- RL_QA
- TCMv4_format_random2000_answer_prompt
- aime24
- amc23
- aqua
- asdiv
- carp_en
- cmath
- cn_middle_school
- college_math
- eval_rm_maj_example
- gaokao2023en
- gaokao2024_I
- gaokao2024_II
- gaokao2024_mix
- gaokao_math_cloze
- gaokao_math_qa
- gsm8k
- math
- math500
- math500_answer_prompt
- mawps
- minerva_math
- mmlu_stem
- olympiadbench
- sat_math
- svamp
- tabmwp