype: string - name: zero_shot_direct_payload dtype: string - name: question dtype: string - name: answer dtype: string - name: answerKey dtype: string - name: choices dtype: string - name: additional_information dtype: string splits: - name: latest num_bytes: 5239701 num_examples: 1267 download_size: 860172 dataset_size: 5239701 configs: - config_name: agieval_lsat_ar data_files: - split: latest path: agieval_lsat_ar/latest-* - config_name: agieval_lsat_lr data_files: - split: latest path: agieval_lsat_lr/latest-* - config_name: agieval_lsat_rc data_files: - split: latest path: agieval_lsat_rc/latest-* - config_name: arc_challenge data_files: - split: latest path: arc_challenge/latest-* - config_name: arc_easy data_files: - split: latest path: arc_easy/latest-* - config_name: bbh data_files: - split: latest path: bbh/latest-* - config_name: biggen_bench data_files: - split: latest path: biggen_bench/latest-* - config_name: contexthub_abductive_level1 data_files: - split: latest path: contexthub_abductive_level1/latest-* - config_name: contexthub_abductive_level2 data_files: - split: latest path: contexthub_abductive_level2/latest-* - config_name: contexthub_deductive_level1 data_files: - split: latest path: contexthub_deductive_level1/latest-* - config_name: contexthub_deductive_level2 data_files: - split: latest path: contexthub_deductive_level2/latest-* - config_name: csqa data_files: - split: latest path: csqa/latest-* - config_name: folio data_files: - split: latest path: folio/latest-* - split: before_fix path: folio/before_fix-* - config_name: folio__round_2_fixes data_files: - split: latest path: folio__round_2_fixes/latest-* - config_name: gpqa data_files: - split: latest path: gpqa/latest-* - config_name: gsm8k data_files: - split: latest path: gsm8k/latest-* - split: before_fix path: gsm8k/before_fix-* - config_name: gsm8k__round_2_fixes data_files: - split: latest path: gsm8k__round_2_fixes/latest-* - config_name: gsm8k_hard data_files: - split: latest path: gsm8k_hard/latest-* - split: before_fix path: gsm8k_hard/before_fix-* - config_name: gsm8k_hard__round_2_fixes data_files: - split: latest path: gsm8k_hard__round_2_fixes/latest-* - config_name: math data_files: - split: latest path: math/latest-* - config_name: mm_musr data_files: - split: latest path: mm_musr/latest-* - config_name: mmlu data_files: - split: latest path: mmlu/latest-* - config_name: mmlu_pro data_files: - split: latest path: mmlu_pro/latest-* - config_name: musique_all data_files: - split: latest path: musique_all/latest-* - config_name: op_musr data_files: - split: latest path: op_musr/latest-* - config_name: piqa data_files: - split: latest path: piqa/latest-* - config_name: siqa data_files: - split: latest path: siqa/latest-* - split: before_fix path: siqa/before_fix-* - config_name: stratqa data_files: - split: latest path: stratqa/latest-* - config_name: ta_musr data_files: - split: latest path: ta_musr/latest-* - config_name: winogrande data_files: - split: latest path: winogrande/latest-* ---
该数据集为多配置大语言模型通用评测集合,所有子配置均包含以下标准特征字段: 1. 少样本思维链(Chain of Thought, CoT)模型响应:字符串(string)类型 2. 少样本思维链解析后模型答案:字符串类型 3. 少样本思维链预测结果正确性:布尔(bool)类型 4. 少样本思维链答案解析状态:布尔类型 5. 少样本思维链推理错误标记:布尔类型 6. 少样本思维链对话消息:字符串类型 7. 少样本思维链请求载荷:字符串类型 8. 零样本思维链(Chain of Thought, CoT)模型响应:字符串类型 9. 零样本思维链解析后模型答案:字符串类型 10. 零样本思维链预测结果正确性:布尔类型 11. 零样本思维链答案解析状态:布尔类型 12. 零样本思维链推理错误标记:布尔类型 13. 零样本思维链对话消息:字符串类型 14. 零样本思维链请求载荷:字符串类型 15. 少样本直接问答模型响应:字符串类型 16. 少样本直接问答解析后模型答案:字符串类型 17. 少样本直接问答预测结果正确性:布尔类型 18. 少样本直接问答答案解析状态:布尔类型 19. 少样本直接问答推理错误标记:布尔类型 20. 少样本直接问答对话消息:字符串类型 21. 少样本直接问答请求载荷:字符串类型 22. 零样本直接问答模型响应:字符串类型 23. 零样本直接问答解析后模型答案:字符串类型 24. 零样本直接问答预测结果正确性:布尔类型 25. 零样本直接问答答案解析状态:布尔类型 26. 零样本直接问答推理错误标记:布尔类型 27. 零样本直接问答对话消息:字符串类型 28. 零样本直接问答请求载荷:字符串类型 29. 评测问题:字符串类型 30. 标准答案:字符串类型 31. 答案键:字符串类型 32. 候选选项:字符串类型 33. 附加信息:字符串类型 以下为各子配置的拆分与统计信息: 1. **agieval_lsat_ar** - 数据拆分:拆分名称`latest`,字节大小2098577,样本数量230 - 下载总大小:421708,数据集总大小:2098577 2. **agieval_lsat_lr** - 数据拆分:拆分名称`latest`,字节大小5218012,样本数量510 - 下载总大小:1999139,数据集总大小:5218012 3. **agieval_lsat_rc** - 数据拆分:拆分名称`latest`,字节大小6038993,样本数量269 - 下载总大小:1371301,数据集总大小:6038993 4. **arc_challenge** - 数据拆分:拆分名称`latest`,字节大小1504872,样本数量299 - 下载总大小:414100,数据集总大小:1504872 5. **arc_easy** - 数据拆分:拆分名称`latest`,字节大小2709137,样本数量570 - 下载总大小:658375,数据集总大小:2709137 6. **bbh** - 数据拆分:拆分名称`latest`,字节大小36025464,样本数量6258 - 下载总大小:8191592,数据集总大小:36025464 7. **biggen_bench** - 数据拆分:拆分名称`latest`,字节大小13475179,样本数量765 - 下载总大小:5953955,数据集总大小:13475179 8. **contexthub_abductive_level1** - 数据拆分:拆分名称`latest`,字节大小1769576,样本数量360 - 下载总大小:400334,数据集总大小:1769576 9. **contexthub_abductive_level2** - 数据拆分:拆分名称`latest`,字节大小15311572,样本数量2400 - 下载总大小:4308989,数据集总大小:15311572 10. **contexthub_deductive_level1** - 数据拆分:拆分名称`latest`,字节大小2857723,样本数量600 - 下载总大小:669957,数据集总大小:2857723 11. **contexthub_deductive_level2** - 数据拆分:拆分名称`latest`,字节大小15242219,样本数量2400 - 下载总大小:4363387,数据集总大小:15242219 12. **csqa** - 数据拆分:拆分名称`latest`,字节大小5404040,样本数量1221 - 下载总大小:1065737,数据集总大小:5404040 13. **folio** - 数据拆分: - 拆分名称`latest`,字节大小1447466,样本数量203 - 拆分名称`before_fix`,字节大小1449066,样本数量203 - 下载总大小:672462,数据集总大小:2896532 14. **folio__round_2_fixes** - 数据拆分:拆分名称`latest`,字节大小1012515,样本数量203 - 下载总大小:231229,数据集总大小:1012515 15. **gpqa** - 数据拆分:拆分名称`latest`,字节大小3198070,样本数量448 - 下载总大小:1157312,数据集总大小:3198070 16. **gsm8k** - 数据拆分: - 拆分名称`latest`,字节大小7745748,样本数量1319 - 拆分名称`before_fix`,字节大小7745748,样本数量1319 - 下载总大小:3425056,数据集总大小:15491496 17. **gsm8k__round_2_fixes** - 数据拆分:拆分名称`latest`,字节大小7505501,样本数量1319 - 下载总大小:1677962,数据集总大小:7505501 18. **gsm8k_hard** - 数据拆分: - 拆分名称`latest`,字节大小7508856,样本数量1319 - 拆分名称`before_fix`,字节大小7508856,样本数量1319 - 下载总大小:3647962,数据集总大小:15017712 19. **gsm8k_hard__round_2_fixes** - 数据拆分:拆分名称`latest`,字节大小7257848,样本数量1319 - 下载总大小:1778108,数据集总大小:7257848 20. **math** - 数据拆分:拆分名称`latest`,字节大小26368107,样本数量5000 - 下载总大小:6117223,数据集总大小:26368107 21. **mm_musr** - 数据拆分:拆分名称`latest`,字节大小7408761,样本数量250 - 下载总大小:3645914,数据集总大小:7408761 22. **mmlu** - 数据拆分:拆分名称`latest`,字节大小82736658,样本数量14042 - 下载总大小:27126564,数据集总大小:82736658 23. **mmlu_pro** - 数据拆分:拆分名称`latest`,字节大小84319947,样本数量12032 - 下载总大小:32287830,数据集总大小:84319947 24. **musique_all** - 数据拆分:拆分名称`latest`,字节大小45537933,样本数量4834 - 下载总大小:20273272,数据集总大小:45537933 25. **op_musr** - 数据拆分:拆分名称`latest`,字节大小6475152,样本数量256 - 下载总大小:1413946,数据集总大小:6475152 26. **piqa** - 数据拆分:拆分名称`latest`,字节大小8831335,样本数量1838 - 下载总大小:1867992,数据集总大小:8831335 27. **siqa** - 数据拆分: - 拆分名称`latest`,字节大小8749789,样本数量1954 - 拆分名称`before_fix`,字节大小8306687,样本数量1954 - 下载总大小:3322760,数据集总大小:17056476 28. **stratqa** - 数据拆分:拆分名称`latest`,字节大小11513046,样本数量2821 - 下载总大小:1439393,数据集总大小:11513046 29. **ta_musr** - 数据拆分:拆分名称`latest`,字节大小5712472,样本数量250 - 下载总大小:2442655,数据集总大小:5712472 30. **winogrande** - 数据拆分:拆分名称`latest`,字节大小5239701,样本数量1267 - 下载总大小:860172,数据集总大小:5239701 ### 数据集配置文件映射 所有子配置与对应数据文件的映射关系如下: 1. `agieval_lsat_ar`:拆分`latest`对应文件路径`agieval_lsat_ar/latest-*` 2. `agieval_lsat_lr`:拆分`latest`对应文件路径`agieval_lsat_lr/latest-*` 3. `agieval_lsat_rc`:拆分`latest`对应文件路径`agieval_lsat_rc/latest-*` 4. `arc_challenge`:拆分`latest`对应文件路径`arc_challenge/latest-*` 5. `arc_easy`:拆分`latest`对应文件路径`arc_easy/latest-*` 6. `bbh`:拆分`latest`对应文件路径`bbh/latest-*` 7. `biggen_bench`:拆分`latest`对应文件路径`biggen_bench/latest-*` 8. `contexthub_abductive_level1`:拆分`latest`对应文件路径`contexthub_abductive_level1/latest-*` 9. `contexthub_abductive_level2`:拆分`latest`对应文件路径`contexthub_abductive_level2/latest-*` 10. `contexthub_deductive_level1`:拆分`latest`对应文件路径`contexthub_deductive_level1/latest-*` 11. `contexthub_deductive_level2`:拆分`latest`对应文件路径`contexthub_deductive_level2/latest-*` 12. `csqa`:拆分`latest`对应文件路径`csqa/latest-*` 13. `folio`:拆分`latest`对应文件路径`folio/latest-*`,拆分`before_fix`对应文件路径`folio/before_fix-*` 14. `folio__round_2_fixes`:拆分`latest`对应文件路径`folio__round_2_fixes/latest-*` 15. `gpqa`:拆分`latest`对应文件路径`gpqa/latest-*` 16. `gsm8k`:拆分`latest`对应文件路径`gsm8k/latest-*`,拆分`before_fix`对应文件路径`gsm8k/before_fix-*` 17. `gsm8k__round_2_fixes`:拆分`latest`对应文件路径`gsm8k__round_2_fixes/latest-*` 18. `gsm8k_hard`:拆分`latest`对应文件路径`gsm8k_hard/latest-*`,拆分`before_fix`对应文件路径`gsm8k_hard/before_fix-*` 19. `gsm8k_hard__round_2_fixes`:拆分`latest`对应文件路径`gsm8k_hard__round_2_fixes/latest-*` 20. `math`:拆分`latest`对应文件路径`math/latest-*` 21. `mm_musr`:拆分`latest`对应文件路径`mm_musr/latest-*` 22. `mmlu`:拆分`latest`对应文件路径`mmlu/latest-*` 23. `mmlu_pro`:拆分`latest`对应文件路径`mmlu_pro/latest-*` 24. `musique_all`:拆分`latest`对应文件路径`musique_all/latest-*` 25. `op_musr`:拆分`latest`对应文件路径`op_musr/latest-*` 26. `piqa`:拆分`latest`对应文件路径`piqa/latest-*` 27. `siqa`:拆分`latest`对应文件路径`siqa/latest-*`,拆分`before_fix`对应文件路径`siqa/before_fix-*` 28. `stratqa`:拆分`latest`对应文件路径`stratqa/latest-*` 29. `ta_musr`:拆分`latest`对应文件路径`ta_musr/latest-*` 30. `winogrande`:拆分`latest`对应文件路径`winogrande/latest-*`



