readme.md

February 26, 2025 ยท View on GitHub

Here are the datasets list: [ "math_onlyans", "math_human", "math_mix_llama_level1", "math_mix_llama_level2", "math_mix_llama_level3", "math_mix_llama_level4", "math_mix_llama_level5", "math_mix_llama_level6", "math_mix_gemini_level1", "math_mix_gemini_level2", "math_mix_gemini_level3", "math_mix_gemini_level4", "math_mix_gemini_level5", "math_mix_gemini_level6", "math_mix_chatgpt_level1", "math_mix_chatgpt_level2", "math_mix_chatgpt_level3", "math_mix_chatgpt_level4", "math_mix_chatgpt_level5", "math_mix_chatgpt_level6", "ecqa_human", "csqa_only_ans", "obqa_only_ans", "stqa_only_ans", "stqa_human", "stqa_llama_level1", "stqa_llama_level2", "stqa_llama_level3", "stqa_llama_level4", "stqa_llama_level5", "stqa_llama_level6", "stqa_gemini_level1", "stqa_gemini_level2", "stqa_gemini_level3", "stqa_gemini_level4", "stqa_gemini_level5", "stqa_gemini_level6", "stqa_chatgpt_level1", "stqa_chatgpt_level2", "stqa_chatgpt_level3", "stqa_chatgpt_level4", "stqa_chatgpt_level5", "stqa_chatgpt_level6", "obqa_llama_level1", "obqa_llama_level2", "obqa_llama_level3", "obqa_llama_level4", "obqa_llama_level5", "obqa_llama_level6", "obqa_gemini_level1", "obqa_gemini_level2", "obqa_gemini_level3", "obqa_gemini_level4", "obqa_gemini_level5", "obqa_gemini_level6", "obqa_chatgpt_level1", "obqa_chatgpt_level2", "obqa_chatgpt_level3", "obqa_chatgpt_level4", "obqa_chatgpt_level5", "obqa_chatgpt_level6", "obqa_level3_bsm", "obqa_level3_rar", "obqa_level3_sym", "cQA_llama_level1", "cQA_llama_level2", "cQA_llama_level3", "cQA_llama_level4", "cQA_llama_level5", "cQA_llama_level6", "cQA_gemini_level1", "cQA_gemini_level2", "cQA_gemini_level3", "cQA_gemini_level4", "cQA_gemini_level5", "cQA_gemini_level6", "cQA_chatgpt_level1", "cQA_chatgpt_level2", "cQA_chatgpt_level3", "cQA_chatgpt_level4", "cQA_chatgpt_level5", "cQA_chatgpt_level6", "aqua_level5_sym", "aqua_level5_bsm", "aqua_level5_rar", "aqua_level6_bsm", "aqua_level6_rar", "gsm8k_gemma_sym", "gsm8k_bloom_sym", "gsm8k_gemma_rar", "gsm8k_bloom_rar", "gsm8k_gemma_bsm", "gsm8k_bloom_bsm", "svamp_gemma_sym", "svamp_bloom_sym", "svamp_gemma_rar", "svamp_bloom_rar", "svamp_gemma_bsm", "svamp_bloom_bsm", "auqa_human", "auqa_only_ans", "auqa_llama_level1", "auqa_llama_level2", "auqa_llama_level3", "auqa_llama_level4", "auqa_llama_level5", "auqa_llama_level6", "auqa_gemini_level1", "auqa_gemini_level2", "auqa_gemini_level3", "auqa_gemini_level4", "auqa_gemini_level5", "auqa_gemini_level6", "auqa_ChatGPT_level1", "auqa_ChatGPT_level2", "auqa_ChatGPT_level3", "auqa_ChatGPT_level4", "auqa_ChatGPT_level5", "auqa_ChatGPT_level6", "GSM8k_human", "GSM8k_only_ans", "GSM8k_llama_level1", "GSM8k_llama_level2", "GSM8k_llama_level3", "GSM8k_llama_level4", "GSM8k_llama_level5", "GSM8k_gemini_level1", "GSM8k_gemini_level2", "GSM8k_gemini_level3", "GSM8k_gemini_level4", "GSM8k_gemini_level5", "GSM8k_gemini_level6", "GSM8k_ChatGPT_level1", "GSM8k_ChatGPT_level2", "GSM8k_ChatGPT_level3", "GSM8k_ChatGPT_level4", "GSM8k_ChatGPT_level5", "GSM8k_ChatGPT_level6", "SVAMP_only_ans", "SVAMP_llama_level1", "SVAMP_llama_level2", "SVAMP_llama_level3", "SVAMP_llama_level4", "SVAMP_gemini_level1", "SVAMP_gemini_level2", "SVAMP_gemini_level3", "SVAMP_gemini_level4", "SVAMP_gemini_level5", "SVAMP_gemini_level6", "SVAMP_ChatGPT_level1", "SVAMP_ChatGPT_level2", "SVAMP_ChatGPT_level3", "SVAMP_ChatGPT_level4", "SVAMP_ChatGPT_level5", "SVAMP_ChatGPT_level6", "SVAMP_human" ]