evoagentx/benchmark/__init__.py

from .nq import NQ 
from .hotpotqa import HotPotQA, AFlowHotPotQA
from .gsm8k import GSM8K, AFlowGSM8K
from .mbpp import MBPP, AFlowMBPP
from .classeval import ClassEval, AFlowClassEval
from .mbppplus import MBPPPLUS, AFlowMBPPPLUS
from .humanevalplus import HumanEvalPLUS,AFlowHumanEvalPLUS
from .math_benchmark import MATH
from .humaneval import HumanEval, AFlowHumanEval
from .livecodebench import LiveCodeBench, AFlowLiveCodeBench
from .scicode import SciCode,AFlowSciCode
from .pubmedqa import PubMedQA, AFlowPubMedQA,PubMed4ominiWorkflowQA
from .medpertqa import MedPertQA, AFlowMedPertQA,MedPert4ominiWorkflowQA
from .pertqa import PertQA, AFlowPertQA
from .hitqa import MolQA, AFlowMolQA


__all__ = [
    "NQ", 
    "HotPotQA", 
    "MBPP", 
    "GSM8K", 
    "MATH", 
    "HumanEval", 
    "LiveCodeBench", 
    "AFlowHumanEval", 
    "AFlowMBPP", 
    "AFlowHotPotQA", 
    "AFlowGSM8K"
    "SciCode",
    "MedPertQA"
]