Name: haowu89/math-ai-bench-sources-middle-wo-answer
Creator: haowu89
Published: 2026-04-28 13:25:21
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/haowu89/math-ai-bench-sources-middle-wo-answer

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: aime25 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 650249 num_examples: 30 download_size: 331947 dataset_size: 650249 - config_name: aime26 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 672595 num_examples: 30 download_size: 346165 dataset_size: 672595 - config_name: apex_2025 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 261556 num_examples: 12 download_size: 147867 dataset_size: 261556 - config_name: arxivmath features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 1787887 num_examples: 72 download_size: 849047 dataset_size: 1787887 - config_name: cmimc_2025 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 866470 num_examples: 40 download_size: 433796 dataset_size: 866470 - config_name: gpqa_diamond features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 4994843 num_examples: 198 download_size: 2301842 dataset_size: 4994843 - config_name: hmmt_feb_2026 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 714011 num_examples: 33 download_size: 363268 dataset_size: 714011 - config_name: hmmt_nov_2025 features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 672313 num_examples: 30 download_size: 350896 dataset_size: 672313 - config_name: imobench features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 9064725 num_examples: 400 download_size: 4235476 dataset_size: 9064725 - config_name: olympiadbench features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 13027387 num_examples: 674 download_size: 5818610 dataset_size: 13027387 - config_name: theoremqa features: - name: problem dtype: string - name: original_solution dtype: string - name: answer dtype: string - name: source dtype: string - name: index dtype: int64 - name: model dtype: string - name: generated_solutions list: string - name: count dtype: int64 - name: context_metadata struct: - name: correctness list: bool - name: cot_num_token list: int64 - name: num_correct dtype: int64 - name: num_wrong dtype: int64 - name: source_candidate_count dtype: int64 - name: source_models list: string - name: source_traj_indices list: int64 - name: total_num_token dtype: int64 splits: - name: train num_bytes: 15060079 num_examples: 800 download_size: 6694765 dataset_size: 15060079 configs: - config_name: aime25 data_files: - split: train path: aime25/train-* - config_name: aime26 data_files: - split: train path: aime26/train-* - config_name: apex_2025 data_files: - split: train path: apex_2025/train-* - config_name: arxivmath data_files: - split: train path: arxivmath/train-* - config_name: cmimc_2025 data_files: - split: train path: cmimc_2025/train-* - config_name: gpqa_diamond data_files: - split: train path: gpqa_diamond/train-* - config_name: hmmt_feb_2026 data_files: - split: train path: hmmt_feb_2026/train-* - config_name: hmmt_nov_2025 data_files: - split: train path: hmmt_nov_2025/train-* - config_name: imobench data_files: - split: train path: imobench/train-* - config_name: olympiadbench data_files: - split: train path: olympiadbench/train-* - config_name: theoremqa data_files: - split: train path: theoremqa/train-* ---

应用场景：