from ais_bench.benchmark.datasets.aime2024 import * # noqa: F401, F403
from ais_bench.benchmark.datasets.aime2025 import * # noqa: F401, F403
from ais_bench.benchmark.datasets.gsm8k import * # noqa: F401, F403
from ais_bench.benchmark.datasets.ceval import * # noqa: F401, F403
from ais_bench.benchmark.datasets.boolq import * # noqa: F401, F403
from ais_bench.benchmark.datasets.mmlu import * # noqa: F401, F403
from ais_bench.benchmark.datasets.gpqa import * # noqa: F401, F403
from ais_bench.benchmark.datasets.math import * # noqa: F401, F403
from ais_bench.benchmark.datasets.drop_simple_eval import * # noqa: F401, F403
from ais_bench.benchmark.datasets.synthetic import *
from ais_bench.benchmark.datasets.mmlu_pro import * # noqa: F401, F403
from ais_bench.benchmark.datasets.humaneval import * # noqa: F401, F403
from ais_bench.benchmark.datasets.livecodebench import * # noqa: F401, F403
from ais_bench.benchmark.datasets.mgsm import * # noqa: F401, F403
from ais_bench.benchmark.datasets.piqa import *  # noqa: F401, F403
from ais_bench.benchmark.datasets.agieval import * # noqa: F401, F403
from ais_bench.benchmark.datasets.arc import * # noqa: F401, F403
from ais_bench.benchmark.datasets.winogrande import * # noqa: F401, F403
from ais_bench.benchmark.datasets.mbpp import * # noqa: F401，F403
from ais_bench.benchmark.datasets.hellaswag import * # noqa: F401, F403
from ais_bench.benchmark.datasets.triviaqa import * # noqa: F401, F403
from ais_bench.benchmark.datasets.cmmlu import * # noqa: F401, F403
from ais_bench.benchmark.datasets.humanevalx import humanevalx, humaneval_x_eval, humaneval_x_utils
from ais_bench.benchmark.datasets.humanevalx.humanevalx import * # noqa: F401, F403
from ais_bench.benchmark.datasets.bbh import * # noqa: F401, F403
from ais_bench.benchmark.datasets.race import *
from ais_bench.benchmark.datasets.textvqa import *
from ais_bench.benchmark.datasets.videobench import *
from ais_bench.benchmark.datasets.vocalsound import *
from ais_bench.benchmark.datasets.lambada import * # noqa: F401, F403
from ais_bench.benchmark.datasets.lcsts import * # noqa: F401, F403
from ais_bench.benchmark.datasets.siqa import * # noqa: F401, F403
from ais_bench.benchmark.datasets.xsum import * # noqa: F401, F403
from ais_bench.benchmark.datasets.sharegpt import *
from ais_bench.benchmark.datasets.mtbench import *
from ais_bench.benchmark.datasets.longbench import * # noqa: F401, F403
from ais_bench.benchmark.datasets.longbenchv2 import * # noqa: F401, F403
from ais_bench.benchmark.datasets.bfcl.bfcl import * # noqa: F401, F403
from ais_bench.benchmark.datasets.custom import *
from ais_bench.benchmark.datasets.infovqa import *
from ais_bench.benchmark.datasets.docvqa import *
from ais_bench.benchmark.datasets.omnidocbench.omnidocbench import *
from ais_bench.benchmark.datasets.mm_custom import *
from ais_bench.benchmark.datasets.mmmu import *
from ais_bench.benchmark.datasets.mmmu_pro import *
from ais_bench.benchmark.datasets.csl import * # noqa: F401, F403
from ais_bench.benchmark.datasets.chid import * # noqa: F401, F403
from ais_bench.benchmark.datasets.huggingface import * # noqa: F401, F403
from ais_bench.benchmark.datasets.cluewsc import * # noqa: F401, F403
from ais_bench.benchmark.datasets.eprstmt import * # noqa: F401, F403
from ais_bench.benchmark.datasets.tnews import * # noqa: F401, F403
from ais_bench.benchmark.datasets.videomme import *
from ais_bench.benchmark.datasets.mmstar import * # noqa: F401, F403
from ais_bench.benchmark.datasets.dapo_math import * # noqa: F401, F403
from ais_bench.benchmark.datasets.mooncake_trace import * # noqa: F401, F403
from ais_bench.benchmark.datasets.swebench import * # noqa: F401, F403