AI/Microsoft-fara
1
0
Fork 0
mirror of https://github.com/microsoft/fara.git synced 2026-06-10 02:54:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update __init__.py

Browse Source
This commit is contained in:
Corby Rosset
2026-04-23 01:33:57 -04:00
committed by GitHub
parent 7ea1e441c4
commit b0030f7abe
1 changed files with 1 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
webeval/src/webeval/benchmarks/__init__.py
View File

@@ -1,39 +1,9 @@
# from .assistantbench.assistantbench import AssistantBenchBenchmark
# from .custom.custom import CustomBenchmark
# from .gaia.gaia import GaiaBenchmark
from .webvoyager.webvoyager import WebVoyagerBenchmark
# from .mdm2w.mdm2w import MultimodalM2WBenchmark
# from .aurora.aurora import AuroraBenchmark
from .om2w.om2w import OnlineM2WBenchmark
from .webtailbench.webtailbench import WebTailBenchBenchmark
# from .holdout.holdout import HoldoutBenchmark
# from .deepshop.deepshop import DeepShopBenchmark
# from .browsecomp.browsecomp import BrowseCompBenchmark
# from .screenspot.screenspot_v1 import ScreenspotV1Benchmark
# from .screenspot.screenspot_v2 import ScreenspotV2Benchmark
# from .screenspot.screenspot_pro import ScreenspotProBenchmark
# from .instruction_following.instruction_following import InstructionFollowingBenchmark
# from .instruction_following.agent_harm import AgentHarmBenchmark
# from .instruction_following.visualwebbench_webqa import VisualWebBenchWebQA
# from .realeval.realeval import RealEvalBenchmark
__all__ = [
# "AssistantBenchBenchmark",
# "CustomBenchmark",
# "GaiaBenchmark",
"WebVoyagerBenchmark",
# "MultimodalM2WBenchmark",
# "AuroraBenchmark",
"OnlineM2WBenchmark",
"WebTailBenchBenchmark",
# "HoldoutBenchmark",
# "DeepShopBenchmark",
# "BrowseCompBenchmark",
# "ScreenspotV1Benchmark",
# "ScreenspotV2Benchmark",
# "ScreenspotProBenchmark",
# "InstructionFollowingBenchmark",
# "AgentHarmBenchmark",
# "VisualWebBenchWebQA",
# "RealEvalBenchmark"
"WebTailBenchBenchmark"
]